P&G Report

  # log semantic segmentation in the new style

  def on_epoch_end(self, **kwargs):

    input_batch = self.learn.data.valid_ds[:num_log]

    mask_list = []

    for i, img in enumerate(input_batch):

config.img_size = (360, 640)    # dimensions of resized image - can be 1 dim or tuple

config.epochs = 10            # Number of epochs for training

if config.encoder == "resnet18":

  encoder = models.resnet18     # encoder of unet (contracting path)

elif config.encoder == "resnet34":

  encoder = models.resnet34

elif config.encoder == "squeezenet1_0":

config.bn_weight_decay = True # whether weight decay is applied on batch norm layers

config.one_cycle = True         # use the "1cycle" policy -> https://arxiv.org/abs/1803.09820

# SWEEPS UNCOMMENT

save_model = False

# Custom values to filter runs

# SWEEPS UNCOMMENT

# Data paths

path_data = Path('../../../../BigData/bdd100K/bdd100k/seg')

path_lbl = path_data / 'labels'

path_img = path_data / 'images'

# Associate a label to an input

get_y_fn = lambda x: path_lbl / x.parts[-2] / f'{x.stem}_train_id.png'