def evaluate_model(eval_model, detector_name):
cfg = get_configuration(detector_name)
cfg['NUM_CHANNELS'] = 3
print("Map file = ", cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].CLASSES = parse_class_map_file(
os.path.join("Steer_Bad_Relevant_output", cfg["DATA"].CLASS_MAP_FILE))
cfg["DATA"].NUM_CLASSES = len(cfg["DATA"].CLASSES)
# detect objects in single image
img_path = os.path.join(
os.path.dirname(os.path.abspath(__file__)),
r"Steer_Bad_Relevant_output/testImages/Steer_Bad_Front_Zoom (269).jpg")
regressed_rois, cls_probs = od.evaluate_single_image(
eval_model, img_path, cfg)
bboxes, labels, scores = od.filter_results(regressed_rois, cls_probs, cfg)
fg_boxes = np.where(labels > 0)
print("#bboxes: before nms: {}, after nms: {}, foreground: {}".format(
len(regressed_rois), len(bboxes), len(fg_boxes[0])))
for i in fg_boxes[0]:
print("{:<12} (label: {:<2}), score: {:.3f}, box: {}".format(
cfg["DATA"].CLASSES[labels[i]], labels[i], scores[i],
[int(v) for v in bboxes[i]]))
od.visualize_results(img_path,
bboxes,
labels,
scores,
cfg,
store_to_path="Steer_Bad_Relevant_output/output.jpg")
def prepare_train(cfg, use_arg_parser=True):
cfg.MB_SIZE = 1
cfg.NUM_CHANNELS = 3
cfg.OUTPUT_PATH = "../"
cfg["DATA"].MAP_FILE_PATH = "../"
data_path = cfg["DATA"].MAP_FILE_PATH
if not os.path.isdir(data_path):
raise RuntimeError("Directory %s does not exist" % data_path)
cfg["DATA"].CLASS_MAP_FILE = os.path.join(data_path, cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].TRAIN_MAP_FILE = os.path.join(data_path, cfg["DATA"].TRAIN_MAP_FILE)
#cfg["DATA"].TEST_MAP_FILE = os.path.join(data_path, cfg["DATA"].TEST_MAP_FILE)
cfg["DATA"].TRAIN_ROI_FILE = os.path.join(data_path, cfg["DATA"].TRAIN_ROI_FILE)
#cfg["DATA"].TEST_ROI_FILE = os.path.join(data_path, cfg["DATA"].TEST_ROI_FILE)
cfg['MODEL_PATH'] = os.path.join(cfg.OUTPUT_PATH, "faster_rcnn_eval_{}_{}.model"
.format(cfg["MODEL"].BASE_MODEL, "e2e" if cfg["CNTK"].TRAIN_E2E else "4stage"))
if(cfg["MODEL"].BASE_MODEL=="VGG16"):
cfg['BASE_MODEL_PATH'] = "../VGG16_ImageNet_Caffe.model"
if(cfg["MODEL"].BASE_MODEL=="VGG19"):
cfg['BASE_MODEL_PATH'] = "../VGG19_ImageNet_Caffe.model"
if(cfg["MODEL"].BASE_MODEL=="AlexNet"):
cfg['BASE_MODEL_PATH'] = "../AlexNet_ImageNet_Caffe.model"
cfg["DATA"].CLASSES = parse_class_map_file(cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].NUM_CLASSES = len(cfg["DATA"].CLASSES)
if cfg["CNTK"].FAST_MODE:
cfg["CNTK"].E2E_MAX_EPOCHS = 1
cfg["CNTK"].RPN_EPOCHS = 1
cfg["CNTK"].FRCN_EPOCHS = 1
np.random.seed(seed=cfg.RND_SEED)
def prepare(cfg, use_arg_parser=True):
cfg.MB_SIZE = 1
cfg.NUM_CHANNELS = 3
cfg.OUTPUT_PATH = os.path.join(cfg.DATA.MAP_FILE_PATH, "results", datetime.now().strftime("%d-%m-%Y-%H-%M"))
# cfg["DATA"].MAP_FILE_PATH = os.path.join(abs_path, cfg["DATA"].MAP_FILE_PATH)
running_locally = os.path.exists(cfg["DATA"].MAP_FILE_PATH)
if not running_locally:
# disable debug and plot outputs when running on GPU cluster
cfg["CNTK"].DEBUG_OUTPUT = False
cfg.VISUALIZE_RESULTS = False
if use_arg_parser:
parse_arguments(cfg)
data_path = cfg["DATA"].MAP_FILE_PATH
if not os.path.isdir(data_path):
raise RuntimeError("Directory %s does not exist" % data_path)
cfg["DATA"].CLASS_MAP_FILE = os.path.join(data_path, cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].TRAIN_MAP_FILE = os.path.join(data_path, cfg["DATA"].TRAIN_MAP_FILE)
cfg["DATA"].TEST_MAP_FILE = os.path.join(data_path, cfg["DATA"].TEST_MAP_FILE)
cfg["DATA"].TRAIN_ROI_FILE = os.path.join(data_path, cfg["DATA"].TRAIN_ROI_FILE)
cfg["DATA"].TEST_ROI_FILE = os.path.join(data_path, cfg["DATA"].TEST_ROI_FILE)
cfg['MODEL_PATH'] = os.path.join(cfg.OUTPUT_PATH, "faster_rcnn_eval_{}_{}_{}.model"
.format(cfg["MODEL"].BASE_MODEL, "e2e" if cfg["CNTK"].TRAIN_E2E else "4stage",
cfg.DATA.DATASET))
cfg['BASE_MODEL_PATH'] = os.path.join(cfg['DATA'].MAP_FILE_PATH,
"pretrained-models",
cfg["MODEL"].BASE_MODEL_FILE)
cfg["DATA"].CLASSES = parse_class_map_file(cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].NUM_CLASSES = len(cfg["DATA"].CLASSES)
if cfg["CNTK"].FAST_MODE:
cfg["CNTK"].E2E_MAX_EPOCHS = 1
cfg["CNTK"].RPN_EPOCHS = 1
cfg["CNTK"].FRCN_EPOCHS = 1
if cfg["CNTK"].FORCE_DETERMINISTIC:
force_deterministic_algorithms()
np.random.seed(seed=cfg.RND_SEED)
if False and cfg["CNTK"].DEBUG_OUTPUT:
# report args
print("Using the following parameters:")
print("Flip image : {}".format(cfg["TRAIN"].USE_FLIPPED))
print("Train conv layers: {}".format(cfg.TRAIN_CONV_LAYERS))
print("Random seed : {}".format(cfg.RND_SEED))
print("Momentum per MB : {}".format(cfg["CNTK"].MOMENTUM_PER_MB))
if cfg["CNTK"].TRAIN_E2E:
print("E2E epochs : {}".format(cfg["CNTK"].E2E_MAX_EPOCHS))
else:
print("RPN lr factor : {}".format(cfg["CNTK"].RPN_LR_FACTOR))
print("RPN epochs : {}".format(cfg["CNTK"].RPN_EPOCHS))
print("FRCN lr factor : {}".format(cfg["CNTK"].FRCN_LR_FACTOR))
print("FRCN epochs : {}".format(cfg["CNTK"].FRCN_EPOCHS))
def prepare(cfg, use_arg_parser=True):
cfg.MB_SIZE = 1
cfg.NUM_CHANNELS = 3
cfg.OUTPUT_PATH = os.path.join(abs_path, "Output")
cfg["DATA"].MAP_FILE_PATH = os.path.join(abs_path, cfg["DATA"].MAP_FILE_PATH)
running_locally = os.path.exists(cfg["DATA"].MAP_FILE_PATH)
if running_locally:
os.chdir(cfg["DATA"].MAP_FILE_PATH)
if not os.path.exists(os.path.join(abs_path, "Output")):
os.makedirs(os.path.join(abs_path, "Output"))
if not os.path.exists(os.path.join(abs_path, "Output", cfg["DATA"].DATASET)):
os.makedirs(os.path.join(abs_path, "Output", cfg["DATA"].DATASET))
else:
# disable debug and plot outputs when running on GPU cluster
cfg["CNTK"].DEBUG_OUTPUT = False
cfg.VISUALIZE_RESULTS = False
if use_arg_parser:
parse_arguments(cfg)
data_path = cfg["DATA"].MAP_FILE_PATH
if not os.path.isdir(data_path):
raise RuntimeError("Directory %s does not exist" % data_path)
cfg["DATA"].CLASS_MAP_FILE = os.path.join(data_path, cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].TRAIN_MAP_FILE = os.path.join(data_path, cfg["DATA"].TRAIN_MAP_FILE)
cfg["DATA"].TEST_MAP_FILE = os.path.join(data_path, cfg["DATA"].TEST_MAP_FILE)
cfg["DATA"].TRAIN_ROI_FILE = os.path.join(data_path, cfg["DATA"].TRAIN_ROI_FILE)
cfg["DATA"].TEST_ROI_FILE = os.path.join(data_path, cfg["DATA"].TEST_ROI_FILE)
if cfg.USE_PRECOMPUTED_PROPOSALS:
try:
cfg["DATA"].TRAIN_PRECOMPUTED_PROPOSALS_FILE = os.path.join(data_path,
cfg["DATA"].TRAIN_PRECOMPUTED_PROPOSALS_FILE)
except:
print("To use precomputed proposals please specify the following parameters in your configuration:\n"
"__C.DATA.TRAIN_PRECOMPUTED_PROPOSALS_FILE\n"
"__C.DATA.TEST_PRECOMPUTED_PROPOSALS_FILE")
exit(-1)
cfg['MODEL_PATH'] = os.path.join(cfg.OUTPUT_PATH, "fast_rcnn_eval_{}.model".format(cfg["MODEL"].BASE_MODEL))
cfg['BASE_MODEL_PATH'] = os.path.join(os.path.dirname(os.path.abspath(__file__)), "..", "..", "..", "..",
"PretrainedModels",
cfg["MODEL"].BASE_MODEL_FILE)
cfg["DATA"].CLASSES = parse_class_map_file(cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].NUM_CLASSES = len(cfg["DATA"].CLASSES)
if cfg["CNTK"].FAST_MODE:
cfg["CNTK"].MAX_EPOCHS = 1
if cfg["CNTK"].FORCE_DETERMINISTIC:
force_deterministic_algorithms()
np.random.seed(seed=cfg.RND_SEED)
def prepare(cfg, use_arg_parser=True):
cfg.MB_SIZE = 1
cfg.NUM_CHANNELS = 3
cfg.OUTPUT_PATH = os.path.join(abs_path, "Output")
cfg["DATA"].MAP_FILE_PATH = os.path.join(abs_path, cfg["DATA"].MAP_FILE_PATH)
running_locally = os.path.exists(cfg["DATA"].MAP_FILE_PATH)
if running_locally:
os.chdir(cfg["DATA"].MAP_FILE_PATH)
if not os.path.exists(os.path.join(abs_path, "Output")):
os.makedirs(os.path.join(abs_path, "Output"))
if not os.path.exists(os.path.join(abs_path, "Output", cfg["DATA"].DATASET)):
os.makedirs(os.path.join(abs_path, "Output", cfg["DATA"].DATASET))
else:
# disable debug and plot outputs when running on GPU cluster
cfg["CNTK"].DEBUG_OUTPUT = False
cfg.VISUALIZE_RESULTS = False
if use_arg_parser:
parse_arguments(cfg)
data_path = cfg["DATA"].MAP_FILE_PATH
if not os.path.isdir(data_path):
raise RuntimeError("Directory %s does not exist" % data_path)
cfg["DATA"].CLASS_MAP_FILE = os.path.join(data_path, cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].TRAIN_MAP_FILE = os.path.join(data_path, cfg["DATA"].TRAIN_MAP_FILE)
cfg["DATA"].TEST_MAP_FILE = os.path.join(data_path, cfg["DATA"].TEST_MAP_FILE)
cfg["DATA"].TRAIN_ROI_FILE = os.path.join(data_path, cfg["DATA"].TRAIN_ROI_FILE)
cfg["DATA"].TEST_ROI_FILE = os.path.join(data_path, cfg["DATA"].TEST_ROI_FILE)
if cfg.USE_PRECOMPUTED_PROPOSALS:
try:
cfg["DATA"].TRAIN_PRECOMPUTED_PROPOSALS_FILE = os.path.join(data_path, cfg["DATA"].TRAIN_PRECOMPUTED_PROPOSALS_FILE)
except:
print("To use precomputed proposals please specify the following parameters in your configuration:\n"
"__C.DATA.TRAIN_PRECOMPUTED_PROPOSALS_FILE\n"
"__C.DATA.TEST_PRECOMPUTED_PROPOSALS_FILE")
exit(-1)
cfg['MODEL_PATH'] = os.path.join(cfg.OUTPUT_PATH, "fast_rcnn_eval_{}.model".format(cfg["MODEL"].BASE_MODEL))
cfg['BASE_MODEL_PATH'] = os.path.join(os.path.dirname(os.path.abspath(__file__)), "..", "..", "..", "..", "PretrainedModels",
cfg["MODEL"].BASE_MODEL_FILE)
cfg["DATA"].CLASSES = parse_class_map_file(cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].NUM_CLASSES = len(cfg["DATA"].CLASSES)
if cfg["CNTK"].FAST_MODE:
cfg["CNTK"].MAX_EPOCHS = 1
if cfg["CNTK"].FORCE_DETERMINISTIC:
force_deterministic_algorithms()
np.random.seed(seed=cfg.RND_SEED)
def set_global_vars(use_arg_parser=True):
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
globalvars['fea_map_dim'] = cfg["CNTK"].FEA_MAP_DIM
if use_arg_parser:
parser = argparse.ArgumentParser()
parser.add_argument(
'-datadir',
'--datadir',
help='Data directory where the ImageNet dataset is located',
required=False,
default=data_path)
parser.add_argument('-outputdir',
'--outputdir',
help='Output directory for checkpoints and models',
required=False,
default=None)
parser.add_argument('-logdir',
'--logdir',
help='Log file',
required=False,
default=None)
parser.add_argument('-n',
'--num_epochs',
help='Total number of epochs to train',
type=int,
required=False,
default=cfg["CNTK"].E2E_MAX_EPOCHS)
parser.add_argument('-m',
'--minibatch_size',
help='Minibatch size',
type=int,
required=False,
default=mb_size)
parser.add_argument('-e',
'--epoch_size',
help='Epoch size',
type=int,
required=False,
default=epoch_size)
parser.add_argument(
'-q',
'--quantized_bits',
help='Number of quantized bits used for gradient aggregation',
type=int,
required=False,
default='32')
parser.add_argument(
'-r',
'--restart',
help=
'Indicating whether to restart from scratch (instead of restart from checkpoint file by default)',
action='store_true')
parser.add_argument(
'-device',
'--device',
type=int,
help="Force to run the script on a specified device",
required=False,
default=None)
parser.add_argument('-rpnLrFactor',
'--rpnLrFactor',
type=float,
help="Scale factor for rpn lr schedule",
required=False)
parser.add_argument('-frcnLrFactor',
'--frcnLrFactor',
type=float,
help="Scale factor for frcn lr schedule",
required=False)
parser.add_argument('-e2eLrFactor',
'--e2eLrFactor',
type=float,
help="Scale factor for e2e lr schedule",
required=False)
parser.add_argument('-momentumPerMb',
'--momentumPerMb',
type=float,
help="momentum per minibatch",
required=False)
parser.add_argument('-e2eEpochs',
'--e2eEpochs',
type=int,
help="number of epochs for e2e training",
required=False)
parser.add_argument('-rpnEpochs',
'--rpnEpochs',
type=int,
help="number of epochs for rpn training",
required=False)
parser.add_argument('-frcnEpochs',
'--frcnEpochs',
type=int,
help="number of epochs for frcn training",
required=False)
parser.add_argument('-rndSeed',
'--rndSeed',
type=int,
help="the random seed",
required=False)
parser.add_argument('-trainConv',
'--trainConv',
type=int,
help="whether to train conv layers",
required=False)
parser.add_argument('-trainE2E',
'--trainE2E',
type=int,
help="whether to train e2e (otherwise 4 stage)",
required=False)
args = vars(parser.parse_args())
if args['rpnLrFactor'] is not None:
globalvars['rpn_lr_factor'] = args['rpnLrFactor']
if args['frcnLrFactor'] is not None:
globalvars['frcn_lr_factor'] = args['frcnLrFactor']
if args['e2eLrFactor'] is not None:
globalvars['e2e_lr_factor'] = args['e2eLrFactor']
if args['momentumPerMb'] is not None:
globalvars['momentum_per_mb'] = args['momentumPerMb']
if args['e2eEpochs'] is not None:
globalvars['e2e_epochs'] = args['e2eEpochs']
if args['rpnEpochs'] is not None:
globalvars['rpn_epochs'] = args['rpnEpochs']
if args['frcnEpochs'] is not None:
globalvars['frcn_epochs'] = args['frcnEpochs']
if args['rndSeed'] is not None:
globalvars['rnd_seed'] = args['rndSeed']
if args['trainConv'] is not None:
globalvars[
'train_conv'] = True if args['trainConv'] == 1 else False
if args['trainE2E'] is not None:
globalvars['train_e2e'] = True if args['trainE2E'] == 1 else False
if args['outputdir'] is not None:
globalvars['output_path'] = args['outputdir']
if args['logdir'] is not None:
log_dir = args['logdir']
if args['device'] is not None:
# Setting one worker on GPU and one worker on CPU. Otherwise memory consumption is too high for a single GPU.
if Communicator.rank() == 0:
cntk.device.try_set_default_device(
cntk.device.gpu(args['device']))
else:
cntk.device.try_set_default_device(cntk.device.cpu())
if args['datadir'] is not None:
data_path = args['datadir']
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'])
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']))
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 = {}
map_file_path = cfg["CNTK"].MODEL_DIRECTORY
globalvars['class_map_file'] = os.path.join(map_file_path, cfg["CNTK"].CLASS_MAP_FILE)
globalvars['classes'] = parse_class_map_file(globalvars['class_map_file'])
globalvars['num_classes'] = len(globalvars['classes'])
globalvars['temppath'] = cfg["CNTK"].TEMP_PATH
feature_node_name = cfg["CNTK"].FEATURE_NODE_NAME
model_path = os.path.join(cfg["CNTK"].MODEL_DIRECTORY, cfg["CNTK"].MODEL_NAME)
# helper function
def load_resize_and_pad(image_path, width, height, pad_value=114):
if "@" in image_path:
print("WARNING: zipped image archives are not supported for visualizing results.")
exit(0)
img = cv2.imread(image_path)
img_width = len(img[0])
img_height = len(img)
scale_w = img_width > img_height
def prepare(cfg, use_arg_parser=True):
cfg.MB_SIZE = 1
cfg.NUM_CHANNELS = 3
cfg.OUTPUT_PATH = os.path.join(abs_path, "Output")
data_path = cfg["DATA"].MAP_FILE_PATH
if load_file_from_blob(cfg["AZURE"].ACCOUNT_NAME, \
cfg["AZURE"].DATA, cfg["DATA"].DATASET +".zip", data_path+".zip" ) is True:
unzip_file(data_path + ".zip", data_path)
if not os.path.isdir(data_path):
raise RuntimeError("Directory %s does not exist" % data_path)
running_locally = os.path.exists(cfg["DATA"].MAP_FILE_PATH)
if running_locally:
os.chdir(cfg["DATA"].MAP_FILE_PATH)
if not os.path.exists(os.path.join(abs_path, "Output")):
os.makedirs(os.path.join(abs_path, "Output"))
if not os.path.exists(
os.path.join(abs_path, "Output", cfg["DATA"].DATASET)):
os.makedirs(os.path.join(abs_path, "Output", cfg["DATA"].DATASET))
else:
# disable debug and plot outputs when running on GPU cluster
cfg["CNTK"].DEBUG_OUTPUT = False
cfg.VISUALIZE_RESULTS = False
if use_arg_parser:
parse_arguments(cfg)
cfg["DATA"].CLASS_MAP_FILE = os.path.join(data_path,
cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].TRAIN_MAP_FILE = os.path.join(data_path,
cfg["DATA"].TRAIN_MAP_FILE)
cfg["DATA"].TEST_MAP_FILE = os.path.join(data_path,
cfg["DATA"].TEST_MAP_FILE)
cfg["DATA"].TRAIN_ROI_FILE = os.path.join(data_path,
cfg["DATA"].TRAIN_ROI_FILE)
cfg["DATA"].TEST_ROI_FILE = os.path.join(data_path,
cfg["DATA"].TEST_ROI_FILE)
cfg['OUTPUT_MODEL_NAME'] = "faster_rcnn_eval_{}_{}.model".format(
cfg["MODEL"].BASE_MODEL, "e2e" if cfg["CNTK"].TRAIN_E2E else "4stage")
cfg['MODEL_PATH'] = os.path.join(
os.environ['AZUREML_NATIVE_SHARE_DIRECTORY'], "output",
cfg['OUTPUT_MODEL_NAME'])
cfg['BASE_MODEL_PATH'] = os.path.join(
os.environ['AZUREML_NATIVE_SHARE_DIRECTORY'], "base_model")
cfg["DATA"].CLASSES = parse_class_map_file(cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].NUM_CLASSES = len(cfg["DATA"].CLASSES)
if cfg["CNTK"].FAST_MODE:
cfg["CNTK"].E2E_MAX_EPOCHS = 1
cfg["CNTK"].RPN_EPOCHS = 1
cfg["CNTK"].FRCN_EPOCHS = 1
if cfg["CNTK"].FORCE_DETERMINISTIC:
force_deterministic_algorithms()
np.random.seed(seed=cfg.RND_SEED)
print("Downloading base model {}".format(cfg["MODEL"].BASE_MODEL_FILE))
print("PRETRAINED_MODELS {} ".format(cfg["AZURE"].PRETRAINED_MODELS))
print("BASE_MODEL_FILE {}".format(cfg["MODEL"].BASE_MODEL_FILE))
cfg['BASE_MODEL_PATH'] = cfg['BASE_MODEL_PATH'] + '_' + cfg[
"MODEL"].BASE_MODEL_FILE
print("BASE_MODEL_PATH {}".format(cfg['BASE_MODEL_PATH']))
# For testing to make sure this works when we don't have any stored model in shared directory
# os.remove(cfg['BASE_MODEL_PATH'])
load_file_from_blob(cfg["AZURE"].ACCOUNT_NAME, \
cfg["AZURE"].PRETRAINED_MODELS, cfg["MODEL"].BASE_MODEL_FILE, cfg['BASE_MODEL_PATH'] )
if False and cfg["CNTK"].DEBUG_OUTPUT:
# report args
print("Using the following parameters:")
print("Flip image : {}".format(cfg["TRAIN"].USE_FLIPPED))
print("Train conv layers: {}".format(cfg.TRAIN_CONV_LAYERS))
print("Random seed : {}".format(cfg.RND_SEED))
print("Momentum per MB : {}".format(cfg["CNTK"].MOMENTUM_PER_MB))
if cfg["CNTK"].TRAIN_E2E:
print("E2E epochs : {}".format(cfg["CNTK"].E2E_MAX_EPOCHS))
else:
print("RPN lr factor : {}".format(cfg["CNTK"].RPN_LR_FACTOR))
print("RPN epochs : {}".format(cfg["CNTK"].RPN_EPOCHS))
print("FRCN lr factor : {}".format(cfg["CNTK"].FRCN_LR_FACTOR))
print("FRCN epochs : {}".format(cfg["CNTK"].FRCN_EPOCHS))
def prepare(cfg, use_arg_parser=True):
cfg.MB_SIZE = 1
cfg.NUM_CHANNELS = 3
cfg.OUTPUT_PATH = os.path.join(abs_path, "Output")
cfg["DATA"].MAP_FILE_PATH = os.path.join(abs_path, cfg["DATA"].MAP_FILE_PATH)
running_locally = os.path.exists(cfg["DATA"].MAP_FILE_PATH)
if running_locally:
os.chdir(cfg["DATA"].MAP_FILE_PATH)
if not os.path.exists(os.path.join(abs_path, "Output")):
os.makedirs(os.path.join(abs_path, "Output"))
if not os.path.exists(os.path.join(abs_path, "Output", cfg["DATA"].DATASET)):
os.makedirs(os.path.join(abs_path, "Output", cfg["DATA"].DATASET))
else:
# disable debug and plot outputs when running on GPU cluster
cfg["CNTK"].DEBUG_OUTPUT = False
cfg.VISUALIZE_RESULTS = False
if use_arg_parser:
parse_arguments(cfg)
data_path = cfg["DATA"].MAP_FILE_PATH
if not os.path.isdir(data_path):
raise RuntimeError("Directory %s does not exist" % data_path)
cfg["DATA"].CLASS_MAP_FILE = os.path.join(data_path, cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].TRAIN_MAP_FILE = os.path.join(data_path, cfg["DATA"].TRAIN_MAP_FILE)
cfg["DATA"].TEST_MAP_FILE = os.path.join(data_path, cfg["DATA"].TEST_MAP_FILE)
cfg["DATA"].TRAIN_ROI_FILE = os.path.join(data_path, cfg["DATA"].TRAIN_ROI_FILE)
cfg["DATA"].TEST_ROI_FILE = os.path.join(data_path, cfg["DATA"].TEST_ROI_FILE)
cfg['MODEL_PATH'] = os.path.join(cfg.OUTPUT_PATH, "faster_rcnn_eval_{}_{}.model"
.format(cfg["MODEL"].BASE_MODEL, "e2e" if cfg["CNTK"].TRAIN_E2E else "4stage"))
cfg['BASE_MODEL_PATH'] = os.path.join(os.path.dirname(os.path.abspath(__file__)), "..", "..", "..", "..", "PretrainedModels",
cfg["MODEL"].BASE_MODEL_FILE)
cfg["DATA"].CLASSES = parse_class_map_file(cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].NUM_CLASSES = len(cfg["DATA"].CLASSES)
if cfg["CNTK"].FAST_MODE:
cfg["CNTK"].E2E_MAX_EPOCHS = 1
cfg["CNTK"].RPN_EPOCHS = 1
cfg["CNTK"].FRCN_EPOCHS = 1
if cfg["CNTK"].FORCE_DETERMINISTIC:
force_deterministic_algorithms()
np.random.seed(seed=cfg.RND_SEED)
if False and cfg["CNTK"].DEBUG_OUTPUT:
# report args
print("Using the following parameters:")
print("Flip image : {}".format(cfg["TRAIN"].USE_FLIPPED))
print("Train conv layers: {}".format(cfg.TRAIN_CONV_LAYERS))
print("Random seed : {}".format(cfg.RND_SEED))
print("Momentum per MB : {}".format(cfg["CNTK"].MOMENTUM_PER_MB))
if cfg["CNTK"].TRAIN_E2E:
print("E2E epochs : {}".format(cfg["CNTK"].E2E_MAX_EPOCHS))
else:
print("RPN lr factor : {}".format(cfg["CNTK"].RPN_LR_FACTOR))
print("RPN epochs : {}".format(cfg["CNTK"].RPN_EPOCHS))
print("FRCN lr factor : {}".format(cfg["CNTK"].FRCN_LR_FACTOR))
print("FRCN epochs : {}".format(cfg["CNTK"].FRCN_EPOCHS))
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 = {}
map_file_path = cfg["CNTK"].MODEL_DIRECTORY
globalvars['class_map_file'] = os.path.join(map_file_path,
cfg["CNTK"].CLASS_MAP_FILE)
globalvars['classes'] = parse_class_map_file(globalvars['class_map_file'])
globalvars['num_classes'] = len(globalvars['classes'])
globalvars['temppath'] = cfg["CNTK"].TEMP_PATH
feature_node_name = cfg["CNTK"].FEATURE_NODE_NAME
model_path = os.path.join(cfg["CNTK"].MODEL_DIRECTORY, cfg["CNTK"].MODEL_NAME)
# helper function
def load_resize_and_pad(image_path, width, height, pad_value=114):
if "@" in image_path:
print(
"WARNING: zipped image archives are not supported for visualizing results."
)
exit(0)
img = cv2.imread(image_path)
def set_global_vars(use_arg_parser = True):
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 use_arg_parser:
parser = argparse.ArgumentParser()
parser.add_argument('-datadir', '--datadir', help='Data directory where the ImageNet dataset is located',
required=False, default=data_path)
parser.add_argument('-outputdir', '--outputdir', help='Output directory for checkpoints and models',
required=False, default=None)
parser.add_argument('-logdir', '--logdir', help='Log file',
required=False, default=None)
parser.add_argument('-n', '--num_epochs', help='Total number of epochs to train', type=int,
required=False, default=cfg["CNTK"].E2E_MAX_EPOCHS)
parser.add_argument('-m', '--minibatch_size', help='Minibatch size', type=int,
required=False, default=mb_size)
parser.add_argument('-e', '--epoch_size', help='Epoch size', type=int,
required=False, default=epoch_size)
parser.add_argument('-q', '--quantized_bits', help='Number of quantized bits used for gradient aggregation', type=int,
required=False, default='32')
parser.add_argument('-r', '--restart',
help='Indicating whether to restart from scratch (instead of restart from checkpoint file by default)',
action='store_true')
parser.add_argument('-device', '--device', type=int, help="Force to run the script on a specified device",
required=False, default=None)
parser.add_argument('-rpnLrFactor', '--rpnLrFactor', type=float, help="Scale factor for rpn lr schedule", required=False)
parser.add_argument('-frcnLrFactor', '--frcnLrFactor', type=float, help="Scale factor for frcn lr schedule", required=False)
parser.add_argument('-e2eLrFactor', '--e2eLrFactor', type=float, help="Scale factor for e2e lr schedule", required=False)
parser.add_argument('-momentumPerMb', '--momentumPerMb', type=float, help="momentum per minibatch", required=False)
parser.add_argument('-e2eEpochs', '--e2eEpochs', type=int, help="number of epochs for e2e training", required=False)
parser.add_argument('-rpnEpochs', '--rpnEpochs', type=int, help="number of epochs for rpn training", required=False)
parser.add_argument('-frcnEpochs', '--frcnEpochs', type=int, help="number of epochs for frcn training", required=False)
parser.add_argument('-rndSeed', '--rndSeed', type=int, help="the random seed", required=False)
parser.add_argument('-trainConv', '--trainConv', type=int, help="whether to train conv layers", required=False)
parser.add_argument('-trainE2E', '--trainE2E', type=int, help="whether to train e2e (otherwise 4 stage)", required=False)
args = vars(parser.parse_args())
if args['rpnLrFactor'] is not None:
globalvars['rpn_lr_factor'] = args['rpnLrFactor']
if args['frcnLrFactor'] is not None:
globalvars['frcn_lr_factor'] = args['frcnLrFactor']
if args['e2eLrFactor'] is not None:
globalvars['e2e_lr_factor'] = args['e2eLrFactor']
if args['momentumPerMb'] is not None:
globalvars['momentum_per_mb'] = args['momentumPerMb']
if args['e2eEpochs'] is not None:
globalvars['e2e_epochs'] = args['e2eEpochs']
if args['rpnEpochs'] is not None:
globalvars['rpn_epochs'] = args['rpnEpochs']
if args['frcnEpochs'] is not None:
globalvars['frcn_epochs'] = args['frcnEpochs']
if args['rndSeed'] is not None:
globalvars['rnd_seed'] = args['rndSeed']
if args['trainConv'] is not None:
globalvars['train_conv'] = True if args['trainConv']==1 else False
if args['trainE2E'] is not None:
globalvars['train_e2e'] = True if args['trainE2E']==1 else False
if args['outputdir'] is not None:
globalvars['output_path'] = args['outputdir']
if args['logdir'] is not None:
log_dir = args['logdir']
if args['device'] is not None:
# Setting one worker on GPU and one worker on CPU. Otherwise memory consumption is too high for a single GPU.
if Communicator.rank() == 0:
cntk.device.try_set_default_device(cntk.device.gpu(args['device']))
else:
cntk.device.try_set_default_device(cntk.device.cpu())
if args['datadir'] is not None:
data_path = args['datadir']
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'])
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']))
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']))
