def model_creator(config):
opt = config["opt"]
hyper_params = config["hyper_params"]
ssd_model = get_model(hyper_params)
ssd_custom_losses = CustomLoss(hyper_params["neg_pos_ratio"],
hyper_params["loc_loss_alpha"])
ssd_model.compile(
optimizer=Adam(learning_rate=1e-3),
loss=[ssd_custom_losses.loc_loss_fn, ssd_custom_losses.conf_loss_fn])
init_model(ssd_model)
if opt.load_weights:
ssd_model.load_weights(config["ssd_model_path"])
return ssd_model
img_size = hyper_params["img_size"]
# Data pre-processing
train_data = train_data.map(lambda x: data_utils.preprocessing(
x, img_size, img_size, augmentation.apply))
val_data = val_data.map(
lambda x: data_utils.preprocessing(x, img_size, img_size))
data_shapes = data_utils.get_data_shapes()
padding_values = data_utils.get_padding_values()
train_data = train_data.shuffle(batch_size * 4).padded_batch(
batch_size, padded_shapes=data_shapes, padding_values=padding_values)
val_data = val_data.padded_batch(batch_size,
padded_shapes=data_shapes,
padding_values=padding_values)
# Setup training model (ssd+vgg) and loss function (location + confidence)
ssd_model = get_model(hyper_params)
ssd_custom_losses = CustomLoss(hyper_params["neg_pos_ratio"],
hyper_params["loc_loss_alpha"])
ssd_model.compile(
optimizer=Adam(learning_rate=1e-3),
loss=[ssd_custom_losses.loc_loss_fn, ssd_custom_losses.conf_loss_fn])
init_model(ssd_model)
ssd_model_path = io_utils.get_model_path(backbone)
if load_weights:
ssd_model.load_weights(ssd_model_path)
ssd_log_path = io_utils.get_log_path(backbone)
# We calculate prior boxes for one time and use it for all operations because of the all images are the same sizes
prior_boxes = bbox_utils.generate_prior_boxes(
hyper_params["feature_map_shapes"], hyper_params["aspect_ratios"])
ssd_train_feed = train_utils.generator(train_data, prior_boxes, hyper_params)