def dataset_creator(config):
opt = config["opt"]
hyper_params = config["hyper_params"]
train_data, _ = data_utils.get_dataset("voc/2007", "train+validation")
val_data, _ = data_utils.get_dataset("voc/2007", "test")
if opt.with_voc12:
voc_2012_data, _ = data_utils.get_dataset("voc/2012",
"train+validation")
train_data = train_data.concatenate(voc_2012_data)
img_size = hyper_params["img_size"]
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(opt.batch_size * 4).padded_batch(
opt.batch_size,
padded_shapes=data_shapes,
padding_values=padding_values)
val_data = val_data.padded_batch(opt.batch_size,
padded_shapes=data_shapes,
padding_values=padding_values)
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)
ssd_val_feed = train_utils.generator(val_data, prior_boxes, hyper_params)
return ssd_train_feed, ssd_val_feed
hyper_params["total_labels"] = len(labels)
img_size = hyper_params["img_size"]
data_types = data_utils.get_data_types()
data_shapes = data_utils.get_data_shapes()
padding_values = data_utils.get_padding_values()
if use_custom_images:
img_paths = data_utils.get_custom_imgs(custom_image_path)
total_items = len(img_paths)
test_data = tf.data.Dataset.from_generator(
lambda: data_utils.custom_data_generator(img_paths, img_size, img_size
), data_types, data_shapes)
else:
test_data = test_data.map(
lambda x: data_utils.preprocessing(x, img_size, img_size))
test_data = test_data.padded_batch(batch_size,
padded_shapes=data_shapes,
padding_values=padding_values)
rpn_model, _ = get_model(hyper_params)
frcnn_model_path = io_utils.get_model_path("faster_rcnn", backbone)
rpn_model_path = io_utils.get_model_path("rpn", backbone)
model_path = frcnn_model_path if load_weights_from_frcnn else rpn_model_path
rpn_model.load_weights(model_path, by_name=True)
anchors = bbox_utils.generate_anchors(hyper_params)
for image_data in test_data:
"voc/2012", "train+validation")
voc_2012_total_items = data_utils.get_total_item_size(
voc_2012_info, "train+validation")
train_total_items += voc_2012_total_items
train_data = train_data.concatenate(voc_2012_data)
#
# Get labels
labels = data_utils.get_labels(info)
# Add background label into labels
labels = ["bg"] + labels
# Get hyper-parameters and image size
hyper_params["total_labels"] = len(labels)
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(
val_total_items = data_utils.get_total_item_size(dataset_info, "test")
if with_voc_2012:
voc_2012_data, voc_2012_info = data_utils.get_dataset(
"voc/2012", "train+validation")
voc_2012_total_items = data_utils.get_total_item_size(
voc_2012_info, "train+validation")
train_total_items += voc_2012_total_items
train_data = train_data.concatenate(voc_2012_data)
labels = data_utils.get_labels(dataset_info)
# We add 1 class for background
hyper_params["total_labels"] = len(labels) + 1
(img_width, img_height) = hyper_params["img_size"]
train_data = train_data.map(lambda x: data_utils.preprocessing(
x, img_width, img_height, apply_augmentation=True))
val_data = val_data.map(
lambda x: data_utils.preprocessing(x, img_width, img_height))
data_shapes = data_utils.get_data_shapes()
padding_values = data_utils.get_padding_values()
train_data = train_data.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)
anchors = bbox_utils.generate_anchors(hyper_params)
rpn_train_feed = train_utils.rpn_generator(train_data, anchors, hyper_params)
rpn_val_feed = train_utils.rpn_generator(val_data, anchors, hyper_params)
labels = ["bg"] + labels
hyper_params["total_labels"] = len(labels)
img_size = hyper_params["img_size"]
data_types = data_utils.get_data_types()
data_shapes = data_utils.get_data_shapes()
padding_values = data_utils.get_padding_values()
if use_custom_images:
img_paths = data_utils.get_custom_imgs(custom_image_path)
total_items = len(img_paths)
test_data = tf.data.Dataset.from_generator(
lambda: data_utils.custom_data_generator(img_paths, img_size, img_size
), data_types, data_shapes)
else:
test_data = test_data.map(lambda x: data_utils.preprocessing(
x, img_size, img_size, evaluate=evaluate))
test_data = test_data.padded_batch(batch_size,
padded_shapes=data_shapes,
padding_values=padding_values)
ssd_model = get_model(hyper_params)
ssd_model_path = io_utils.get_model_path(backbone)
ssd_model.load_weights(ssd_model_path)
prior_boxes = bbox_utils.generate_prior_boxes(
hyper_params["feature_map_shapes"], hyper_params["aspect_ratios"])
ssd_decoder_model = get_decoder_model(ssd_model, prior_boxes, hyper_params)
step_size = train_utils.get_step_size(total_items, batch_size)
pred_bboxes, pred_labels, pred_scores = ssd_decoder_model.predict(
val_data, _ = data_utils.get_dataset("voc/2007", "test")
train_total_items = data_utils.get_total_item_size(dataset_info, "train+validation")
val_total_items = data_utils.get_total_item_size(dataset_info, "test")
if with_voc_2012:
voc_2012_data, voc_2012_info = data_utils.get_dataset("voc/2012", "train+validation")
voc_2012_total_items = data_utils.get_total_item_size(voc_2012_info, "train+validation")
train_total_items += voc_2012_total_items
train_data = train_data.concatenate(voc_2012_data)
labels = data_utils.get_labels(dataset_info)
# We add 1 class for background
hyper_params["total_labels"] = len(labels) + 1
#
img_size = hyper_params["img_size"]
train_data = train_data.map(lambda x: data_utils.preprocessing(x, img_size, img_size, apply_augmentation=True))
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.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)
anchors = bbox_utils.generate_anchors(hyper_params)
frcnn_train_feed = train_utils.faster_rcnn_generator(train_data, anchors, hyper_params)
frcnn_val_feed = train_utils.faster_rcnn_generator(val_data, anchors, hyper_params)
#
rpn_model, feature_extractor = get_rpn_model(hyper_params)
frcnn_model = faster_rcnn.get_model(feature_extractor, rpn_model, anchors, hyper_params)
frcnn_model.compile(optimizer=tf.optimizers.Adam(learning_rate=1e-5),
loss=[None] * len(frcnn_model.output))
