def create_faster_rcnn_model(features, scaled_gt_boxes, dims_input, cfg):
# Load the pre-trained classification net and clone layers
base_model = load_model(cfg['BASE_MODEL_PATH'])
conv_layers = clone_conv_layers(base_model, cfg)
fc_layers = clone_model(base_model, [cfg["MODEL"].POOL_NODE_NAME],
[cfg["MODEL"].LAST_HIDDEN_NODE_NAME],
clone_method=CloneMethod.clone)
# Normalization and conv layers
feat_norm = features - Constant([[[v]]
for v in cfg["MODEL"].IMG_PAD_COLOR])
conv_out = conv_layers(feat_norm)
# RPN and prediction targets
rpn_rois, rpn_losses = create_rpn(conv_out, scaled_gt_boxes, dims_input,
cfg)
rois, label_targets, bbox_targets, bbox_inside_weights = \
create_proposal_target_layer(rpn_rois, scaled_gt_boxes, cfg)
# Fast RCNN and losses
cls_score, bbox_pred = create_fast_rcnn_predictor(conv_out, rois,
fc_layers, cfg)
detection_losses = create_detection_losses(cls_score, label_targets,
bbox_pred, rois, bbox_targets,
bbox_inside_weights, cfg)
loss = rpn_losses + detection_losses
pred_error = classification_error(cls_score, label_targets, axis=1)
return loss, pred_error
def frcn_predictor(features, rois, n_classes, model_path):
# Load the pretrained classification net and find nodes
loaded_model = load_model(model_path)
feature_node = find_by_name(loaded_model, feature_node_name)
conv_node = find_by_name(loaded_model, last_conv_node_name)
pool_node = find_by_name(loaded_model, pool_node_name)
last_node = find_by_name(loaded_model, last_hidden_node_name)
# Clone the conv layers and the fully connected layers of the network
conv_layers = combine([conv_node.owner
]).clone(CloneMethod.freeze,
{feature_node: placeholder()})
fc_layers = combine([last_node.owner]).clone(CloneMethod.clone,
{pool_node: placeholder()})
# Create the Fast R-CNN model
feat_norm = features - Constant(114)
conv_out = conv_layers(feat_norm)
roi_out = roipooling(conv_out, rois, C.MAX_POOLING, (roi_dim, roi_dim),
0.0625)
fc_out = fc_layers(roi_out)
# z = Dense(rois[0], num_classes, map_rank=1)(fc_out) # --> map_rank=1 is not yet supported
W = parameter(shape=(4096, n_classes), init=glorot_uniform())
b = parameter(shape=n_classes, init=0)
z = times(fc_out, W) + b
return z
def modify_model(features, n_classes):
loaded_model = load_model(model_file)
feature_node = find_by_name(loaded_model, 'features')
last_node = find_by_name(loaded_model, 'h2_d')
all_layers = combine([last_node.owner
]).clone(CloneMethod.freeze,
{feature_node: placeholder()})
feat_norm = features - Constant(114)
fc_out = all_layers(feat_norm)
z = Dense(num_classes)(fc_out)
return (z)
def create_model(base_model_file,
feature_node_name,
last_hidden_node_name,
num_classes,
input_features,
freeze=False):
# Load the pretrained classification net and find nodes
base_model = load_model(base_model_file)
feature_node = find_by_name(base_model, feature_node_name)
last_node = find_by_name(base_model, last_hidden_node_name)
# Clone the desired layers with fixed weights
cloned_layers = combine([last_node.owner]).clone(
CloneMethod.freeze if freeze else CloneMethod.clone,
{feature_node: Placeholder(name='features')})
# Add new dense layer for class prediction
feat_norm = input_features - Constant(114)
cloned_out = cloned_layers(feat_norm)
z = Dense(num_classes, activation=None,
name=new_output_node_name)(cloned_out)
return z
def train_faster_rcnn_alternating(cfg):
'''
4-Step Alternating Training scheme from the Faster R-CNN paper:
# Create initial network, only rpn, without detection network
# --> train only the rpn (and conv3_1 and up for VGG16)
# buffer region proposals from rpn
# Create full network, initialize conv layers with imagenet, use buffered proposals
# --> train only detection network (and conv3_1 and up for VGG16)
# Keep conv weights from detection network and fix them
# --> train only rpn
# buffer region proposals from rpn
# Keep conv and rpn weights from step 3 and fix them
# --> train only detection network
'''
# setting pre- and post-nms top N to training values since buffered proposals are used for further training
test_pre = cfg["TEST"].RPN_PRE_NMS_TOP_N
test_post = cfg["TEST"].RPN_POST_NMS_TOP_N
cfg["TEST"].RPN_PRE_NMS_TOP_N = cfg["TRAIN"].RPN_PRE_NMS_TOP_N
cfg["TEST"].RPN_POST_NMS_TOP_N = cfg["TRAIN"].RPN_POST_NMS_TOP_N
# Learning parameters
rpn_lr_factor = cfg["MODEL"].RPN_LR_FACTOR
rpn_lr_per_sample_scaled = [x * rpn_lr_factor for x in cfg["CNTK"].RPN_LR_PER_SAMPLE]
frcn_lr_factor = cfg["MODEL"].FRCN_LR_FACTOR
frcn_lr_per_sample_scaled = [x * frcn_lr_factor for x in cfg["CNTK"].FRCN_LR_PER_SAMPLE]
l2_reg_weight = cfg["CNTK"].L2_REG_WEIGHT
mm_schedule = momentum_schedule(cfg["CNTK"].MOMENTUM_PER_MB)
rpn_epochs = cfg["CNTK"].RPN_EPOCHS
frcn_epochs = cfg["CNTK"].FRCN_EPOCHS
feature_node_name = cfg["MODEL"].FEATURE_NODE_NAME
last_conv_node_name = cfg["MODEL"].LAST_CONV_NODE_NAME
print("Using base model: {}".format(cfg["MODEL"].BASE_MODEL))
print("rpn_lr_per_sample: {}".format(rpn_lr_per_sample_scaled))
print("frcn_lr_per_sample: {}".format(frcn_lr_per_sample_scaled))
debug_output=cfg["CNTK"].DEBUG_OUTPUT
if debug_output:
print("Storing graphs and models to %s." % cfg.OUTPUT_PATH)
# Input variables denoting features, labeled ground truth rois (as 5-tuples per roi) and image dimensions
image_input = input_variable(shape=(cfg.NUM_CHANNELS, cfg.IMAGE_HEIGHT, cfg.IMAGE_WIDTH),
dynamic_axes=[Axis.default_batch_axis()],
name=feature_node_name)
feat_norm = image_input - Constant([[[v]] for v in cfg["MODEL"].IMG_PAD_COLOR])
roi_input = input_variable((cfg.INPUT_ROIS_PER_IMAGE, 5), dynamic_axes=[Axis.default_batch_axis()])
scaled_gt_boxes = alias(roi_input, name='roi_input')
dims_input = input_variable((6), dynamic_axes=[Axis.default_batch_axis()])
dims_node = alias(dims_input, name='dims_input')
rpn_rois_input = input_variable((cfg["TRAIN"].RPN_POST_NMS_TOP_N, 4), dynamic_axes=[Axis.default_batch_axis()])
rpn_rois_buf = alias(rpn_rois_input, name='rpn_rois')
# base image classification model (e.g. VGG16 or AlexNet)
base_model = load_model(cfg['BASE_MODEL_PATH'])
print("stage 1a - rpn")
if True:
# Create initial network, only rpn, without detection network
# initial weights train?
# conv: base_model only conv3_1 and up
# rpn: init new yes
# frcn: - -
# conv layers
conv_layers = clone_conv_layers(base_model, cfg)
conv_out = conv_layers(feat_norm)
# RPN and losses
rpn_rois, rpn_losses = create_rpn(conv_out, scaled_gt_boxes, dims_node, cfg)
stage1_rpn_network = combine([rpn_rois, rpn_losses])
# train
if debug_output: plot(stage1_rpn_network, os.path.join(cfg.OUTPUT_PATH, "graph_frcn_train_stage1a_rpn." + cfg["CNTK"].GRAPH_TYPE))
train_model(image_input, roi_input, dims_input, rpn_losses, rpn_losses,
rpn_lr_per_sample_scaled, mm_schedule, l2_reg_weight, rpn_epochs, cfg)
print("stage 1a - buffering rpn proposals")
buffered_proposals_s1 = compute_rpn_proposals(stage1_rpn_network, image_input, roi_input, dims_input, cfg)
print("stage 1b - frcn")
if True:
# Create full network, initialize conv layers with imagenet, fix rpn weights
# initial weights train?
# conv: base_model only conv3_1 and up
# rpn: stage1a rpn model no --> use buffered proposals
# frcn: base_model + new yes
# conv_layers
conv_layers = clone_conv_layers(base_model, cfg)
conv_out = conv_layers(feat_norm)
# use buffered proposals in target layer
rois, label_targets, bbox_targets, bbox_inside_weights = \
create_proposal_target_layer(rpn_rois_buf, scaled_gt_boxes, cfg)
# Fast RCNN and losses
fc_layers = clone_model(base_model, [cfg["MODEL"].POOL_NODE_NAME], [cfg["MODEL"].LAST_HIDDEN_NODE_NAME], CloneMethod.clone)
cls_score, bbox_pred = create_fast_rcnn_predictor(conv_out, rois, fc_layers, cfg)
detection_losses = create_detection_losses(cls_score, label_targets, bbox_pred, rois, bbox_targets, bbox_inside_weights, cfg)
pred_error = classification_error(cls_score, label_targets, axis=1, name="pred_error")
stage1_frcn_network = combine([rois, cls_score, bbox_pred, detection_losses, pred_error])
# train
if debug_output: plot(stage1_frcn_network, os.path.join(cfg.OUTPUT_PATH, "graph_frcn_train_stage1b_frcn." + cfg["CNTK"].GRAPH_TYPE))
train_model(image_input, roi_input, dims_input, detection_losses, pred_error,
frcn_lr_per_sample_scaled, mm_schedule, l2_reg_weight, frcn_epochs, cfg,
rpn_rois_input=rpn_rois_input, buffered_rpn_proposals=buffered_proposals_s1)
buffered_proposals_s1 = None
print("stage 2a - rpn")
if True:
# Keep conv weights from detection network and fix them
# initial weights train?
# conv: stage1b frcn model no
# rpn: stage1a rpn model yes
# frcn: - -
# conv_layers
conv_layers = clone_model(stage1_frcn_network, [feature_node_name], [last_conv_node_name], CloneMethod.freeze)
conv_out = conv_layers(image_input)
# RPN and losses
rpn = clone_model(stage1_rpn_network, [last_conv_node_name, "roi_input", "dims_input"], ["rpn_rois", "rpn_losses"], CloneMethod.clone)
rpn_net = rpn(conv_out, dims_node, scaled_gt_boxes)
rpn_rois = rpn_net.outputs[0]
rpn_losses = rpn_net.outputs[1]
stage2_rpn_network = combine([rpn_rois, rpn_losses])
# train
if debug_output: plot(stage2_rpn_network, os.path.join(cfg.OUTPUT_PATH, "graph_frcn_train_stage2a_rpn." + cfg["CNTK"].GRAPH_TYPE))
train_model(image_input, roi_input, dims_input, rpn_losses, rpn_losses,
rpn_lr_per_sample_scaled, mm_schedule, l2_reg_weight, rpn_epochs, cfg)
print("stage 2a - buffering rpn proposals")
buffered_proposals_s2 = compute_rpn_proposals(stage2_rpn_network, image_input, roi_input, dims_input, cfg)
print("stage 2b - frcn")
if True:
# Keep conv and rpn weights from step 3 and fix them
# initial weights train?
# conv: stage2a rpn model no
# rpn: stage2a rpn model no --> use buffered proposals
# frcn: stage1b frcn model yes -
# conv_layers
conv_layers = clone_model(stage2_rpn_network, [feature_node_name], [last_conv_node_name], CloneMethod.freeze)
conv_out = conv_layers(image_input)
# Fast RCNN and losses
frcn = clone_model(stage1_frcn_network, [last_conv_node_name, "rpn_rois", "roi_input"],
["cls_score", "bbox_regr", "rpn_target_rois", "detection_losses", "pred_error"], CloneMethod.clone)
stage2_frcn_network = frcn(conv_out, rpn_rois_buf, scaled_gt_boxes)
detection_losses = stage2_frcn_network.outputs[3]
pred_error = stage2_frcn_network.outputs[4]
# train
if debug_output: plot(stage2_frcn_network, os.path.join(cfg.OUTPUT_PATH, "graph_frcn_train_stage2b_frcn." + cfg["CNTK"].GRAPH_TYPE))
train_model(image_input, roi_input, dims_input, detection_losses, pred_error,
frcn_lr_per_sample_scaled, mm_schedule, l2_reg_weight, frcn_epochs, cfg,
rpn_rois_input=rpn_rois_input, buffered_rpn_proposals=buffered_proposals_s2)
buffered_proposals_s2 = None
# resetting config values to original test values
cfg["TEST"].RPN_PRE_NMS_TOP_N = test_pre
cfg["TEST"].RPN_POST_NMS_TOP_N = test_post
return create_faster_rcnn_eval_model(stage2_frcn_network, image_input, dims_input, cfg, rpn_model=stage2_rpn_network)
image_height = cfg["CNTK"].IMAGE_HEIGHT
num_channels = cfg["CNTK"].NUM_CHANNELS
# dims_input -- (pad_width, pad_height, scaled_image_width, scaled_image_height, orig_img_width, orig_img_height)
dims_input_const = MinibatchData(
Value(batch=np.asarray([
image_width, image_height, image_width, image_height, image_width,
image_height
],
dtype=np.float32)), 1, 1, False)
# Color used for padding and normalization (Caffe model uses [102.98010, 115.94650, 122.77170])
img_pad_value = [103, 116, 123
] if cfg["CNTK"].BASE_MODEL == "VGG16" else [114, 114, 114]
normalization_const = Constant([[[103]], [[116]], [[
123
]]]) if cfg["CNTK"].BASE_MODEL == "VGG16" else Constant([[[114]], [[114]],
[[114]]])
globalvars = {}
globalvars['output_path'] = os.path.join(abs_path, "Output")
# dataset specific parameters
map_file_path = os.path.join(abs_path, cfg["CNTK"].MAP_FILE_PATH)
globalvars['class_map_file'] = cfg["CNTK"].CLASS_MAP_FILE
globalvars['train_map_file'] = cfg["CNTK"].TRAIN_MAP_FILE
globalvars['test_map_file'] = cfg["CNTK"].TEST_MAP_FILE
globalvars['train_roi_file'] = cfg["CNTK"].TRAIN_ROI_FILE
globalvars['test_roi_file'] = cfg["CNTK"].TEST_ROI_FILE
epoch_size = cfg["CNTK"].NUM_TRAIN_IMAGES
num_test_images = cfg["CNTK"].NUM_TEST_IMAGES
def set_global_vars(use_arg_parser=True):
global globalvars
global image_width
global image_height
global dims_input_const
global img_pad_value
global normalization_const
global map_file_path
global epoch_size
global num_test_images
global model_folder
global base_model_file
global feature_node_name
global last_conv_node_name
global start_train_conv_node_name
global pool_node_name
global last_hidden_node_name
global roi_dim
global prediction
global prediction_in
global prediction_out
if use_arg_parser:
parser = argparse.ArgumentParser()
parser.add_argument('-c',
'--config',
help='Configuration file in YAML format',
required=False,
default=None)
parser.add_argument('-t',
'--device_type',
type=str,
help="The type of the device (cpu|gpu)",
required=False,
default="cpu")
parser.add_argument(
'-d',
'--device',
type=int,
help="Force to run the script on a specified device",
required=False,
default=None)
parser.add_argument('-l',
'--list_devices',
action='store_true',
help="Lists the available devices and exits",
required=False,
default=False)
parser.add_argument('--prediction',
action='store_true',
help="Switches to prediction mode",
required=False,
default=False)
parser.add_argument(
'--prediction_in',
action='append',
type=str,
help=
"The input directory for images in prediction mode. Can be supplied mulitple times.",
required=False,
default=list())
parser.add_argument(
'--prediction_out',
action='append',
type=str,
help=
"The output directory for processed images and predicitons in prediction mode. Can be supplied mulitple times.",
required=False,
default=list())
parser.add_argument(
'--no_headers',
action='store_true',
help="Whether to suppress the header row in the ROI CSV files",
required=False,
default=False)
parser.add_argument(
'--output_width_height',
action='store_true',
help=
"Whether to output width/height instead of second x/y in the ROI CSV files",
required=False,
default=False)
parser.add_argument(
'--suppressed_labels',
type=str,
help=
"Comma-separated list of labels to suppress from being output in ROI CSV files.",
required=False,
default="")
args = vars(parser.parse_args())
# prediction mode?
prediction = args['prediction']
if prediction:
prediction_in = args['prediction_in']
if len(prediction_in) == 0:
raise RuntimeError("No prediction input directory provided!")
for p in prediction_in:
if not os.path.exists(p):
raise RuntimeError(
"Prediction input directory '%s' does not exist" % p)
prediction_out = args['prediction_out']
if len(prediction_out) == 0:
raise RuntimeError("No prediction output directory provided!")
for p in prediction_out:
if not os.path.exists(p):
raise RuntimeError(
"Prediction output directory '%s' does not exist" % p)
if len(prediction_in) != len(prediction_out):
raise RuntimeError(
"Number of input and output directories don't match: %i != %i"
% (len(prediction_in), len(prediction_out)))
for i in range(len(prediction_in)):
if prediction_in[i] == prediction_out[i]:
raise RuntimeError(
"Input and output directories #%i for prediction are the same: %s"
% ((i + 1), prediction_in[i]))
if args['list_devices']:
print("Available devices (Type - ID - description)")
for d in cntk.device.all_devices():
if d.type() == 0:
type = "cpu"
elif d.type() == 1:
type = "gpu"
else:
type = "<unknown:" + str(d.type()) + ">"
print(type + " - " + str(d.id()) + " - " + str(d))
sys.exit(0)
if args['config'] is not None:
cfg_from_file(args['config'])
if args['device'] is not None:
if args['device_type'] == 'gpu':
cntk.device.try_set_default_device(
cntk.device.gpu(args['device']))
else:
cntk.device.try_set_default_device(cntk.device.cpu())
image_width = cfg["CNTK"].IMAGE_WIDTH
image_height = cfg["CNTK"].IMAGE_HEIGHT
# dims_input -- (pad_width, pad_height, scaled_image_width, scaled_image_height, orig_img_width, orig_img_height)
dims_input_const = MinibatchData(
Value(batch=np.asarray([
image_width, image_height, image_width, image_height, image_width,
image_height
],
dtype=np.float32)), 1, 1, False)
# Color used for padding and normalization (Caffe model uses [102.98010, 115.94650, 122.77170])
img_pad_value = [103, 116, 123] if cfg["CNTK"].BASE_MODEL == "VGG16" else [
114, 114, 114
]
normalization_const = Constant([[[103]], [[116]], [[
123
]]]) if cfg["CNTK"].BASE_MODEL == "VGG16" else Constant([[[114]], [[114]],
[[114]]])
# dataset specific parameters
map_file_path = os.path.join(abs_path, cfg["CNTK"].MAP_FILE_PATH)
globalvars['class_map_file'] = cfg["CNTK"].CLASS_MAP_FILE
globalvars['train_map_file'] = cfg["CNTK"].TRAIN_MAP_FILE
globalvars['test_map_file'] = cfg["CNTK"].TEST_MAP_FILE
globalvars['train_roi_file'] = cfg["CNTK"].TRAIN_ROI_FILE
globalvars['test_roi_file'] = cfg["CNTK"].TEST_ROI_FILE
globalvars['output_path'] = cfg["CNTK"].OUTPUT_PATH
epoch_size = cfg["CNTK"].NUM_TRAIN_IMAGES
num_test_images = cfg["CNTK"].NUM_TEST_IMAGES
# model specific parameters
if cfg["CNTK"].PRETRAINED_MODELS.startswith(".."):
model_folder = os.path.join(abs_path, cfg["CNTK"].PRETRAINED_MODELS)
else:
model_folder = cfg["CNTK"].PRETRAINED_MODELS
base_model_file = os.path.join(model_folder, cfg["CNTK"].BASE_MODEL_FILE)
feature_node_name = cfg["CNTK"].FEATURE_NODE_NAME
last_conv_node_name = cfg["CNTK"].LAST_CONV_NODE_NAME
start_train_conv_node_name = cfg["CNTK"].START_TRAIN_CONV_NODE_NAME
pool_node_name = cfg["CNTK"].POOL_NODE_NAME
last_hidden_node_name = cfg["CNTK"].LAST_HIDDEN_NODE_NAME
roi_dim = cfg["CNTK"].ROI_DIM
data_path = map_file_path
# set and overwrite learning parameters
globalvars['rpn_lr_factor'] = cfg["CNTK"].RPN_LR_FACTOR
globalvars['frcn_lr_factor'] = cfg["CNTK"].FRCN_LR_FACTOR
globalvars['e2e_lr_factor'] = cfg["CNTK"].E2E_LR_FACTOR
globalvars['momentum_per_mb'] = cfg["CNTK"].MOMENTUM_PER_MB
globalvars['e2e_epochs'] = 1 if cfg["CNTK"].FAST_MODE else cfg[
"CNTK"].E2E_MAX_EPOCHS
globalvars[
'rpn_epochs'] = 1 if cfg["CNTK"].FAST_MODE else cfg["CNTK"].RPN_EPOCHS
globalvars['frcn_epochs'] = 1 if cfg["CNTK"].FAST_MODE else cfg[
"CNTK"].FRCN_EPOCHS
globalvars['rnd_seed'] = cfg.RNG_SEED
globalvars['train_conv'] = cfg["CNTK"].TRAIN_CONV_LAYERS
globalvars['train_e2e'] = cfg["CNTK"].TRAIN_E2E
if not os.path.isdir(data_path):
raise RuntimeError("Directory %s does not exist" % data_path)
globalvars['class_map_file'] = os.path.join(data_path,
globalvars['class_map_file'])
globalvars['train_map_file'] = os.path.join(data_path,
globalvars['train_map_file'])
globalvars['test_map_file'] = os.path.join(data_path,
globalvars['test_map_file'])
globalvars['train_roi_file'] = os.path.join(data_path,
globalvars['train_roi_file'])
globalvars['test_roi_file'] = os.path.join(data_path,
globalvars['test_roi_file'])
globalvars['headers'] = not args['no_headers']
globalvars['output_width_height'] = args['output_width_height']
suppressed_labels = []
if len(args['suppressed_labels']) > 0:
suppressed_labels = args['suppressed_labels'].split(",")
globalvars['suppressed_labels'] = suppressed_labels
if cfg["CNTK"].FORCE_DETERMINISTIC:
force_deterministic_algorithms()
np.random.seed(seed=globalvars['rnd_seed'])
globalvars['classes'] = parse_class_map_file(globalvars['class_map_file'])
globalvars['num_classes'] = len(globalvars['classes'])
if cfg["CNTK"].DEBUG_OUTPUT:
# report args
print("Using the following parameters:")
print("Flip image : {}".format(cfg["TRAIN"].USE_FLIPPED))
print("Train conv layers: {}".format(globalvars['train_conv']))
print("Random seed : {}".format(globalvars['rnd_seed']))
print("Momentum per MB : {}".format(globalvars['momentum_per_mb']))
if globalvars['train_e2e']:
print("E2E epochs : {}".format(globalvars['e2e_epochs']))
else:
print("RPN lr factor : {}".format(globalvars['rpn_lr_factor']))
print("RPN epochs : {}".format(globalvars['rpn_epochs']))
print("FRCN lr factor : {}".format(globalvars['frcn_lr_factor']))
print("FRCN epochs : {}".format(globalvars['frcn_epochs']))
