diff options
Diffstat (limited to 'megapixels')
29 files changed, 1730 insertions, 575 deletions
diff --git a/megapixels/app/utils/path_utils.py b/megapixels/app/models/data_store.py index b0262ea0..244aba60 100644 --- a/megapixels/app/utils/path_utils.py +++ b/megapixels/app/models/data_store.py @@ -21,12 +21,27 @@ class DataStore: def metadata(self, enum_type): return join(self.dir_metadata, f'{enum_type.name.lower()}.csv') - def face_image(self, subdir, fn, ext): + def metadata(self, enum_type): + return join(self.dir_metadata) + + def media_images_original(self): + return join(self.dir_media, 'original') + + def face(self, subdir, fn, ext): return join(self.dir_media, 'original', subdir, f'{fn}.{ext}') - def face_image_crop(self, subdir, fn, ext): + def face_crop(self, subdir, fn, ext): return join(self.dir_media, 'cropped', subdir, f'{fn}.{ext}') + def face_uuid(self, uuid, ext): + return join(self.dir_media, 'uuid',f'{uuid}.{ext}') + + def face_crop_uuid(self, uuid, ext): + return join(self.dir_media, 'uuid', f'{uuid}.{ext}') + + def uuid_dir(self): + return join(self.dir_media, 'uuid') + class DataStoreS3: # S3 server @@ -37,11 +52,11 @@ class DataStoreS3: def metadata(self, opt_metadata_type, ext='csv'): return join(self._dir_metadata, f'{opt_metadata_type.name.lower()}.{ext}') - def face_image(self, opt_uuid, ext='jpg'): + def face(self, opt_uuid, ext='jpg'): #return join(self._dir_media, 'original', f'{opt_uuid}.{ext}') return join(self._dir_media, f'{opt_uuid}.{ext}') - def face_image_crop(self, opt_uuid, ext='jpg'): + def face_crop(self, opt_uuid, ext='jpg'): # not currently using? return join(self._dir_media, 'cropped', f'{opt_uuid}.{ext}') diff --git a/megapixels/app/models/dataset.py b/megapixels/app/models/dataset.py index 11d568a5..35e10465 100644 --- a/megapixels/app/models/dataset.py +++ b/megapixels/app/models/dataset.py @@ -2,6 +2,7 @@ Dataset model: container for all CSVs about a dataset """ import os +import sys from os.path import join from pathlib import Path import logging @@ -12,7 +13,8 @@ import numpy as np from app.settings import app_cfg as cfg from app.settings import types from app.models.bbox import BBox -from app.utils import file_utils, im_utils, path_utils +from app.utils import file_utils, im_utils +from app.models.data_store import DataStore, DataStoreS3 from app.utils.logger_utils import Logger # ------------------------------------------------------------------------- @@ -21,36 +23,70 @@ from app.utils.logger_utils import Logger class Dataset: - def __init__(self, opt_dataset_type, opt_data_store=types.DataStore.NAS): + def __init__(self, opt_data_store, opt_dataset_type): self._dataset_type = opt_dataset_type # enum type self.log = Logger.getLogger() self._metadata = {} self._face_vectors = [] self._nullframe = pd.DataFrame() # empty placeholder - self.data_store = path_utils.DataStore(opt_data_store, self._dataset_type) - self.data_store_s3 = path_utils.DataStoreS3(self._dataset_type) + self.data_store = DataStore(opt_data_store, self._dataset_type) + self.data_store_s3 = DataStoreS3(self._dataset_type) - def load(self, opt_data_store): - '''Loads all CSV files into (dict) of DataFrames''' - for metadata_type in types.Metadata: - self.log.info(f'load metadata: {metadata_type}') - fp_csv = self.data_store.metadata(metadata_type) - self.log.info(f'loading: {fp_csv}') - if Path(fp_csv).is_file(): - self._metadata[metadata_type] = pd.read_csv(fp_csv).set_index('index') - if metadata_type == types.Metadata.FACE_VECTOR: - # convert DataFrame to list of floats - self._face_vecs = self.df_to_vec_list(self._metadata[metadata_type]) - self._metadata[metadata_type].drop('vec', axis=1, inplace=True) - else: - self.log.error('File not found: {fp_csv}. Replaced with empty DataFrame') - self._metadata[metadata_type] = self._nullframe - self.log.info('finished loading') + def load_face_vectors(self): + metadata_type = types.Metadata.FACE_VECTOR + fp_csv = self.data_store.metadata(metadata_type) + self.log.info(f'loading: {fp_csv}') + if Path(fp_csv).is_file(): + self._metadata[metadata_type] = pd.read_csv(fp_csv).set_index('index') + # convert DataFrame to list of floats + self._face_vectors = self.df_vecs_to_dict(self._metadata[metadata_type]) + self._face_vector_idxs = self.df_vec_idxs_to_dict(self._metadata[metadata_type]) + self.log.info(f'build face vector dict: {len(self._face_vectors)}') + # remove the face vector column, it can be several GB of memory + self._metadata[metadata_type].drop('vec', axis=1, inplace=True) + else: + self.log.error(f'File not found: {fp_csv}. Exiting.') + sys.exit() + + def load_records(self): + metadata_type = types.Metadata.FILE_RECORD + fp_csv = self.data_store.metadata(metadata_type) + self.log.info(f'loading: {fp_csv}') + if Path(fp_csv).is_file(): + self._metadata[metadata_type] = pd.read_csv(fp_csv).set_index('index') + else: + self.log.error(f'File not found: {fp_csv}. Exiting.') + sys.exit() + + def load_identities(self): + metadata_type = types.Metadata.IDENTITY + fp_csv = self.data_store.metadata(metadata_type) + self.log.info(f'loading: {fp_csv}') + if Path(fp_csv).is_file(): + self._metadata[metadata_type] = pd.read_csv(fp_csv).set_index('index') + else: + self.log.error(f'File not found: {fp_csv}. Exiting.') + sys.exit() def metadata(self, opt_metadata_type): - return self._metadata.get(opt_metadata_type, self._nullframe) + return self._metadata.get(opt_metadata_type, None) - def roi_idx_to_record(self, vector_index): + def index_to_record(self, index): + # get record meta + df_record = self._metadata[types.Metadata.FILE_RECORD] + ds_record = df_record.iloc[index] + identity_index = ds_record.identity_index + # get identity meta + df_identity = self._metadata[types.Metadata.IDENTITY] + # future datasets can have multiple identities per images + ds_identities = df_identity.iloc[identity_index] + # get filepath and S3 url + fp_im = self.data_store.face_image(ds_record.subdir, ds_record.fn, ds_record.ext) + s3_url = self.data_store_s3.face_image(ds_record.uuid) + image_record = ImageRecord(ds_record, fp_im, s3_url, ds_identities=ds_identities) + return image_record + + def vector_to_record(self, record_index): '''Accumulates image and its metadata''' df_face_vector = self._metadata[types.Metadata.FACE_VECTOR] ds_face_vector = df_face_vector.iloc[vector_index] @@ -80,7 +116,7 @@ class Dataset: image_record = ImageRecord(image_index, sha256, uuid, bbox, fp_im, fp_url) # now get the identity index (if available) identity_index = ds_sha256.identity_index - if identity_index: + if identity_index > -1: # then use the identity index to get the identity meta df_identity = df_filepath = self._metadata[types.Metadata.IDENTITY] ds_identity = df_identity.iloc[identity_index] @@ -95,27 +131,38 @@ class Dataset: identity = Identity(identity_index, name=name, desc=desc, gender=gender, n_images=n_images, url=url, age=age, nationality=nationality) image_record.identity = identity + else: + self.log.info(f'no identity index: {ds_sha256}') return image_record - def matches(self, query_vec, n_results=5, threshold=0.5): + def find_matches(self, query_vec, n_results=5, threshold=0.6): image_records = [] # list of image matches w/identity if available # find most similar feature vectors indexes - match_idxs = self.similar(query_vec, n_results, threshold) + #match_idxs = self.similar(query_vec, n_results, threshold) + sim_scores = np.linalg.norm(np.array([query_vec]) - np.array(self._face_vectors), axis=1) + match_idxs = np.argpartition(sim_scores, n_results)[:n_results] + for match_idx in match_idxs: # get the corresponding face vector row - image_record = self.roi_idx_to_record(match_idx) - results.append(image_record) + roi_index = self._face_vector_roi_idxs[match_idx] + self.log.debug(f'find match index: {match_idx}, --> roi_index: {roi_index}') + image_record = self.roi_idx_to_record(roi_index) + image_records.append(image_record) return image_records # ---------------------------------------------------------------------- # utilities - def df_to_vec_list(self, df): + def df_vecs_to_dict(self, df): # convert the DataFrame CSV to float list of vecs - vecs = [list(map(float,x.vec.split(','))) for x in df.itertuples()] - return vecs + return [list(map(float,x.vec.split(','))) for x in df.itertuples()] + + def df_vec_idxs_to_dict(self, df): + # convert the DataFrame CSV to float list of vecs + #return [x.roi_index for x in df.itertuples()] + return [x.image_index for x in df.itertuples()] def similar(self, query_vec, n_results): '''Finds most similar N indices of query face vector @@ -124,45 +171,42 @@ class Dataset: :returns (list) of (int) indices ''' # uses np.linalg based on the ageitgey/face_recognition code - vecs_sim_scores = np.linalg.norm(np.array([query_vec]) - np.array(self._face_vectors), axis=1) - top_idxs = np.argpartition(vecs_sim_scores, n_results)[:n_results] + return top_idxs class ImageRecord: - def __init__(self, image_index, sha256, uuid, bbox, filepath, url): - self.image_index = image_index - self.sha256 = sha256 - self.uuid = uuid - self.bbox = bbox - self.filepath = filepath + def __init__(self, ds_record, fp, url, ds_rois=None, ds_identities=None): + # maybe more other meta will go there + self.image_index = ds_record.index + self.sha256 = ds_record.sha256 + self.uuid = ds_record.uuid + self.filepath = fp self.url = url - self._identity = None + self._identities = [] + # image records contain ROIs + # ROIs are linked to identities + + #self._identities = [Identity(x) for x in ds_identities] @property - def identity(self): + def identity(self, index): return self._identity - @identity.setter - def identity(self, value): - self._identity = value - def summarize(self): '''Summarizes data for debugging''' log = Logger.getLogger() log.info(f'filepath: {self.filepath}') log.info(f'sha256: {self.sha256}') log.info(f'UUID: {self.uuid}') - log.info(f'BBox: {self.bbox}') - log.info(f's3 url: {self.url}') - if self._identity: - log.info(f'name: {self._identity.name}') - log.info(f'age: {self._identity.age}') - log.info(f'gender: {self._identity.gender}') - log.info(f'nationality: {self._identity.nationality}') - log.info(f'images: {self._identity.n_images}') + log.info(f'S3 url: {self.url}') + for identity in self._identities: + log.info(f'fullname: {identity.fullname}') + log.info(f'description: {identity.description}') + log.info(f'gender: {identity.gender}') + log.info(f'images: {identity.n_images}') class Identity: diff --git a/megapixels/app/settings/app_cfg.py b/megapixels/app/settings/app_cfg.py index 50eaf576..0c28b315 100644 --- a/megapixels/app/settings/app_cfg.py +++ b/megapixels/app/settings/app_cfg.py @@ -75,6 +75,7 @@ DIR_COMMANDS_DATASETS = 'commands/datasets' DIR_COMMANDS_FAISS = 'commands/faiss' DIR_COMMANDS_MISC = 'commands/misc' DIR_COMMANDS_SITE = 'commands/site' +DIR_COMMANDS_DEMO = 'commands/demo' # ----------------------------------------------------------------------------- # Filesystem settings @@ -86,9 +87,16 @@ CKPT_ZERO_PADDING = 9 HASH_TREE_DEPTH = 3 HASH_BRANCH_SIZE = 3 -DLIB_FACEREC_JITTERS = 5 # number of face recognition jitters +DLIB_FACEREC_JITTERS = 25 # number of face recognition jitters DLIB_FACEREC_PADDING = 0.25 # default dlib +POSE_MINMAX_YAW = (-25,25) +POSE_MINMAX_ROLL = (-15,15) +POSE_MINMAX_PITCH = (-10,10) + +POSE_MINMAX_YAW = (-40,40) +POSE_MINMAX_ROLL = (-35,35) +POSE_MINMAX_PITCH = (-25,25) # ----------------------------------------------------------------------------- # Logging options exposed for custom click Params # ----------------------------------------------------------------------------- diff --git a/megapixels/app/settings/types.py b/megapixels/app/settings/types.py index 685744aa..754be618 100644 --- a/megapixels/app/settings/types.py +++ b/megapixels/app/settings/types.py @@ -45,7 +45,7 @@ class LogLevel(Enum): # -------------------------------------------------------------------- class Metadata(Enum): - IDENTITY, FILEPATH, SHA256, UUID, FACE_VECTOR, FACE_POSE, FACE_ROI = range(7) + IDENTITY, FILE_RECORD, FACE_VECTOR, FACE_POSE, FACE_ROI = range(5) class Dataset(Enum): LFW, VGG_FACE2 = range(2) diff --git a/megapixels/app/utils/file_utils.py b/megapixels/app/utils/file_utils.py index 80239fe2..5c7b39d1 100644 --- a/megapixels/app/utils/file_utils.py +++ b/megapixels/app/utils/file_utils.py @@ -40,10 +40,16 @@ log = logging.getLogger(cfg.LOGGER_NAME) # File I/O read/write little helpers # ------------------------------------------ -def glob_multi(dir_in, exts): +def glob_multi(dir_in, exts, recursive=False): files = [] - for e in exts: - files.append(glob(join(dir_in, '*.{}'.format(e)))) + for ext in exts: + if recursive: + fp_glob = join(dir_in, '**/*.{}'.format(ext)) + log.info(f'glob {fp_glob}') + files += glob(fp_glob, recursive=True) + else: + fp_glob = join(dir_in, '*.{}'.format(ext)) + files += glob(fp_glob) return files diff --git a/megapixels/cli_demo.py b/megapixels/cli_demo.py new file mode 100644 index 00000000..703db856 --- /dev/null +++ b/megapixels/cli_demo.py @@ -0,0 +1,35 @@ +# -------------------------------------------------------- +# add/edit commands in commands/datasets directory +# -------------------------------------------------------- + +import click + +from app.settings import app_cfg as cfg +from app.utils import logger_utils +from app.models.click_factory import ClickSimple + +# click cli factory +cc = ClickSimple.create(cfg.DIR_COMMANDS_DEMO) + +# -------------------------------------------------------- +# CLI +# -------------------------------------------------------- +@click.group(cls=cc, chain=False) +@click.option('-v', '--verbose', 'verbosity', count=True, default=4, + show_default=True, + help='Verbosity: -v DEBUG, -vv INFO, -vvv WARN, -vvvv ERROR, -vvvvv CRITICAL') +@click.pass_context +def cli(ctx, **kwargs): + """\033[1m\033[94mMegaPixels: Dataset Image Scripts\033[0m + """ + ctx.opts = {} + # init logger + logger_utils.Logger.create(verbosity=kwargs['verbosity']) + + +# -------------------------------------------------------- +# Entrypoint +# -------------------------------------------------------- +if __name__ == '__main__': + cli() + diff --git a/megapixels/commands/cv/cluster.py b/megapixels/commands/cv/cluster.py index 94334133..419091a0 100644 --- a/megapixels/commands/cv/cluster.py +++ b/megapixels/commands/cv/cluster.py @@ -23,20 +23,20 @@ from app.utils.logger_utils import Logger @click.pass_context def cli(ctx, opt_data_store, opt_dataset, opt_metadata): """Display image info""" - - # cluster the embeddings -print("[INFO] clustering...") -clt = DBSCAN(metric="euclidean", n_jobs=args["jobs"]) -clt.fit(encodings) - -# determine the total number of unique faces found in the dataset -labelIDs = np.unique(clt.labels_) -numUniqueFaces = len(np.where(labelIDs > -1)[0]) -print("[INFO] # unique faces: {}".format(numUniqueFaces)) + + # cluster the embeddings + print("[INFO] clustering...") + clt = DBSCAN(metric="euclidean", n_jobs=args["jobs"]) + clt.fit(encodings) + + # determine the total number of unique faces found in the dataset + labelIDs = np.unique(clt.labels_) + numUniqueFaces = len(np.where(labelIDs > -1)[0]) + print("[INFO] # unique faces: {}".format(numUniqueFaces)) # load and display image im = cv.imread(fp_im) cv.imshow('', im) - + while True: k = cv.waitKey(1) & 0xFF if k == 27 or k == ord('q'): # ESC diff --git a/megapixels/commands/cv/rois_to_pose.py b/megapixels/commands/cv/face_pose.py index 3877cecf..e7ffb7ac 100644 --- a/megapixels/commands/cv/rois_to_pose.py +++ b/megapixels/commands/cv/face_pose.py @@ -9,14 +9,22 @@ from app.utils import click_utils from app.settings import app_cfg as cfg @click.command() -@click.option('-i', '--input', 'opt_fp_files', required=True, - help='Input ROI CSV') -@click.option('-r', '--rois', 'opt_fp_rois', required=True, - help='Input ROI CSV') -@click.option('-m', '--media', 'opt_dir_media', required=True, - help='Input media directory') -@click.option('-o', '--output', 'opt_fp_out', required=True, - help='Output CSV') +@click.option('-i', '--input', 'opt_fp_in', default=None, + help='Override enum input filename CSV') +@click.option('-o', '--output', 'opt_fp_out', default=None, + help='Override enum output filename CSV') +@click.option('-m', '--media', 'opt_dir_media', default=None, + help='Override enum media directory') +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.SSD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) @click.option('--size', 'opt_size', type=(int, int), default=(300, 300), help='Output image size') @@ -27,7 +35,7 @@ from app.settings import app_cfg as cfg @click.option('-d', '--display', 'opt_display', is_flag=True, help='Display image for debugging') @click.pass_context -def cli(ctx, opt_fp_files, opt_fp_rois, opt_dir_media, opt_fp_out, opt_size, +def cli(ctx, opt_fp_in, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size, opt_slice, opt_force, opt_display): """Converts ROIs to pose: roll, yaw, pitch""" @@ -47,42 +55,47 @@ def cli(ctx, opt_fp_files, opt_fp_rois, opt_dir_media, opt_fp_out, opt_size, from app.utils import logger_utils, file_utils, im_utils from app.processors.face_landmarks import LandmarksDLIB from app.processors.face_pose import FacePoseDLIB + from app.models.data_store import DataStore # ------------------------------------------------- # init here log = logger_utils.Logger.getLogger() + + # set data_store + data_store = DataStore(opt_data_store, opt_dataset) + + # get filepath out + fp_out = data_store.metadata(types.Metadata.FACE_POSE) if opt_fp_out is None else opt_fp_out + if not opt_force and Path(fp_out).exists(): + log.error('File exists. Use "-f / --force" to overwite') + return # init face processors face_pose = FacePoseDLIB() face_landmarks = LandmarksDLIB() - # load datra - df_files = pd.read_csv(opt_fp_files) - df_rois = pd.read_csv(opt_fp_rois) - - if not opt_force and Path(opt_fp_out).exists(): - log.error('File exists. Use "-f / --force" to overwite') - return - + # load filepath data + fp_record = data_store.metadata(types.Metadata.FILE_RECORD) + df_record = pd.read_csv(fp_record).set_index('index') + # load ROI data + fp_roi = data_store.metadata(types.Metadata.FACE_ROI) + df_roi = pd.read_csv(fp_roi).set_index('index') + # slice if you want if opt_slice: - df_rois = df_rois[opt_slice[0]:opt_slice[1]] - - # ------------------------------------------------- - # process here - df_img_groups = df_rois.groupby('image_index') + df_roi = df_roi[opt_slice[0]:opt_slice[1]] + # group by image index (speedup if multiple faces per image) + df_img_groups = df_roi.groupby('record_index') log.debug('processing {:,} groups'.format(len(df_img_groups))) - + # store poses and convert to DataFrame poses = [] # iterate - #for df_roi_group_idx, df_roi_group in tqdm(df_roi_groups): - for image_index, df_img_group in tqdm(df_img_groups): + for record_index, df_img_group in tqdm(df_img_groups): # make fp - #image_index = df_roi_group.image_index.values[0] - pds_file = df_files.iloc[image_index] - fp_im = join(opt_dir_media, pds_file.subdir, '{}.{}'.format(pds_file.fn, pds_file.ext)) + ds_record = df_record.iloc[record_index] + fp_im = data_store.face_image(ds_record.subdir, ds_record.fn, ds_record.ext) im = cv.imread(fp_im) # get bbox x = df_img_group.x.values[0] @@ -116,12 +129,12 @@ def cli(ctx, opt_fp_files, opt_fp_rois, opt_dir_media, opt_fp_out, opt_size, break # add image index and append to result CSV data - pose_degrees['image_index'] = image_index + pose_degrees['record_index'] = record_index poses.append(pose_degrees) # save date - file_utils.mkdirs(opt_fp_out) + file_utils.mkdirs(fp_out) df = pd.DataFrame.from_dict(poses) df.index.name = 'index' - df.to_csv(opt_fp_out)
\ No newline at end of file + df.to_csv(fp_out)
\ No newline at end of file diff --git a/megapixels/commands/cv/files_to_rois.py b/megapixels/commands/cv/face_roi.py index 1aaf991c..d7248aee 100644 --- a/megapixels/commands/cv/files_to_rois.py +++ b/megapixels/commands/cv/face_roi.py @@ -12,12 +12,22 @@ from app.settings import app_cfg as cfg color_filters = {'color': 1, 'gray': 2, 'all': 3} @click.command() -@click.option('-i', '--input', 'opt_fp_in', required=True, - help='Input CSV (eg image_files.csv)') -@click.option('-m', '--media', 'opt_dir_media', required=True, - help='Input media directory') -@click.option('-o', '--output', 'opt_fp_out', required=True, - help='Output CSV') +@click.option('-i', '--input', 'opt_fp_in', default=None, + help='Override enum input filename CSV') +@click.option('-o', '--output', 'opt_fp_out', default=None, + help='Override enum output filename CSV') +@click.option('-m', '--media', 'opt_dir_media', default=None, + help='Override enum media directory') +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.SSD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) @click.option('--size', 'opt_size', type=(int, int), default=(300, 300), help='Output image size') @@ -40,10 +50,10 @@ color_filters = {'color': 1, 'gray': 2, 'all': 3} @click.option('--color', 'opt_color_filter', type=click.Choice(color_filters.keys()), default='all', help='Filter to keep color or grayscale images (color = keep color') -@click.option('--largest', 'opt_largest', is_flag=True, +@click.option('--largest/--all-faces', 'opt_largest', is_flag=True, default=True, help='Only keep largest face') @click.pass_context -def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_size, opt_detector_type, +def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_data_store, opt_dataset, opt_size, opt_detector_type, opt_gpu, opt_conf_thresh, opt_pyramids, opt_slice, opt_display, opt_force, opt_color_filter, opt_largest): """Converts frames with faces to CSV of ROIs""" @@ -61,17 +71,24 @@ def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_size, opt_detector_type, import pandas as pd from app.utils import logger_utils, file_utils, im_utils - from app.processors import face_detector + from app.processors import face_detector + from app.models.data_store import DataStore # ------------------------------------------------- # init here log = logger_utils.Logger.getLogger() - if not opt_force and Path(opt_fp_out).exists(): + # set data_store + data_store = DataStore(opt_data_store, opt_dataset) + + # get filepath out + fp_out = data_store.metadata(types.Metadata.FACE_ROI) if opt_fp_out is None else opt_fp_out + if not opt_force and Path(fp_out).exists(): log.error('File exists. Use "-f / --force" to overwite') return + # set detector if opt_detector_type == types.FaceDetectNet.CVDNN: detector = face_detector.DetectorCVDNN() elif opt_detector_type == types.FaceDetectNet.DLIB_CNN: @@ -85,22 +102,20 @@ def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_size, opt_detector_type, return - # ------------------------------------------------- - # process here - color_filter = color_filters[opt_color_filter] - # get list of files to process - df_files = pd.read_csv(opt_fp_in).set_index('index') - + fp_in = data_store.metadata(types.Metadata.FILE_RECORD) if opt_fp_in is None else opt_fp_in + df_records = pd.read_csv(fp_in).set_index('index') if opt_slice: - df_files = df_files[opt_slice[0]:opt_slice[1]] - log.debug('processing {:,} files'.format(len(df_files))) + df_records = df_records[opt_slice[0]:opt_slice[1]] + log.debug('processing {:,} files'.format(len(df_records))) + # filter out grayscale + color_filter = color_filters[opt_color_filter] data = [] - for df_file in tqdm(df_files.itertuples(), total=len(df_files)): - fp_im = join(opt_dir_media, str(df_file.subdir), f'{df_file.fn}.{df_file.ext}') + for df_record in tqdm(df_records.itertuples(), total=len(df_records)): + fp_im = data_store.face_image(str(df_record.subdir), str(df_record.fn), str(df_record.ext)) im = cv.imread(fp_im) # filter out color or grayscale iamges @@ -123,7 +138,7 @@ def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_size, opt_detector_type, for bbox in bboxes: roi = { - 'image_index': int(df_file.Index), + 'record_index': int(df_record.Index), 'x': bbox.x, 'y': bbox.y, 'w': bbox.w, @@ -150,7 +165,7 @@ def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_size, opt_detector_type, break # save date - file_utils.mkdirs(opt_fp_out) + file_utils.mkdirs(fp_out) df = pd.DataFrame.from_dict(data) df.index.name = 'index' - df.to_csv(opt_fp_out)
\ No newline at end of file + df.to_csv(fp_out)
\ No newline at end of file diff --git a/megapixels/commands/cv/rois_to_vecs.py b/megapixels/commands/cv/face_vector.py index 525f4404..203f73eb 100644 --- a/megapixels/commands/cv/rois_to_vecs.py +++ b/megapixels/commands/cv/face_vector.py @@ -9,14 +9,20 @@ from app.utils import click_utils from app.settings import app_cfg as cfg @click.command() -@click.option('-i', '--input', 'opt_fp_files', required=True, - help='Input file meta CSV') -@click.option('-r', '--rois', 'opt_fp_rois', required=True, - help='Input ROI CSV') -@click.option('-m', '--media', 'opt_dir_media', required=True, - help='Input media directory') -@click.option('-o', '--output', 'opt_fp_out', required=True, - help='Output CSV') +@click.option('-o', '--output', 'opt_fp_out', default=None, + help='Override enum output filename CSV') +@click.option('-m', '--media', 'opt_dir_media', default=None, + help='Override enum media directory') +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.SSD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) @click.option('--size', 'opt_size', type=(int, int), default=(300, 300), help='Output image size') @@ -31,7 +37,7 @@ from app.settings import app_cfg as cfg @click.option('-g', '--gpu', 'opt_gpu', default=0, help='GPU index') @click.pass_context -def cli(ctx, opt_fp_files, opt_fp_rois, opt_dir_media, opt_fp_out, opt_size, +def cli(ctx, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size, opt_slice, opt_force, opt_gpu, opt_jitters, opt_padding): """Converts face ROIs to vectors""" @@ -48,6 +54,7 @@ def cli(ctx, opt_fp_files, opt_fp_rois, opt_dir_media, opt_fp_out, opt_size, import pandas as pd from app.models.bbox import BBox + from app.models.data_store import DataStore from app.utils import logger_utils, file_utils, im_utils from app.processors import face_recognition @@ -56,24 +63,30 @@ def cli(ctx, opt_fp_files, opt_fp_rois, opt_dir_media, opt_fp_out, opt_size, # init here log = logger_utils.Logger.getLogger() + # set data_store + data_store = DataStore(opt_data_store, opt_dataset) + + # get filepath out + fp_out = data_store.metadata(types.Metadata.FACE_VECTOR) if opt_fp_out is None else opt_fp_out + if not opt_force and Path(fp_out).exists(): + log.error('File exists. Use "-f / --force" to overwite') + return # init face processors facerec = face_recognition.RecognitionDLIB() # load data - df_file_meta = pd.read_csv(opt_fp_files) - df_rois = pd.read_csv(opt_fp_rois) + fp_record = data_store.metadata(types.Metadata.FILE_RECORD) + df_record = pd.read_csv(fp_record).set_index('index') + fp_roi = data_store.metadata(types.Metadata.FACE_ROI) + df_roi = pd.read_csv(fp_roi).set_index('index') - if not opt_force and Path(opt_fp_out).exists(): - log.error('File exists. Use "-f / --force" to overwite') - return - if opt_slice: - df_rois = df_rois[opt_slice[0]:opt_slice[1]] + df_roi = df_roi[opt_slice[0]:opt_slice[1]] # ------------------------------------------------- # process here - df_img_groups = df_rois.groupby('image_index') + df_img_groups = df_roi.groupby('record_index') log.debug('processing {:,} groups'.format(len(df_img_groups))) vecs = [] @@ -81,8 +94,11 @@ def cli(ctx, opt_fp_files, opt_fp_rois, opt_dir_media, opt_fp_out, opt_size, for image_index, df_img_group in tqdm(df_img_groups): # make fp roi_index = df_img_group.index.values[0] - file_meta = df_file_meta.iloc[image_index] # locate image meta - fp_im = join(opt_dir_media, file_meta.subdir, '{}.{}'.format(file_meta.fn, file_meta.ext)) + # log.debug(f'roi_index: {roi_index}, image_index: {image_index}') + ds_file = df_record.loc[roi_index] # locate image meta + #ds_file = df_record.loc['index', image_index] # locate image meta + + fp_im = data_store.face_image(str(ds_file.subdir), str(ds_file.fn), str(ds_file.ext)) im = cv.imread(fp_im) # get bbox x = df_img_group.x.values[0] @@ -103,7 +119,7 @@ def cli(ctx, opt_fp_files, opt_fp_rois, opt_dir_media, opt_fp_out, opt_size, # save date - file_utils.mkdirs(opt_fp_out) df = pd.DataFrame.from_dict(vecs) df.index.name = 'index' - df.to_csv(opt_fp_out)
\ No newline at end of file + file_utils.mkdirs(fp_out) + df.to_csv(fp_out)
\ No newline at end of file diff --git a/megapixels/commands/datasets/add_uuid.py b/megapixels/commands/datasets/add_uuid.py deleted file mode 100644 index 9c14c0e3..00000000 --- a/megapixels/commands/datasets/add_uuid.py +++ /dev/null @@ -1,44 +0,0 @@ -import click - -from app.settings import types -from app.utils import click_utils -from app.settings import app_cfg as cfg -from app.utils.logger_utils import Logger - -log = Logger.getLogger() - -@click.command() -@click.option('-i', '--input', 'opt_fp_in', required=True, - help='Input directory') -@click.option('-o', '--output', 'opt_fp_out', - help='Output directory') -@click.option('-f', '--force', 'opt_force', is_flag=True, - help='Force overwrite file') -@click.pass_context -def cli(ctx, opt_fp_in, opt_fp_out, opt_force): - """Appends UUID to records CSV""" - - from glob import glob - from os.path import join - from pathlib import Path - import base64 - import uuid - - from tqdm import tqdm - import pandas as pd - - if not opt_force and Path(opt_fp_out).exists(): - log.error('File exists. Use "-f / --force" to overwite') - return - - # load names - df_records = pd.read_csv(opt_fp_in) - records = df_records.to_dict('index') - # append a UUID to every entry - for idx, item in records.items(): - records[idx]['uuid'] = uuid.uuid4() - # save to csv - df_uuid = pd.DataFrame.from_dict(list(records.values())) # ignore the indices - df_uuid.to_csv(opt_fp_out, index=False) - - log.info('done')
\ No newline at end of file diff --git a/megapixels/commands/datasets/filter_by_pose.py b/megapixels/commands/datasets/filter_by_pose.py new file mode 100644 index 00000000..a588b18e --- /dev/null +++ b/megapixels/commands/datasets/filter_by_pose.py @@ -0,0 +1,96 @@ +import click + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg +from app.utils.logger_utils import Logger + +log = Logger.getLogger() + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', default=None, + help='Override enum input filename CSV') +@click.option('-o', '--output', 'opt_fp_out', default=None, + help='Override enum output filename CSV') +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.SSD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--yaw', 'opt_yaw', type=(float, float), default=cfg.POSE_MINMAX_YAW, + help='Yaw (min, max)') +@click.option('--roll', 'opt_roll', type=(float, float), default=cfg.POSE_MINMAX_ROLL, + help='Roll (min, max)') +@click.option('--pitch', 'opt_pitch', type=(float, float), default=cfg.POSE_MINMAX_PITCH, + help='Pitch (min, max)') +@click.pass_context +def cli(ctx, opt_fp_in, opt_fp_out, opt_data_store, opt_dataset, opt_yaw, opt_roll, opt_pitch): + """Filter out exaggerated poses""" + + import sys + from os.path import join + from pathlib import Path + import shutil + from datetime import datetime + + import pandas as pd + from tqdm import tqdm + + from app.models.data_store import DataStore + from app.utils import file_utils + + # create date store + data_store = DataStore(opt_data_store, opt_dataset) + # load pose + fp_pose = data_store.metadata(types.Metadata.FACE_POSE) + df_pose = pd.read_csv(fp_pose).set_index('index') + # load roi + fp_roi = data_store.metadata(types.Metadata.FACE_ROI) + df_roi = pd.read_csv(fp_roi).set_index('index') + # load filepath + fp_record = data_store.metadata(types.Metadata.FILE_RECORD) + df_record = pd.read_csv(fp_record).set_index('index') + # debug + log.info('Processing {:,} rows'.format(len(df_pose))) + n_rows = len(df_record) + + # filter out extreme poses + invalid_indices = [] + for ds_pose in tqdm(df_pose.itertuples(), total=len(df_pose)): + if ds_pose.yaw < opt_yaw[0] or ds_pose.yaw > opt_yaw[1] \ + and ds_pose.roll < opt_roll[0] or ds_pose.roll > opt_roll[1] \ + and ds_pose.pitch < opt_pitch[0] or ds_pose.pitch > opt_pitch[1]: + invalid_indices.append(ds_pose.Index) # unique file indexs + + # filter out valid/invalid + log.info(f'indices 0-20: {invalid_indices[:20]}') + log.info(f'Removing {len(invalid_indices)} invalid indices...') + df_record = df_record.drop(df_record.index[invalid_indices]) + df_roi = df_roi.drop(df_roi.index[invalid_indices]) + df_pose = df_pose.drop(df_pose.index[invalid_indices]) + log.info(f'Removed {n_rows - len(df_record)}') + + # move file to make backup + dir_bkup = join(Path(fp_pose).parent, f'backup_{datetime.now():%Y%m%d_%M%S}') + file_utils.mkdirs(dir_bkup) + # move files to backup + shutil.move(fp_record, join(dir_bkup, Path(fp_record).name)) + shutil.move(fp_roi, join(dir_bkup, Path(fp_roi).name)) + shutil.move(fp_pose, join(dir_bkup, Path(fp_pose).name)) + # resave file records + df_record = df_record.reset_index(drop=True) + df_record.index.name = 'index' + df_record.to_csv(fp_record) + # resave ROI + df_roi = df_roi.reset_index(drop=True) + df_roi.index.name = 'index' + df_roi.to_csv(fp_roi) + # resave pose + df_pose = df_pose.reset_index(drop=True) + df_pose.index.name = 'index' + df_pose.to_csv(fp_pose) diff --git a/megapixels/commands/datasets/filter_poses.py b/megapixels/commands/datasets/filter_poses.py deleted file mode 100644 index 304eeff2..00000000 --- a/megapixels/commands/datasets/filter_poses.py +++ /dev/null @@ -1,76 +0,0 @@ -import click - -from app.settings import types -from app.utils import click_utils -from app.settings import app_cfg as cfg -from app.utils.logger_utils import Logger - -log = Logger.getLogger() - -@click.command() -@click.option('-i', '--input', 'opt_fp_in', required=True, - help='Input directory') -@click.option('-o', '--output', 'opt_fp_out', required=True, - help='Output directory') -@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), - help='Slice list of files') -@click.option('-f', '--force', 'opt_force', is_flag=True, - help='Force overwrite file') -@click.option('--yaw', 'opt_yaw', type=(float, float), default=(-25,25), - help='Yaw (min, max)') -@click.option('--roll', 'opt_roll', type=(float, float), default=(-15,15), - help='Roll (min, max)') -@click.option('--pitch', 'opt_pitch', type=(float, float), default=(-10,10), - help='Pitch (min, max)') -@click.option('--drop', 'opt_drop', type=click.Choice(['valid', 'invalid']), default='invalid', - help='Drop valid or invalid poses') -@click.pass_context -def cli(ctx, opt_fp_in, opt_fp_out, opt_slice, opt_yaw, opt_roll, opt_pitch, - opt_drop, opt_force): - """Filter out exaggerated poses""" - - from glob import glob - from os.path import join - from pathlib import Path - import time - from multiprocessing.dummy import Pool as ThreadPool - import random - - import pandas as pd - from tqdm import tqdm - from glob import glob - - from app.utils import file_utils, im_utils - - - if not opt_force and Path(opt_fp_out).exists(): - log.error('File exists. Use "-f / --force" to overwite') - return - - df_poses = pd.read_csv(opt_fp_in).set_index('index') - - if opt_slice: - df_poses = df_poses[opt_slice[0]:opt_slice[1]] - - log.info('Processing {:,} rows'.format(len(df_poses))) - - # extend a new temporary column - df_poses['valid'] = [0] * len(df_poses) - - # filter out extreme poses - for ds_pose in tqdm(df_poses.itertuples(), total=len(df_poses)): - if ds_pose.yaw > opt_yaw[0] and ds_pose.yaw < opt_yaw[1] \ - and ds_pose.roll > opt_roll[0] and ds_pose.roll < opt_roll[1] \ - and ds_pose.pitch > opt_pitch[0] and ds_pose.pitch < opt_pitch[1]: - df_poses.at[ds_pose.Index, 'valid'] = 1 - - # filter out valid/invalid - drop_val = 0 if opt_drop == 'valid' else 0 # drop 0's if drop == valid, else drop 1's - df_poses_filtered = df_poses.drop(df_poses[df_poses.valid == int()].index, axis=0) - - # drop temp column - df_poses_filtered = df_poses_filtered.drop('valid', axis=1) - - # save filtered poses - df_poses_filtered.to_csv(opt_fp_out) - log.info('Saved {:,} rows'.format(len(df_poses_filtered)))
\ No newline at end of file diff --git a/megapixels/commands/datasets/file_meta.py b/megapixels/commands/datasets/gen_filepath.py index e1456f44..5db405c0 100644 --- a/megapixels/commands/datasets/file_meta.py +++ b/megapixels/commands/datasets/gen_filepath.py @@ -12,10 +12,20 @@ from app.utils.logger_utils import Logger log = Logger.getLogger() @click.command() -@click.option('-i', '--input', 'opt_fp_in', required=True, - help='Input directory') -@click.option('-o', '--output', 'opt_fp_out', required=True, - help='Output file for file meta CSV') +@click.option('-i', '--input', 'opt_fp_in', + help='Override enum input filename CSV') +@click.option('-o', '--output', 'opt_fp_out', + help='Override enum output filename CSV') +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.NAS), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) @click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), help='Slice list of files') @click.option('--recursive/--no-recursive', 'opt_recursive', is_flag=True, default=False, @@ -25,7 +35,8 @@ log = Logger.getLogger() @click.option('-f', '--force', 'opt_force', is_flag=True, help='Force overwrite file') @click.pass_context -def cli(ctx, opt_fp_in, opt_fp_out, opt_slice, opt_recursive, opt_threads, opt_force): +def cli(ctx, opt_fp_in, opt_fp_out, opt_data_store, opt_dataset, opt_slice, + opt_recursive, opt_threads, opt_force): """Multithreading test""" from glob import glob @@ -39,21 +50,26 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_slice, opt_recursive, opt_threads, opt_f from tqdm import tqdm from glob import glob + from app.models.data_store import DataStore from app.utils import file_utils, im_utils - - if not opt_force and Path(opt_fp_out).exists(): + data_store = DataStore(opt_data_store, opt_dataset) + fp_out = opt_fp_out if opt_fp_out is not None else data_store.metadata(types.Metadata.FILEPATH) + if not opt_force and Path(fp_out).exists(): log.error('File exists. Use "-f / --force" to overwite') return + + # glob files + fp_in = opt_fp_in if opt_fp_in is not None else data_store.media_images_original() fp_ims = [] - log.info(f'Globbing {opt_fp_in}') + log.info(f'Globbing {fp_in}') for ext in ['jpg', 'png']: if opt_recursive: - fp_glob = join(opt_fp_in, '**/*.{}'.format(ext)) + fp_glob = join(fp_in, '**/*.{}'.format(ext)) fp_ims += glob(fp_glob, recursive=True) else: - fp_glob = join(opt_fp_in, '*.{}'.format(ext)) + fp_glob = join(fp_in, '*.{}'.format(ext)) fp_ims += glob(fp_glob) if not fp_ims: @@ -63,14 +79,14 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_slice, opt_recursive, opt_threads, opt_f if opt_slice: fp_ims = fp_ims[opt_slice[0]:opt_slice[1]] - log.info('Processing {:,} images'.format(len(fp_ims))) + log.info('Found {:,} images'.format(len(fp_ims))) # convert data to dict data = [] for i, fp_im in enumerate(tqdm(fp_ims)): fpp_im = Path(fp_im) - subdir = str(fpp_im.parent.relative_to(opt_fp_in)) + subdir = str(fpp_im.parent.relative_to(fp_in)) data.append( { 'subdir': subdir, 'fn': fpp_im.stem, @@ -78,7 +94,9 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_slice, opt_recursive, opt_threads, opt_f }) # save to CSV - file_utils.mkdirs(opt_fp_out) - df = pd.DataFrame.from_dict(data) - df.index.name = 'index' - df.to_csv(opt_fp_out)
\ No newline at end of file + file_utils.mkdirs(fp_out) + df_filepath = pd.DataFrame.from_dict(data) + df_filepath = df_filepath.sort_values(by=['subdir'], ascending=True) + df_filepath = df_filepath.reset_index() + df_filepath.index.name = 'index' + df_filepath.to_csv(fp_out)
\ No newline at end of file diff --git a/megapixels/commands/datasets/gen_uuid.py b/megapixels/commands/datasets/gen_uuid.py new file mode 100644 index 00000000..d7e7b52c --- /dev/null +++ b/megapixels/commands/datasets/gen_uuid.py @@ -0,0 +1,65 @@ +import click + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg +from app.utils.logger_utils import Logger + +log = Logger.getLogger() + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', default=None, + help='Override enum input filename CSV') +@click.option('-o', '--output', 'opt_fp_out', default=None, + help='Override enum output filename CSV') +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.NAS), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('-f', '--force', 'opt_force', is_flag=True, + help='Force overwrite file') +@click.pass_context +def cli(ctx, opt_fp_in, opt_fp_out, opt_data_store, opt_dataset, opt_force): + """Appends UUID to records CSV""" + + from glob import glob + from os.path import join + from pathlib import Path + import base64 + import uuid + + from tqdm import tqdm + import pandas as pd + + from app.models.data_store import DataStore + + + # set data_store + data_store = DataStore(opt_data_store, opt_dataset) + # get filepath out + fp_out = data_store.metadata(types.Metadata.UUID) if opt_fp_out is None else opt_fp_out + # exit if exists + if not opt_force and Path(fp_out).exists(): + log.error('File exists. Use "-f / --force" to overwite') + return + + # load sha256 records + fp_in = data_store.metadata(types.Metadata.SHA256) if opt_fp_in is None else opt_fp_in + log.info(f'Loading: {fp_in}') + df_records = pd.read_csv(fp_in).set_index('index') + + df_uuids = df_records.copy() + df_uuids['uuid'] = [uuid.uuid4()] * len(df_uuids) + + for df_record in tqdm(df_records.itertuples(), total=len(df_uuids)): + image_index = df_record.Index + df_uuids.at[image_index, 'uuid'] = uuid.uuid4() + + df_uuids = df_uuids.drop(['sha256', 'identity_index'], axis=1) + df_uuids.to_csv(fp_out)
\ No newline at end of file diff --git a/megapixels/commands/datasets/identity_meta_lfw.py b/megapixels/commands/datasets/identity_meta_lfw.py new file mode 100644 index 00000000..45386b23 --- /dev/null +++ b/megapixels/commands/datasets/identity_meta_lfw.py @@ -0,0 +1,93 @@ +''' +add identity from description using subdir +''' +import click + +from app.settings import types +from app.models.dataset import Dataset +from app.utils import click_utils +from app.settings import app_cfg as cfg +from app.utils.logger_utils import Logger + +log = Logger.getLogger() + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', required=True, + help='Identity meta file') +@click.option('-o', '--output', 'opt_fp_out', default=None, + help='Override enum output filename CSV') +@click.option('--column', 'opt_identity_key', default='identity_key', + help='Match column') +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.SSD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('-f', '--force', 'opt_force', is_flag=True, + help='Force overwrite file') +@click.pass_context +def cli(ctx, opt_fp_in, opt_fp_out, opt_identity_key, opt_data_store, opt_force): + """Display image info""" + + import sys + from glob import glob + from os.path import join + from pathlib import Path + import time + + import pandas as pd + import cv2 as cv + from tqdm import tqdm + + from app.utils import file_utils, im_utils + from app.models.data_store import DataStore + + log = Logger.getLogger() + + # output file + opt_dataset = types.Dataset.LFW + data_store = DataStore(opt_data_store, opt_dataset) + fp_out = data_store.metadata(types.Metadata.IDENTITY) if opt_fp_out is None else opt_fp_out + # exit if exists + log.debug(fp_out) + if not opt_force and Path(fp_out).exists(): + log.error('File exists. Use "-f / --force" to overwite') + return + + # init dataset + # load file records + fp_record = data_store.metadata(types.Metadata.FILE_RECORD) + df_record = pd.read_csv(fp_record).set_index('index') + + # load identity meta + # this file is maybe prepared in a Jupyter notebook + # the "identity_key" + df_identity_meta = pd.read_csv(opt_fp_in).set_index('index') + # create a new file called 'identity.csv' + identities = [] + # iterate records and get identity index where 'identity_key' matches + log.debug(type(df_record)) + identity_indices = [] + for record_idx, ds_record in tqdm(df_record.iterrows(), total=len(df_record)): + identity_value = ds_record[opt_identity_key] + identity_index = ds_record.identity_index + ds_identity_meta = df_identity_meta.loc[(df_identity_meta[opt_identity_key] == identity_value)] + if identity_index not in identity_indices: + identity_indices.append(identity_index) + identities.append({ + 'description': ds_identity_meta.description.values[0], + 'name': ds_identity_meta.name.values[0], + 'images': ds_identity_meta.images.values[0], + 'gender': ds_identity_meta.gender.values[0], + }) + + # write to csv + df_identity = pd.DataFrame.from_dict(identities) + df_identity.index.name = 'index' + df_identity.to_csv(fp_out) + ''' + index,name,name_orig,description,gender,images,image_index,identity_key + 0,A. J. Cook,AJ Cook,Canadian actress,f,1,0,AJ_Cook + ''' + + diff --git a/megapixels/commands/datasets/identity_meta_vgg_face2.py b/megapixels/commands/datasets/identity_meta_vgg_face2.py new file mode 100644 index 00000000..85b6644d --- /dev/null +++ b/megapixels/commands/datasets/identity_meta_vgg_face2.py @@ -0,0 +1,88 @@ +''' +add identity from description using subdir +''' +import click + +from app.settings import types +from app.models.dataset import Dataset +from app.utils import click_utils +from app.settings import app_cfg as cfg +from app.utils.logger_utils import Logger + +log = Logger.getLogger() + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', required=True, + help='Identity meta file') +@click.option('-o', '--output', 'opt_fp_out', default=None, + help='Override enum output filename CSV') +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.SSD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('-f', '--force', 'opt_force', is_flag=True, + help='Force overwrite file') +@click.pass_context +def cli(ctx, opt_fp_in, opt_fp_out, opt_data_store, opt_force): + """Display image info""" + + import sys + from glob import glob + from os.path import join + from pathlib import Path + import time + + import pandas as pd + import cv2 as cv + from tqdm import tqdm + + from app.utils import file_utils, im_utils + from app.models.data_store import DataStore + + log = Logger.getLogger() + + # output file + opt_dataset = types.Dataset.VGG_FACE2 + data_store = DataStore(opt_data_store, opt_dataset) + fp_out = data_store.metadata(types.Metadata.IDENTITY) if opt_fp_out is None else opt_fp_out + # exit if exists + log.debug(fp_out) + if not opt_force and Path(fp_out).exists(): + log.error('File exists. Use "-f / --force" to overwite') + return + + # init dataset + # load file records + identity_key = 'identity_key' + fp_record = data_store.metadata(types.Metadata.FILE_RECORD) + df_record = pd.read_csv(fp_record).set_index('index') + + # load identity meta + # this file is maybe prepared in a Jupyter notebook + # the "identity_key" + df_identity_meta = pd.read_csv(opt_fp_in).set_index('index') + # create a new file called 'identity.csv' + identities = [] + # iterate records and get identity index where 'identity_key' matches + log.debug(type(df_record)) + identity_indices = [] + for ds_record in tqdm(df_record.itertuples(), total=len(df_record)): + identity_value = ds_record.identity_key + identity_index = ds_record.identity_index + ds_identity_meta = df_identity_meta.loc[(df_identity_meta[identity_key] == identity_value)] + if identity_index not in identity_indices: + identity_indices.append(identity_index) + identities.append({ + 'description': ds_identity_meta.description.values[0], + 'name': ds_identity_meta.name.values[0], + 'images': ds_identity_meta.images.values[0], + 'gender': ds_identity_meta.gender.values[0], + }) + + # write to csv + df_identity = pd.DataFrame.from_dict(identities) + df_identity.index.name = 'index' + df_identity.to_csv(fp_out) + + diff --git a/megapixels/commands/datasets/lookup.py b/megapixels/commands/datasets/lookup.py index e84bdf3e..c1c66c19 100644 --- a/megapixels/commands/datasets/lookup.py +++ b/megapixels/commands/datasets/lookup.py @@ -6,12 +6,14 @@ from app.utils import click_utils from app.settings import app_cfg as cfg from app.utils.logger_utils import Logger +log = Logger.getLogger() + @click.command() -@click.option('--index', 'opt_index', type=int, +@click.option('--index', 'opt_index', type=int, required=True, help='Vector index to lookup') @click.option('--data_store', 'opt_data_store', type=cfg.DataStoreVar, - default=click_utils.get_default(types.DataStore.NAS), + default=click_utils.get_default(types.DataStore.SSD), show_default=True, help=click_utils.show_help(types.Dataset)) @click.option('--dataset', 'opt_dataset', @@ -19,12 +21,8 @@ from app.utils.logger_utils import Logger required=True, show_default=True, help=click_utils.show_help(types.Dataset)) -@click.option('--metadata', 'opt_metadata_type', required=True, - type=cfg.MetadataVar, - show_default=True, - help=click_utils.show_help(types.Metadata)) @click.pass_context -def cli(ctx, opt_index, opt_data_store, opt_dataset, opt_metadata_type): +def cli(ctx, opt_index, opt_data_store, opt_dataset): """Display image info""" import sys @@ -37,22 +35,21 @@ def cli(ctx, opt_index, opt_data_store, opt_dataset, opt_metadata_type): import cv2 as cv from tqdm import tqdm - from app.utils import file_utils, im_utils, path_utils + from app.utils import file_utils, im_utils + from app.models.data_store import DataStore log = Logger.getLogger() - - log.info(f'creating dataset: {opt_dataset}') - dataset = Dataset(opt_dataset) - # loads all CSV files, may take a while - log.info(f'loading dataset...') - dataset.load(opt_data_store) + # init dataset + dataset = Dataset(opt_data_store, opt_dataset) + #dataset.load_face_vectors() + dataset.load_records() + dataset.load_identities() + # set data store and load files # find image records - image_record = dataset.roi_idx_to_record(opt_index) - # debug + image_record = dataset.index_to_record(opt_index) image_record.summarize() # load image - fp_im = image_record.filepath - im = cv.imread(fp_im) + im = cv.imread(image_record.filepath) # display cv.imshow('', im) # cv gui diff --git a/megapixels/commands/datasets/records.py b/megapixels/commands/datasets/records.py new file mode 100644 index 00000000..80de5040 --- /dev/null +++ b/megapixels/commands/datasets/records.py @@ -0,0 +1,159 @@ +''' + +''' +import click + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg +from app.utils.logger_utils import Logger + +log = Logger.getLogger() + +identity_sources = ['subdir', 'subdir_head', 'subdir_tail'] + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', default=None, + help='Override enum input filename CSV') +@click.option('-o', '--output', 'opt_fp_out', default=None, + help='Override enum output filename CSV') +@click.option('-m', '--media', 'opt_dir_media', default=None, + help='Override enum media directory') +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.SSD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), + help='Slice list of files') +@click.option('-t', '--threads', 'opt_threads', default=12, + help='Number of threads') +@click.option('-f', '--force', 'opt_force', is_flag=True, + help='Force overwrite file') +@click.option('--identity', 'opt_identity', default=None, type=click.Choice(identity_sources), + help='Identity source, blank for no identity') +@click.option('--recursive/--no-recursive', 'opt_recursive', is_flag=True, default=False, + help='Use glob recursion (slower)') +@click.pass_context +def cli(ctx, opt_fp_in, opt_fp_out, opt_dataset, opt_data_store, opt_dir_media, opt_slice, opt_threads, + opt_identity, opt_force, opt_recursive): + """Generates sha256, uuid, and identity index CSV file""" + + import sys + from glob import glob + from os.path import join + from pathlib import Path + import time + from multiprocessing.dummy import Pool as ThreadPool + import random + import uuid + + import pandas as pd + from tqdm import tqdm + from glob import glob + + from app.models.data_store import DataStore + from app.utils import file_utils, im_utils + + + # set data_store + data_store = DataStore(opt_data_store, opt_dataset) + # get filepath out + fp_out = data_store.metadata(types.Metadata.FILE_RECORD) if opt_fp_out is None else opt_fp_out + # exit if exists + if not opt_force and Path(fp_out).exists(): + log.error('File exists. Use "-f / --force" to overwite') + return + + # ---------------------------------------------------------------- + # glob files + + fp_in = opt_fp_in if opt_fp_in is not None else data_store.media_images_original() + log.info(f'Globbing {fp_in}') + fp_ims = file_utils.glob_multi(fp_in, ['jpg', 'png'], recursive=opt_recursive) + # fail if none + if not fp_ims: + log.error('No images. Try with "--recursive"') + return + # slice to reduce + if opt_slice: + fp_ims = fp_ims[opt_slice[0]:opt_slice[1]] + log.info('Found {:,} images'.format(len(fp_ims))) + + + # ---------------------------------------------------------------- + # multithread process into SHA256 + + pbar = tqdm(total=len(fp_ims)) + + def as_sha256(fp_im): + pbar.update(1) + return file_utils.sha256(fp_im) + + # convert to thread pool + sha256s = [] # ? + pool = ThreadPool(opt_threads) + with tqdm(total=len(fp_ims)) as pbar: + sha256s = pool.map(as_sha256, fp_ims) + pbar.close() + + + # ---------------------------------------------------------------- + # convert data to dict + + data = [] + for sha256, fp_im in zip(sha256s, fp_ims): + fpp_im = Path(fp_im) + subdir = str(fpp_im.parent.relative_to(fp_in)) + + if opt_identity: + subdirs = subdir.split('/') + if not len(subdirs) > 0: + log.error(f'Could not split subdir: "{subdir}. Try different option for "--identity"') + log.error('exiting') + return + if opt_identity == 'subdir': + identity = subdirs[0] # use first/only part + elif opt_identity == 'subdir_head': + identity = subdirs[0] # use first part of subdir path + elif opt_identity == 'subdir_tail': + identity = subdirs[-1] # use last part of subdir path + else: + identity = '' + + data.append({ + 'subdir': subdir, + 'fn': fpp_im.stem, + 'ext': fpp_im.suffix.replace('.',''), + 'sha256': sha256, + 'uuid': uuid.uuid4(), + 'identity_key': identity + }) + + log.info(f'adding identity index using: "{opt_identity}". This may take a while...') + # convert dict to DataFrame + df_records = pd.DataFrame.from_dict(data) + # sort based on identity_key + df_records = df_records.sort_values(by=['identity_key'], ascending=True) + # add new column for identity + df_records['identity_index'] = [-1] * len(df_records) + # populate the identity_index + df_records_identity_groups = df_records.groupby('identity_key') + # enumerate groups to create identity indices + for identity_index, df_records_identity_group_tuple in enumerate(df_records_identity_groups): + identity_key, df_records_identity_group = df_records_identity_group_tuple + for ds_record in df_records_identity_group.itertuples(): + df_records.at[ds_record.Index, 'identity_index'] = identity_index + # reset index after being sorted + df_records = df_records.reset_index(drop=True) + df_records.index.name = 'index' # reassign 'index' as primary key column + # write to CSV + file_utils.mkdirs(fp_out) + df_records.to_csv(fp_out) + # done + log.info(f'wrote rows: {len(df_records)} to {fp_out}')
\ No newline at end of file diff --git a/megapixels/commands/datasets/s3.py b/megapixels/commands/datasets/s3.py deleted file mode 100644 index 7769896b..00000000 --- a/megapixels/commands/datasets/s3.py +++ /dev/null @@ -1,47 +0,0 @@ -import click - -from app.settings import types -from app.utils import click_utils -from app.settings import app_cfg as cfg - -s3_dirs = {'media': cfg.S3_MEDIA_ROOT, 'metadata': cfg.S3_METADATA_ROOT} - -@click.command() -@click.option('-i', '--input', 'opt_fps_in', required=True, multiple=True, - help='Input directory') -@click.option('--name', 'opt_dataset_name', required=True, - help='Dataset key (eg "lfw"') -@click.option('-a', '--action', 'opt_action', type=click.Choice(['sync', 'put']), default='sync', - help='S3 action') -@click.option('-t', '--type', 'opt_type', type=click.Choice(s3_dirs.keys()), required=True, - help='S3 location') -@click.option('--dry-run', 'opt_dryrun', is_flag=True, default=False) -@click.pass_context -def cli(ctx, opt_fps_in, opt_dataset_name, opt_action, opt_type, opt_dryrun): - """Syncs files with S3/spaces server""" - - from os.path import join - from pathlib import Path - - from tqdm import tqdm - import pandas as pd - import subprocess - - from app.utils import logger_utils, file_utils - - # ------------------------------------------------- - # init here - - log = logger_utils.Logger.getLogger() - for opt_fp_in in opt_fps_in: - dir_dst = join(s3_dirs[opt_type], opt_dataset_name, '') - if Path(opt_fp_in).is_dir(): - fp_src = join(opt_fp_in, '') # add trailing slashes - else: - fp_src = join(opt_fp_in) - cmd = ['s3cmd', opt_action, fp_src, dir_dst, '-P', '--follow-symlinks'] - log.info(' '.join(cmd)) - if not opt_dryrun: - subprocess.call(cmd) - -
\ No newline at end of file diff --git a/megapixels/commands/datasets/s3_sync.py b/megapixels/commands/datasets/s3_sync.py new file mode 100644 index 00000000..3098d9be --- /dev/null +++ b/megapixels/commands/datasets/s3_sync.py @@ -0,0 +1,57 @@ +import click + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg + +s3_dirs = {'media': cfg.S3_MEDIA_URL, 'metadata': cfg.S3_METADATA_URL} + +@click.command() +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.SSD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('-t', '--type', 'opt_type', type=click.Choice(s3_dirs.keys()), required=True, + help='S3 location') +@click.option('--dry-run', 'opt_dryrun', is_flag=True, default=False) +@click.pass_context +def cli(ctx, opt_data_store, opt_dataset, opt_type, opt_dryrun): + """Syncs files with S3/spaces server""" + + from os.path import join + from pathlib import Path + + from tqdm import tqdm + import pandas as pd + import subprocess + + from app.utils import logger_utils, file_utils + from app.models.data_store import DataStore + + # ------------------------------------------------- + # init here + + log = logger_utils.Logger.getLogger() + + # set data_store + data_store = DataStore(opt_data_store, opt_dataset) + dataset_name = opt_dataset.name.lower() + if opt_type == 'media': + dir_src = join(data_store.uuid_dir(), '') + dir_dst = join(s3_dirs[opt_type], dataset_name, '') + elif opt_type == 'metadata': + dir_src = join(data_store.metadata_dir(), '') + dir_dst = join(s3_dirs[opt_type], dataset_name, '') + + cmd = ['s3cmd', 'sync', dir_src, dir_dst, '-P', '--follow-symlinks'] + log.info(' '.join(cmd)) + if not opt_dryrun: + subprocess.call(cmd) + +
\ No newline at end of file diff --git a/megapixels/commands/datasets/sha256.py b/megapixels/commands/datasets/sha256.py deleted file mode 100644 index 4c734073..00000000 --- a/megapixels/commands/datasets/sha256.py +++ /dev/null @@ -1,89 +0,0 @@ -import click - -from app.settings import types -from app.utils import click_utils -from app.settings import app_cfg as cfg -from app.utils.logger_utils import Logger - -log = Logger.getLogger() - -@click.command() -@click.option('-i', '--input', 'opt_fp_in', required=True, - help='Input directory') -@click.option('-m', '--media', 'opt_dir_media', required=True, - help='Input media directory') -@click.option('-o', '--output', 'opt_fp_out', required=True, - help='Output directory') -@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), - help='Slice list of files') -@click.option('-t', '--threads', 'opt_threads', default=4, - help='Number of threads') -@click.option('-f', '--force', 'opt_force', is_flag=True, - help='Force overwrite file') -@click.pass_context -def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_slice, opt_threads, opt_force): - """Multithreading test""" - - from glob import glob - from os.path import join - from pathlib import Path - import time - from multiprocessing.dummy import Pool as ThreadPool - import random - - import pandas as pd - from tqdm import tqdm - from glob import glob - - from app.utils import file_utils, im_utils - - - if not opt_force and Path(opt_fp_out).exists(): - log.error('File exists. Use "-f / --force" to overwite') - return - - df_files = pd.read_csv(opt_fp_in).set_index('index') - - if opt_slice: - df_files = df_files[opt_slice[0]:opt_slice[1]] - - log.info('Processing {:,} images'.format(len(df_files))) - - - # prepare list of images to multithread into sha256s - file_objs = [] - for ds_file in df_files.itertuples(): - fp_im = join(opt_dir_media, str(ds_file.subdir), f"{ds_file.fn}.{ds_file.ext}") - file_objs.append({'fp': fp_im, 'index': ds_file.Index}) - - # convert to thread pool - pbar = tqdm(total=len(file_objs)) - - def as_sha256(file_obj): - pbar.update(1) - file_obj['sha256'] = file_utils.sha256(file_obj['fp']) - return file_obj - - # multithread pool - pool_file_objs = [] - st = time.time() - pool = ThreadPool(opt_threads) - with tqdm(total=len(file_objs)) as pbar: - pool_file_objs = pool.map(as_sha256, file_objs) - pbar.close() - - # convert data to dict - data = [] - for pool_file_obj in pool_file_objs: - data.append( { - 'sha256': pool_file_obj['sha256'], - 'index': pool_file_obj['index'] - }) - - # save to CSV - file_utils.mkdirs(opt_fp_out) - df = pd.DataFrame.from_dict(data) - df.to_csv(opt_fp_out, index=False) - - # timing - log.info('time: {:.2f}, theads: {}'.format(time.time() - st, opt_threads))
\ No newline at end of file diff --git a/megapixels/commands/datasets/symlink.py b/megapixels/commands/datasets/symlink.py deleted file mode 100644 index 70ec6c46..00000000 --- a/megapixels/commands/datasets/symlink.py +++ /dev/null @@ -1,45 +0,0 @@ -import click - -from app.settings import types -from app.utils import click_utils -from app.settings import app_cfg as cfg - -@click.command() -@click.option('-i', '--input', 'opt_fp_in', required=True, - help='Input records CSV') -@click.option('-m', '--media', 'opt_fp_media', required=True, - help='Input media directory') -@click.option('-o', '--output', 'opt_fp_out', required=True, - help='Output directory') -@click.pass_context -def cli(ctx, opt_fp_in, opt_fp_media, opt_fp_out): - """Symlinks images to new directory for S3""" - - import sys - import os - from os.path import join - from pathlib import Path - - from tqdm import tqdm - import pandas as pd - - from app.utils import logger_utils, file_utils - - # ------------------------------------------------- - # init here - - log = logger_utils.Logger.getLogger() - - df_records = pd.read_csv(opt_fp_in) - nrows = len(df_records) - - file_utils.mkdirs(opt_fp_out) - - for record_id, row in tqdm(df_records.iterrows(), total=nrows): - # make image path - df = df_records.iloc[record_id] - fpp_src = Path(join(opt_fp_media, df['subdir'], '{}.{}'.format(df['fn'], df['ext']))) - fpp_dst = Path(join(opt_fp_out, '{}.{}'.format(df['uuid'], df['ext']))) - fpp_dst.symlink_to(fpp_src) - - log.info('symlinked {:,} files'.format(nrows))
\ No newline at end of file diff --git a/megapixels/commands/datasets/symlink_uuid.py b/megapixels/commands/datasets/symlink_uuid.py new file mode 100644 index 00000000..7c5faa95 --- /dev/null +++ b/megapixels/commands/datasets/symlink_uuid.py @@ -0,0 +1,57 @@ +import click + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', default=None, + help='Override enum input filename CSV') +@click.option('-o', '--output', 'opt_fp_out', default=None, + help='Override enum output filename CSV') +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.SSD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.pass_context +def cli(ctx, opt_fp_in, opt_fp_out, opt_data_store, opt_dataset): + """Symlinks images to new directory for S3""" + + import sys + import os + from os.path import join + from pathlib import Path + + from tqdm import tqdm + import pandas as pd + + from app.utils import logger_utils, file_utils + from app.models.data_store import DataStore + + # ------------------------------------------------- + # init here + + log = logger_utils.Logger.getLogger() + + # set data_store + data_store = DataStore(opt_data_store, opt_dataset) + fp_records = data_store.metadata(types.Metadata.FILE_RECORD) + df_records = pd.read_csv(fp_records).set_index('index') + nrows = len(df_records) + + dir_out = data_store.uuid_dir() if opt_fp_out is None else opt_fp_out + file_utils.mkdirs(dir_out) + + for ds_record in tqdm(df_records.itertuples(), total=nrows): + # make image path + fp_src = data_store.face(ds_record.subdir, ds_record.fn, ds_record.ext) + fp_dst = data_store.face_uuid(ds_record.uuid, ds_record.ext) + Path(fp_dst).symlink_to(Path(fp_src)) + + log.info('symlinked {:,} files'.format(nrows))
\ No newline at end of file diff --git a/megapixels/commands/demo/face_analysis.py b/megapixels/commands/demo/face_analysis.py new file mode 100644 index 00000000..6721a02d --- /dev/null +++ b/megapixels/commands/demo/face_analysis.py @@ -0,0 +1,56 @@ +import click + +from app.settings import types +from app.models.dataset import Dataset +from app.utils import click_utils +from app.settings import app_cfg as cfg +from app.utils.logger_utils import Logger + +@click.command() +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.NAS), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.pass_context +def cli(ctx, opt_index, opt_data_store, opt_dataset): + """Display image info""" + + import sys + from glob import glob + from os.path import join + from pathlib import Path + import time + + import pandas as pd + import cv2 as cv + from tqdm import tqdm + + from app.utils import file_utils, im_utils, path_utils + + log = Logger.getLogger() + + dataset = Dataset(opt_dataset).load(opt_data_store) + # find image records + image_record = dataset.roi_idx_to_record(opt_index) + # debug + image_record.summarize() + # load image + fp_im = image_record.filepath + im = cv.imread(fp_im) + # display + cv.imshow('', im) + # cv gui + while True: + k = cv.waitKey(1) & 0xFF + if k == 27 or k == ord('q'): # ESC + cv.destroyAllWindows() + sys.exit() + elif k != 255: + # any key to continue + break
\ No newline at end of file diff --git a/megapixels/commands/demo/face_search.py b/megapixels/commands/demo/face_search.py new file mode 100644 index 00000000..0452cc9d --- /dev/null +++ b/megapixels/commands/demo/face_search.py @@ -0,0 +1,94 @@ +import click + +from app.settings import types +from app.models.dataset import Dataset +from app.utils import click_utils +from app.settings import app_cfg as cfg +from app.utils.logger_utils import Logger + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', required=True, + help='Input face image') +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.SSD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--gpu', 'opt_gpu', default=0, + help='GPU index (use -1 for CPU)') +@click.pass_context +def cli(ctx, opt_fp_in, opt_data_store, opt_dataset, opt_gpu): + """Display image info""" + + import sys + from glob import glob + from os.path import join + from pathlib import Path + import time + + import imutils + import pandas as pd + import cv2 as cv + import dlib + from tqdm import tqdm + + from app.utils import file_utils, im_utils + from app.models.data_store import DataStore, DataStoreS3 + from app.processors import face_detector + from app.processors import face_recognition + + log = Logger.getLogger() + + # init face detection + detector = face_detector.DetectorDLIBHOG() + + # init face recognition + recognition = face_recognition.RecognitionDLIB(gpu=opt_gpu) + + # load query image + im_query = cv.imread(opt_fp_in) + # get detection as BBox object + bboxes = detector.detect(im_query, largest=True) + bbox = bboxes[0] + dim = im_query.shape[:2][::-1] + bbox = bbox.to_dim(dim) # convert back to real dimensions + + if not bbox: + log.error('No face detected. Exiting') + return + + # extract the face vectors + vec_query = recognition.vec(im_query, bbox) + + # load dataset CSVs + dataset = Dataset(opt_data_store, opt_dataset) + + # find matches + image_records = dataset.find_matches(vec_query, n_results=5) + + # summary + ims_match = [im_query] + for image_record in image_records: + image_record.summarize() + log.info(f'{image_record.filepath}') + im_match = cv.imread(image_record.filepath) + ims_match.append(im_match) + + montages = imutils.build_montages(ims_match, (256, 256), (3,2)) + + for i, montage in enumerate(montages): + cv.imshow(f'{i}', montage) + # cv gui + while True: + k = cv.waitKey(1) & 0xFF + if k == 27 or k == ord('q'): # ESC + cv.destroyAllWindows() + sys.exit() + elif k != 255: + # any key to continue + break
\ No newline at end of file diff --git a/megapixels/notebooks/_local_scratch.ipynb b/megapixels/notebooks/_local_scratch.ipynb index 167b6ddd..cee17cba 100644 --- a/megapixels/notebooks/_local_scratch.ipynb +++ b/megapixels/notebooks/_local_scratch.ipynb @@ -1,161 +1,173 @@ { "cells": [ { - "cell_type": "code", - "execution_count": 1, + "cell_type": "markdown", "metadata": {}, - "outputs": [], "source": [ - "import pandas as pd\n", - "import cv2 as cv\n", - "import numpy as np\n", - "%matplotlib inline\n", - "import matplotlib.pyplot as plt" + "# Scratch pad" ] }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ - "import sys\n", "from glob import glob\n", "from os.path import join\n", "from pathlib import Path\n", + "import random\n", + "\n", + "import pandas as pd\n", + "import cv2 as cv\n", + "import numpy as np\n", + "%matplotlib inline\n", + "import matplotlib.pyplot as plt\n", + "\n", + "import sys\n", "sys.path.append('/work/megapixels_dev/megapixels')\n", "from app.models.bbox import BBox\n", - "#from app.utils import im_utils\n", - "import random" + "from app.utils import im_utils, file_utils" ] }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ - "dir_ims = '/data_store_ssd/apps/megapixels/datasets/umd_faces/faces/'" + "a= [1]" ] }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 6, "metadata": {}, "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "0\n" - ] + "data": { + "text/plain": [ + "1" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" } ], "source": [ - "fp_ims = glob(join(dir_ims, '*.png'))\n", - "print(len(fp_ims))" + "a[-1]" ] }, { "cell_type": "code", - "execution_count": 9, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Help on function choice in module random:\n", - "\n", - "choice(self, seq)\n", - " Choose a random element from a non-empty sequence.\n", - "\n" - ] - } - ], - "source": [ - "help(random.sample)" - ] - }, - { - "cell_type": "code", - "execution_count": 33, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[1, 8, 0, 6, 3] True\n" - ] - } - ], - "source": [ - "a = list(range(0,10))\n", - "b = random.sample(a, 5)\n", - "print(b, len(set(b))==5)" - ] - }, - { - "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, "outputs": [], "source": [ - "from random import randint\n", - "imu" + "fp_filepath = '/data_store_ssd/datasets/people/lfw/metadata/filepath.csv'\n", + "df_filepath = pd.read_csv(fp_filepath)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 48, "metadata": {}, "outputs": [], "source": [ - "import face_alignment\n", - "from skimage import io\n", - "\n", - "fa = face_alignment.FaceAlignment(face_alignment.LandmarksType._3D, flip_input=False, device='cuda')" + "image_index = 12467" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 55, "metadata": {}, - "outputs": [], - "source": [ - "fp_im = np.random.choice(fp_ims)\n", - "im = io.imread(fp_im)\n", - "preds = fa.get_landmarks(im)\n", - "print(preds[0])" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "12474\n" + ] + }, + { + "data": { + "text/plain": [ + "index 12851\n", + "ext jpg\n", + "fn Vladimir_Putin_0029\n", + "subdir Vladimir_Putin\n", + "Name: 12474, dtype: object" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "import json" + "image_index += 1\n", + "print(image_index)\n", + "df_filepath.iloc[image_index]" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 56, "metadata": {}, "outputs": [], "source": [ - "print(len(preds[0]))\n" + "import imutils" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 57, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Help on function build_montages in module imutils.convenience:\n", + "\n", + "build_montages(image_list, image_shape, montage_shape)\n", + " ---------------------------------------------------------------------------------------------\n", + " author: Kyle Hounslow\n", + " ---------------------------------------------------------------------------------------------\n", + " Converts a list of single images into a list of 'montage' images of specified rows and columns.\n", + " A new montage image is started once rows and columns of montage image is filled.\n", + " Empty space of incomplete montage images are filled with black pixels\n", + " ---------------------------------------------------------------------------------------------\n", + " :param image_list: python list of input images\n", + " :param image_shape: tuple, size each image will be resized to for display (width, height)\n", + " :param montage_shape: tuple, shape of image montage (width, height)\n", + " :return: list of montage images in numpy array format\n", + " ---------------------------------------------------------------------------------------------\n", + " \n", + " example usage:\n", + " \n", + " # load single image\n", + " img = cv2.imread('lena.jpg')\n", + " # duplicate image 25 times\n", + " num_imgs = 25\n", + " img_list = []\n", + " for i in xrange(num_imgs):\n", + " img_list.append(img)\n", + " # convert image list into a montage of 256x256 images tiled in a 5x5 montage\n", + " montages = make_montages_of_images(img_list, (256, 256), (5, 5))\n", + " # iterate through montages and display\n", + " for montage in montages:\n", + " cv2.imshow('montage image', montage)\n", + " cv2.waitKey(0)\n", + " \n", + " ----------------------------------------------------------------------------------------------\n", + "\n" + ] + } + ], "source": [ - "with open('test.json', 'w') as fp:\n", - " json.dump(preds[0].tolist(), fp)" + "help(imutils.build_montages)" ] }, { @@ -182,7 +194,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.5" + "version": "3.6.6" } }, "nbformat": 4, diff --git a/megapixels/notebooks/datasets/lfw/lfw_make_identity_csv.ipynb b/megapixels/notebooks/datasets/lfw/lfw_make_identity_csv.ipynb new file mode 100644 index 00000000..039614f0 --- /dev/null +++ b/megapixels/notebooks/datasets/lfw/lfw_make_identity_csv.ipynb @@ -0,0 +1,510 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Add identity ID to index" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "from os.path import join\n", + "from pathlib import Path\n", + "import difflib\n", + "\n", + "from tqdm import tqdm_notebook as tqdm\n", + "import pandas as pd\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "# names\n", + "DATA_STORE = '/data_store_ssd/'\n", + "dir_dataset = 'datasets/people/lfw/metadata'" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [], + "source": [ + "# split records into index and uuids\n", + "fp_identity_in = join(DATA_STORE, dir_dataset, 'identities_old.csv')\n", + "fp_identity_out = join(DATA_STORE, dir_dataset, 'identity_lookup.csv')\n", + "\n", + "df_identity = pd.read_csv(fp_identity_in).set_index('index')" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "<div>\n", + "<style scoped>\n", + " .dataframe tbody tr th:only-of-type {\n", + " vertical-align: middle;\n", + " }\n", + "\n", + " .dataframe tbody tr th {\n", + " vertical-align: top;\n", + " }\n", + "\n", + " .dataframe thead th {\n", + " text-align: right;\n", + " }\n", + "</style>\n", + "<table border=\"1\" class=\"dataframe\">\n", + " <thead>\n", + " <tr style=\"text-align: right;\">\n", + " <th></th>\n", + " <th>name</th>\n", + " <th>name_orig</th>\n", + " <th>description</th>\n", + " <th>gender</th>\n", + " <th>images</th>\n", + " <th>image_index</th>\n", + " </tr>\n", + " <tr>\n", + " <th>index</th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>A. J. Cook</td>\n", + " <td>AJ Cook</td>\n", + " <td>Canadian actress</td>\n", + " <td>f</td>\n", + " <td>1</td>\n", + " <td>0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>AJ Lamas</td>\n", + " <td>AJ Lamas</td>\n", + " <td>American actor</td>\n", + " <td>m</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>Aaron Eckhart</td>\n", + " <td>Aaron Eckhart</td>\n", + " <td>American actor</td>\n", + " <td>m</td>\n", + " <td>1</td>\n", + " <td>2</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>Aaron Guiel</td>\n", + " <td>Aaron Guiel</td>\n", + " <td>Professional baseball player</td>\n", + " <td>m</td>\n", + " <td>1</td>\n", + " <td>3</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>Aaron Patterson</td>\n", + " <td>Aaron Patterson</td>\n", + " <td>Author</td>\n", + " <td>m</td>\n", + " <td>1</td>\n", + " <td>4</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "</div>" + ], + "text/plain": [ + " name name_orig description gender \\\n", + "index \n", + "0 A. J. Cook AJ Cook Canadian actress f \n", + "1 AJ Lamas AJ Lamas American actor m \n", + "2 Aaron Eckhart Aaron Eckhart American actor m \n", + "3 Aaron Guiel Aaron Guiel Professional baseball player m \n", + "4 Aaron Patterson Aaron Patterson Author m \n", + "\n", + " images image_index \n", + "index \n", + "0 1 0 \n", + "1 1 1 \n", + "2 1 2 \n", + "3 1 3 \n", + "4 1 4 " + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_identity.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "<div>\n", + "<style scoped>\n", + " .dataframe tbody tr th:only-of-type {\n", + " vertical-align: middle;\n", + " }\n", + "\n", + " .dataframe tbody tr th {\n", + " vertical-align: top;\n", + " }\n", + "\n", + " .dataframe thead th {\n", + " text-align: right;\n", + " }\n", + "</style>\n", + "<table border=\"1\" class=\"dataframe\">\n", + " <thead>\n", + " <tr style=\"text-align: right;\">\n", + " <th></th>\n", + " <th>name</th>\n", + " <th>name_orig</th>\n", + " <th>description</th>\n", + " <th>gender</th>\n", + " <th>images</th>\n", + " <th>image_index</th>\n", + " <th>subdir</th>\n", + " </tr>\n", + " <tr>\n", + " <th>index</th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>A. J. Cook</td>\n", + " <td>AJ Cook</td>\n", + " <td>Canadian actress</td>\n", + " <td>f</td>\n", + " <td>1</td>\n", + " <td>0</td>\n", + " <td></td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>AJ Lamas</td>\n", + " <td>AJ Lamas</td>\n", + " <td>American actor</td>\n", + " <td>m</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td></td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "</div>" + ], + "text/plain": [ + " name name_orig description gender images image_index \\\n", + "index \n", + "0 A. J. Cook AJ Cook Canadian actress f 1 0 \n", + "1 AJ Lamas AJ Lamas American actor m 1 1 \n", + "\n", + " subdir \n", + "index \n", + "0 \n", + "1 " + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# associate each file with an identity\n", + "df_identity['subdir'] = [''] * len(df_identity)\n", + "df_identity.head(2)" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "ece5c11b90954b25b1f1e28fc2fe6b55", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "HBox(children=(IntProgress(value=0, max=5749), HTML(value='')))" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "for row in tqdm(df_identity.itertuples(), total=len(df_identity)):\n", + " name = row.name_orig\n", + " subdir = name.replace(' ','_')\n", + " df_identity.at[row.Index, 'subdir'] = subdir" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "<div>\n", + "<style scoped>\n", + " .dataframe tbody tr th:only-of-type {\n", + " vertical-align: middle;\n", + " }\n", + "\n", + " .dataframe tbody tr th {\n", + " vertical-align: top;\n", + " }\n", + "\n", + " .dataframe thead th {\n", + " text-align: right;\n", + " }\n", + "</style>\n", + "<table border=\"1\" class=\"dataframe\">\n", + " <thead>\n", + " <tr style=\"text-align: right;\">\n", + " <th></th>\n", + " <th>name</th>\n", + " <th>name_orig</th>\n", + " <th>description</th>\n", + " <th>gender</th>\n", + " <th>images</th>\n", + " <th>image_index</th>\n", + " <th>subdir</th>\n", + " </tr>\n", + " <tr>\n", + " <th>index</th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>A. J. Cook</td>\n", + " <td>AJ Cook</td>\n", + " <td>Canadian actress</td>\n", + " <td>f</td>\n", + " <td>1</td>\n", + " <td>0</td>\n", + " <td>AJ_Cook</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>AJ Lamas</td>\n", + " <td>AJ Lamas</td>\n", + " <td>American actor</td>\n", + " <td>m</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>AJ_Lamas</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>Aaron Eckhart</td>\n", + " <td>Aaron Eckhart</td>\n", + " <td>American actor</td>\n", + " <td>m</td>\n", + " <td>1</td>\n", + " <td>2</td>\n", + " <td>Aaron_Eckhart</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>Aaron Guiel</td>\n", + " <td>Aaron Guiel</td>\n", + " <td>Professional baseball player</td>\n", + " <td>m</td>\n", + " <td>1</td>\n", + " <td>3</td>\n", + " <td>Aaron_Guiel</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>Aaron Patterson</td>\n", + " <td>Aaron Patterson</td>\n", + " <td>Author</td>\n", + " <td>m</td>\n", + " <td>1</td>\n", + " <td>4</td>\n", + " <td>Aaron_Patterson</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "</div>" + ], + "text/plain": [ + " name name_orig description gender \\\n", + "index \n", + "0 A. J. Cook AJ Cook Canadian actress f \n", + "1 AJ Lamas AJ Lamas American actor m \n", + "2 Aaron Eckhart Aaron Eckhart American actor m \n", + "3 Aaron Guiel Aaron Guiel Professional baseball player m \n", + "4 Aaron Patterson Aaron Patterson Author m \n", + "\n", + " images image_index subdir \n", + "index \n", + "0 1 0 AJ_Cook \n", + "1 1 1 AJ_Lamas \n", + "2 1 2 Aaron_Eckhart \n", + "3 1 3 Aaron_Guiel \n", + "4 1 4 Aaron_Patterson " + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_identity.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [], + "source": [ + "df_identity.to_csv(fp_identity_out)" + ] + }, + { + "cell_type": "code", + "execution_count": 138, + "metadata": {}, + "outputs": [], + "source": [ + "# make a clean index separate from files" + ] + }, + { + "cell_type": "code", + "execution_count": 145, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'AJ Lamas'" + ] + }, + "execution_count": 145, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#df_identies = pd.read_csv('identities.csv')\n", + "df_identities.iloc[1]['name']" + ] + }, + { + "cell_type": "code", + "execution_count": 149, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "1 2 3 4\n" + ] + } + ], + "source": [ + "a = [1,2,3,4]\n", + "\n", + "print(*a)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python [conda env:megapixels]", + "language": "python", + "name": "conda-env-megapixels-py" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.6" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/megapixels/notebooks/examples/face_recognition_demo.ipynb b/megapixels/notebooks/examples/face_recognition_demo.ipynb index 68c5f3b6..804c63b6 100644 --- a/megapixels/notebooks/examples/face_recognition_demo.ipynb +++ b/megapixels/notebooks/examples/face_recognition_demo.ipynb @@ -402,7 +402,9 @@ "execution_count": null, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "import imutils" + ] }, { "cell_type": "code", |