update site, white

3 files changed, 422 insertions, 1 deletions

diff --git a/megapixels/commands/processor/_old_files_to_face_rois.py b/megapixels/commands/processor/_old_files_to_face_rois.py
index 895f4718..d92cbd74 100644
--- a/megapixels/commands/processor/_old_files_to_face_rois.py
+++ b/megapixels/commands/processor/_old_files_to_face_rois.py
@@ -1,4 +1,4 @@
- """
+"""
 Crop images to prepare for training
 """
 
diff --git a/megapixels/commands/processor/face_roi_from_annos.py b/megapixels/commands/processor/face_roi_from_annos.py
new file mode 100644
index 00000000..fc933049
--- /dev/null
+++ b/megapixels/commands/processor/face_roi_from_annos.py
@@ -0,0 +1,187 @@
+"""
+Crop images to prepare for training
+"""
+
+import click
+# from PIL import Image, ImageOps, ImageFilter, ImageDraw
+
+from app.settings import types
+from app.utils import click_utils
+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', 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('--store', 'opt_data_store',
+  type=cfg.DataStoreVar,
+  default=click_utils.get_default(types.DataStore.HDD),
+  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=(480, 480),
+  help='Output image size')
+@click.option('-d', '--detector', 'opt_detector_type',
+  type=cfg.FaceDetectNetVar,
+  default=click_utils.get_default(types.FaceDetectNet.CVDNN),
+  help=click_utils.show_help(types.FaceDetectNet))
+@click.option('-g', '--gpu', 'opt_gpu', default=0,
+  help='GPU index')
+@click.option('--conf', 'opt_conf_thresh', default=0.85, type=click.FloatRange(0,1),
+  help='Confidence minimum threshold')
+@click.option('-p', '--pyramids', 'opt_pyramids', default=0, type=click.IntRange(0,4),
+  help='Number pyramids to upscale for DLIB detectors')
+@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None),
+  help='Slice list of files')
+@click.option('--display/--no-display', 'opt_display', is_flag=True, default=False,
+  help='Display detections to debug')
+@click.option('-f', '--force', 'opt_force', is_flag=True,
+  help='Force overwrite file')
+@click.option('--color', 'opt_color_filter', 
+  type=click.Choice(color_filters.keys()), default='color',
+  help='Filter to keep color or grayscale images (color = keep color')
+@click.option('--keep', 'opt_largest', type=click.Choice(['largest', 'all']), default='largest',
+  help='Only keep largest face')
+@click.option('--zone', 'opt_zone', default=(0.0, 0.0), type=(float, float), 
+  help='Face center must be located within zone region (0.5 = half width/height)')
+@click.pass_context
+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, opt_zone):
+  """Converts frames with faces to CSV of ROIs"""
+  
+  import sys
+  import os
+  from os.path import join
+  from pathlib import Path
+  from glob import glob
+  
+  from tqdm import tqdm
+  import numpy as np
+  import dlib  # must keep a local reference for dlib
+  import cv2 as cv
+  import pandas as pd
+
+  from app.utils import logger_utils, file_utils, im_utils, display_utils, draw_utils
+  from app.processors import face_detector
+  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_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:
+    detector = face_detector.DetectorDLIBCNN(gpu=opt_gpu)
+  elif opt_detector_type == types.FaceDetectNet.DLIB_HOG:
+    detector = face_detector.DetectorDLIBHOG()
+  elif opt_detector_type == types.FaceDetectNet.MTCNN_TF:
+    detector = face_detector.DetectorMTCNN_TF(gpu=opt_gpu)
+  elif opt_detector_type == types.FaceDetectNet.HAAR:
+    log.error('{} not yet implemented'.format(opt_detector_type.name))
+    return
+
+  
+  # get list of files to process
+  fp_record = data_store.metadata(types.Metadata.FILE_RECORD) if opt_fp_in is None else opt_fp_in
+  df_record = pd.read_csv(fp_record, dtype=cfg.FILE_RECORD_DTYPES).set_index('index')
+  if opt_slice:
+    df_record = df_record[opt_slice[0]:opt_slice[1]]
+  log.debug('processing {:,} files'.format(len(df_record)))
+
+  # filter out grayscale
+  color_filter = color_filters[opt_color_filter]
+  # set largest flag, to keep all or only largest
+  opt_largest = (opt_largest == 'largest')
+
+  data = []
+  skipped_files = []
+  processed_files = []
+
+  for df_record in tqdm(df_record.itertuples(), total=len(df_record)):
+    fp_im = data_store.face(str(df_record.subdir), str(df_record.fn), str(df_record.ext))
+    try:
+      im = cv.imread(fp_im)
+      im_resized = im_utils.resize(im, width=opt_size[0], height=opt_size[1])
+    except Exception as e:
+      log.debug(f'could not read: {fp_im}')
+      return
+    # filter out color or grayscale iamges
+    if color_filter != color_filters['all']:
+      try:
+        is_gray = im_utils.is_grayscale(im)
+        if is_gray and color_filter != color_filters['gray']:
+          log.debug('Skipping grayscale image: {}'.format(fp_im))
+          continue
+      except Exception as e:
+        log.error('Could not check grayscale: {}'.format(fp_im))
+        continue
+    
+    try:
+      bboxes_norm = detector.detect(im_resized, pyramids=opt_pyramids, largest=opt_largest, 
+        zone=opt_zone, conf_thresh=opt_conf_thresh)
+    except Exception as e:
+      log.error('could not detect: {}'.format(fp_im))
+      log.error('{}'.format(e))
+      continue
+
+    if len(bboxes_norm) == 0:
+      skipped_files.append(fp_im)
+      log.warn(f'no faces in: {fp_im}')
+      log.warn(f'skipped: {len(skipped_files)}. found:{len(processed_files)} files')
+    else:
+      processed_files.append(fp_im)
+      for bbox in bboxes_norm:
+        roi = {
+          'record_index': int(df_record.Index),
+          'x': bbox.x,
+          'y': bbox.y,
+          'w': bbox.w,
+          'h': bbox.h
+          }
+        data.append(roi)
+
+    # if display optined
+    if opt_display and len(bboxes_norm):
+      # draw each box
+      for bbox_norm in bboxes_norm:
+        dim = im_resized.shape[:2][::-1]
+        bbox_dim = bbox.to_dim(dim)
+        if dim[0] > 1000:
+          im_resized = im_utils.resize(im_resized, width=1000)
+        im_resized = draw_utils.draw_bbox(im_resized, bbox_norm)
+
+      # display and wait
+      cv.imshow('', im_resized)
+      display_utils.handle_keyboard()
+
+  # create DataFrame and save to CSV
+  file_utils.mkdirs(fp_out)
+  df = pd.DataFrame.from_dict(data)
+  df.index.name = 'index'
+  df.to_csv(fp_out)
+
+  # save script
+  file_utils.write_text(' '.join(sys.argv), '{}.sh'.format(fp_out))
\ No newline at end of file
diff --git a/megapixels/commands/processor/file_record.py b/megapixels/commands/processor/file_record.py
new file mode 100644
index 00000000..6403c768
--- /dev/null
+++ b/megapixels/commands/processor/file_record.py
@@ -0,0 +1,234 @@
+'''
+
+'''
+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()
+
+# Choose part of the filepath that will be used for the person identity
+# eg subdirectory "lfw/media/original/batch_1/train/barack_obama/001.jpg" --> [subdir_tail] --> "barack_obama"
+# eg subdirectory "lfw/media/original/batch_1/train/barack_obama/001.jpg" --> [subdir_head] --> "batch_1"
+# eg subdirectory "lfw/media/original/batch_1/train/barack_obama/001.jpg" --> [subdir] --> "barack_obama"
+
+identity_sources = ['subdir', 'numeric']
+
+@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.HDD),
+  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', type=click.Choice(identity_sources),
+  required=True,
+  help='Identity source key')
+@click.option('--recursive/--no-recursive', 'opt_recursive', is_flag=True, default=False,
+  help='Use glob recursion (slower)')
+@click.option('--max-depth', 'opt_max_depth', default=None, type=int,
+  help='Max number of images per subdirectory')
+@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, opt_max_depth):
+  """Generates sha256, uuid, and identity index CSV file"""
+  
+  import sys, os
+  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
+
+  from PIL import Image
+  import cv2 as cv
+  import pandas as pd
+  from tqdm import tqdm
+  from glob import glob
+  from operator import itemgetter
+
+  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(f'File {fp_out} 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)
+
+  log.info('Found {:,} images'.format(len(fp_ims)))
+  subdir_groups = {}
+  if opt_max_depth:
+    log.debug(f'using max depth: {opt_max_depth}')
+    for fp_im in fp_ims:
+      fpp_im = Path(fp_im)
+
+      subdir = fp_im.split('/')[-2]
+      if not subdir in subdir_groups.keys():
+        subdir_groups[subdir] = []
+      else:
+        subdir_groups[subdir].append(fp_im)
+    # for each subgroup, limit number of files
+    fp_ims = []
+    for subdir_name, items in subdir_groups.items():
+      ims = items[0:opt_max_depth]
+      fp_ims += ims
+
+  log.debug(f'num subdirs: {len(subdir_groups.keys())}')
+  # 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 pool_mapper(fp_im):
+    pbar.update(1)
+    try:
+      sha256 = file_utils.sha256(fp_im)
+      im = Image.open(fp_im)
+      im.verify()  # throws error if bad file
+      assert(im.size[0] > 60 and im.size[1] > 60)
+    except Exception as e:
+      log.warn(f'skipping file: {fp_im}')
+      return None
+    im = cv.imread(fp_im)
+    w, h = im.shape[:2][::-1]
+    file_size_kb = os.stat(fp_im).st_size // 1000
+    num_channels = im_utils.num_channels(im)
+    return {
+      'width': w, 
+      'height': h, 
+      'sha256': sha256,
+      'file_size_kb': file_size_kb, 
+      'num_channels': num_channels
+      }
+
+  # convert to thread pool
+  pool_maps = []  # ?
+  pool = ThreadPool(opt_threads) 
+  with tqdm(total=len(fp_ims)) as pbar:
+    pool_maps = pool.map(pool_mapper, fp_ims)
+  pbar.close()
+
+
+  # ----------------------------------------------------------------
+  # convert data to dict
+  
+  data = []
+  indentity_count = 0
+  for pool_map, fp_im in zip(pool_maps, fp_ims):
+    if pool_map is None:
+      log.warn(f'skipping file: {fp_im}')
+      continue  # skip error files
+    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[-1]  # use last part of subdir path
+      elif opt_identity == 'numeric':
+        identity = indentity_count  # use incrementing number
+        indentity_count += 1
+    else:
+      identity = ''
+
+    data.append({
+      'subdir': subdir,
+      'num_channels': pool_map['num_channels'],
+      'fn': fpp_im.stem,
+      'ext': fpp_im.suffix.replace('.',''),
+      'sha256': pool_map['sha256'],
+      'uuid': uuid.uuid4(),
+      'identity_key': identity,
+      'width': pool_map['width'],
+      'height': pool_map['height']
+      })
+
+  # create dataframe
+  df_records = pd.DataFrame.from_dict(data)
+
+  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 {len(df_records)} rows to "{fp_out}"')
+  # save script
+  cmd_line = ' '.join(sys.argv)
+  file_utils.write_text(cmd_line, '{}.sh'.format(fp_out))
+
+
+'''
+# create dataframe
+  df_records = pd.DataFrame.from_dict(data)
+
+  # add identity key (used for associating identity)
+  if opt_identity:
+    log.info(f'adding identity index using: "{opt_identity}" subdirectory')
+    # convert dict to DataFrame
+    # 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
+    log.info(f'updating records with identity_key. This may take a while...')
+    st = time.time()
+    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)
+    log.debug('update time: {:.2f}s'.format(time.time() - st))
+  else:
+    # name everyone person 1, 2, 3...
+    df_records = df_records.sort_values(by=['subdir'], ascending=True)
+    pass
+'''
\ No newline at end of file