fixing dataset procesosrs

4 files changed, 37 insertions, 37 deletions

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/gen_pose.py b/megapixels/commands/cv/face_pose.py
index aefadb00..e7ffb7ac 100644
--- a/megapixels/commands/cv/gen_pose.py
+++ b/megapixels/commands/cv/face_pose.py
@@ -76,27 +76,26 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset,
   face_landmarks = LandmarksDLIB()
 
   # load filepath data
-  fp_filepath = data_store.metadata(types.Metadata.FILEPATH)
-  df_filepath = pd.read_csv(fp_filepath)
+  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)
+  df_roi = pd.read_csv(fp_roi).set_index('index')
   # slice if you want
   if opt_slice:
     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('image_index')
+  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 image_index, df_img_group in tqdm(df_img_groups):
+  for record_index, df_img_group in tqdm(df_img_groups):
     # make fp
-    ds_file = df_filepath.iloc[image_index]
-    fp_im = data_store.face_image(ds_file.subdir, ds_file.fn, ds_file.ext)
-    #fp_im = join(opt_dir_media, ds_file.subdir, '{}.{}'.format(ds_file.fn, ds_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]
@@ -130,7 +129,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset,
           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)
 
 
diff --git a/megapixels/commands/cv/gen_rois.py b/megapixels/commands/cv/face_roi.py
index 20dd598a..d7248aee 100644
--- a/megapixels/commands/cv/gen_rois.py
+++ b/megapixels/commands/cv/face_roi.py
@@ -103,20 +103,19 @@ def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_data_store, opt_dataset,
 
   
   # get list of files to process
-  fp_in = data_store.metadata(types.Metadata.FILEPATH) if opt_fp_in is None else opt_fp_in
-  df_files = pd.read_csv(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 = data_store.face_image(str(df_file.subdir), str(df_file.fn), str(df_file.ext))
-    #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
@@ -139,7 +138,7 @@ def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_data_store, opt_dataset,
 
     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, 
@@ -169,4 +168,4 @@ def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_data_store, opt_dataset,
   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/gen_face_vec.py b/megapixels/commands/cv/face_vector.py
index 83e1460d..203f73eb 100644
--- a/megapixels/commands/cv/gen_face_vec.py
+++ b/megapixels/commands/cv/face_vector.py
@@ -76,15 +76,17 @@ def cli(ctx, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size,
   facerec = face_recognition.RecognitionDLIB()
 
   # load data
-  df_file = pd.read_csv(data_store.metadata(types.Metadata.FILEPATH)).set_index('index')
-  df_roi = pd.read_csv(data_store.metadata(types.Metadata.FACE_ROI)).set_index('index')
+  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 opt_slice:
     df_roi = df_roi[opt_slice[0]:opt_slice[1]]
   
   # -------------------------------------------------
   # process here
-  df_img_groups = df_roi.groupby('image_index')
+  df_img_groups = df_roi.groupby('record_index')
   log.debug('processing {:,} groups'.format(len(df_img_groups)))
 
   vecs = []
@@ -92,9 +94,9 @@ def cli(ctx, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size,
   for image_index, df_img_group in tqdm(df_img_groups):
     # make fp
     roi_index = df_img_group.index.values[0]
-    log.debug(f'roi_index: {roi_index}, image_index: {image_index}')
-    ds_file = df_file.loc[roi_index]  # locate image meta
-    #ds_file = df_file.loc['index', image_index]  # locate image meta
+    # 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)
@@ -119,5 +121,5 @@ def cli(ctx, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size,
   # save date
   df = pd.DataFrame.from_dict(vecs)
   df.index.name = 'index'
-  #file_utils.mkdirs(fp_out)
-  #df.to_csv(fp_out)
\ No newline at end of file
+  file_utils.mkdirs(fp_out)
+  df.to_csv(fp_out)
\ No newline at end of file