curiousily

cfg.DATASETS.TRAIN = ("faces_train",)
cfg.DATASETS.TEST = ("faces_val",)
cfg.DATALOADER.NUM_WORKERS = 4

curiousily

cfg = get_cfg()

cfg.merge_from_file(
  model_zoo.get_config_file(
    "COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x.yaml"
  )
)

cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url(
  "COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x.yaml"

curiousily

class CocoTrainer(DefaultTrainer):

  @classmethod
  def build_evaluator(cls, cfg, dataset_name, output_folder=None):

    if output_folder is None:
        os.makedirs("coco_eval", exist_ok=True)
        output_folder = "coco_eval"

    return COCOEvaluator(dataset_name, cfg, False, output_folder)

curiousily

for d in ["train", "val"]:
  DatasetCatalog.register("faces_" + d, lambda d=d: create_dataset_dicts(train_df if d == "train" else test_df, classes))
  MetadataCatalog.get("faces_" + d).set(thing_classes=classes)

statement_metadata = MetadataCatalog.get("faces_train")

curiousily

def create_dataset_dicts(df, classes):
  dataset_dicts = []
  for image_id, img_name in enumerate(df.file_name.unique()):

    record = {}

    image_df = df[df.file_name == img_name]

    file_path = f'{IMAGES_PATH}/{img_name}'
    record["file_name"] = file_path

curiousily

classes = df.class_name.unique().tolist()

curiousily

df = pd.read_csv('annotations.csv')

IMAGES_PATH = f'faces'

unique_files = df.file_name.unique()

train_files = set(np.random.choice(unique_files, int(len(unique_files) * 0.95), replace=False))
train_df = df[df.file_name.isin(train_files)]
test_df = df[~df.file_name.isin(train_files)]

curiousily

def annotate_image(annotations, resize=True):
  file_name = annotations.file_name.to_numpy()[0]
  img = cv2.cvtColor(cv2.imread(f'faces/{file_name}'), cv2.COLOR_BGR2RGB)

  for i, a in annotations.iterrows():
    cv2.rectangle(img, (a.x_min, a.y_min), (a.x_max, a.y_max), (0, 255, 0), 2)

  if not resize:
    return img

curiousily

df.to_csv('annotations.csv', header=True, index=None)

curiousily

df = pd.DataFrame(dataset)
print(df.file_name.unique().shape[0], df.shape[0])