Merge branch 'master' of asdf.us:megapixels_dev

6 files changed, 352 insertions, 3 deletions

diff --git a/megapixels/commands/datasets/megaface_age_from_orig.py b/megapixels/commands/datasets/megaface_age_from_orig.py
new file mode 100644
index 00000000..489bebf3
--- /dev/null
+++ b/megapixels/commands/datasets/megaface_age_from_orig.py
@@ -0,0 +1,62 @@
+import click
+
+@click.command()
+@click.option('-i', '--input', 'opt_fp_in', required=True,
+  help='Input path to metadata directory')
+@click.option('-o', '--output', 'opt_fp_out',
+  help='Output path to age CSV')
+@click.pass_context
+def cli(ctx, opt_fp_in, opt_fp_out):
+  """Creates CSV of MegaFace ages from original BBoxes"""
+  
+  import os
+  from os.path import join
+  from pathlib import Path
+  from glob import glob
+
+  import dlib
+  import pandas as pd
+  from tqdm import tqdm
+
+  from app.settings import types
+  from app.utils import click_utils
+  from app.settings import app_cfg
+
+  from PIL import Image, ImageOps, ImageFilter
+  from app.utils import file_utils, im_utils, logger_utils
+
+  log = logger_utils.Logger.getLogger()
+
+  # -------------------------------------------------
+  # process  
+  fp_im_dirs = glob(join(opt_fp_in, '**/'), recursive=True)
+  
+  log.info('Found {} directories'.format(len(fp_im_dirs)))
+
+  identities = {}
+
+  for fp_im_dir in tqdm(fp_im_dirs):
+    # 1234567@N05_identity_1
+    try:
+      dir_id_name = Path(fp_im_dir).name
+      nsid = dir_id_name.split('_')[0]
+      identity_num = dir_id_name.split('_')[2]
+      id_key = '{}_{}'.format(nsid, identity_num)
+      num_images = len(glob(join(fp_im_dir, '*.jpg')))
+      if not id_key in identities.keys():
+        identities[id_key] = {'nsid': nsid, 'identity': identity_num, 'images': num_images}
+      else:
+        identities[id_key]['images'] += num_images
+    except Exception as e:
+      continue  
+
+  # convert to dict 
+  identities_list = [v for k, v in identities.items()]
+  df = pd.DataFrame.from_dict(identities_list)
+
+  file_utils.mkdirs(opt_fp_out)
+
+  log.info('Wrote {} lines to {}'.format(len(df), opt_fp_out))
+  df.to_csv(opt_fp_out, index=False)
+
+
diff --git a/megapixels/commands/demo/face_search.py b/megapixels/commands/demo/face_search.py
index 4c7036f4..5218d501 100644
--- a/megapixels/commands/demo/face_search.py
+++ b/megapixels/commands/demo/face_search.py
@@ -10,7 +10,7 @@ log = Logger.getLogger()
 
 @click.command()
 @click.option('-i', '--input', 'opt_fp_in', required=True,
-  help='File to lookup')
+  help='Face image file to lookup')
 @click.option('--data_store', 'opt_data_store',
   type=cfg.DataStoreVar,
   default=click_utils.get_default(types.DataStore.HDD),
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/datasets/file_record.py b/megapixels/commands/processor/file_record.py
index 41a5df28..6403c768 100644
--- a/megapixels/commands/datasets/file_record.py
+++ b/megapixels/commands/processor/file_record.py
@@ -78,7 +78,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dataset, opt_data_store, opt_dir_media,
   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')
+    log.error(f'File {fp_out} exists. Use "-f / --force" to overwite')
     return
   
   # ----------------------------------------------------------------
diff --git a/megapixels/commands/site/age_gender_to_site.py b/megapixels/commands/site/age_gender_to_site.py
new file mode 100644
index 00000000..3ad24a8d
--- /dev/null
+++ b/megapixels/commands/site/age_gender_to_site.py
@@ -0,0 +1,100 @@
+"""
+
+"""
+
+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('-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('-f', '--force', 'opt_force', is_flag=True,
+  help='Force overwrite file')
+@click.pass_context
+def cli(ctx, opt_fp_in, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_force):
+  """Converts age/gender to CSV for pie chartgs"""
+  
+  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 cv2 as cv
+  import pandas as pd
+
+  from app.utils import logger_utils
+  from app.models.data_store import DataStore
+
+  # -------------------------------------------------------------------------
+  # init here
+
+  log = logger_utils.Logger.getLogger()
+  
+  # init filepaths
+  data_store = DataStore(opt_data_store, opt_dataset)
+  # set file output path
+  metadata_type = types.Metadata.FACE_ATTRIBUTES
+  fp_in = data_store.metadata(metadata_type) if opt_fp_out is None else opt_fp_in
+  dk = opt_dataset.name.lower()
+  log.debug(f'dk: {dk}')
+  fp_out_age = f'../site/content/pages/datasets/{dk}/assets/age.csv'
+  fp_out_gender = f'../site/content/pages/datasets/{dk}/assets/gender.csv'
+
+  if not opt_force and (Path(fp_out_age).exists() or Path(fp_out_gender).exists()):
+    log.error('File exists. Use "-f / --force" to overwite')
+    return
+
+  # -------------------------------------------------------------------------
+  # Age
+
+  df = pd.read_csv(fp_in)
+
+  results = []
+  brackets = [(0, 12), (13, 18), (19,24), (25, 34), (35, 44), (45, 54), (55, 64), (64, 75), (75, 100)]
+  df_age = df['age_real']
+
+  for a1, a2 in brackets:
+    n = len(df_age.loc[((df_age >= a1) & (df_age <= a2))])
+    results.append({'age': f'{a1} - {a2}', 'faces': n})
+    
+  df_out = pd.DataFrame.from_dict(results)
+  df_out = df_out[['age','faces']]
+  df_out.to_csv(fp_out_age, index=False)
+
+  # Gender
+  results = []
+
+  df_f = df['f']
+  nm = len(df_f.loc[((df_f < 0.33))])
+  nnb = len(df_f.loc[((df_f >= 0.33) & (df_f <= 0.66))])
+  nf = len(df_f.loc[((df_f > 0.66))])
+
+  results = []
+  results.append({'gender': 'Male', 'faces':nm})
+  results.append({'gender': 'Female', 'faces': nf})
+  results.append({'gender': 'They', 'faces': nnb})
+
+  df_out = pd.DataFrame.from_dict(results)
+  df_out = df_out[['gender','faces']]
+  df_out.to_csv(fp_out_gender, index=False)
\ No newline at end of file