def main():
parser = argparse.ArgumentParser(description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
args.distributed = num_gpus > 1
if args.distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.deprecated.init_process_group(
backend="nccl", init_method="env://"
)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
output_dir = cfg.OUTPUT_DIR
if output_dir:
mkdir(output_dir)
logger = setup_logger("maskrcnn_benchmark", output_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(args)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(cfg))
model = train(cfg, args.local_rank, args.distributed)
if not args.skip_test:
test(cfg, model, args.distributed)
def main(val_path, obj_id):
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Webcam Demo")
parser.add_argument(
"--config-file",
default="../configs/caffe2/keypoints_R_101_FPN.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument(
"--confidence-threshold",
type=float,
default=0.7,
help="Minimum score for the prediction to be shown",
)
parser.add_argument(
"--min-image-size",
type=int,
default=224,
help="Smallest size of the image to feed to the model. "
"Model was trained with 800, which gives best results",
)
parser.add_argument(
"--show-mask-heatmaps",
dest="show_mask_heatmaps",
help="Show a heatmap probability for the top masks-per-dim masks",
action="store_true",
)
parser.add_argument(
"--masks-per-dim",
type=int,
default=2,
help="Number of heatmaps per dimension to show",
)
parser.add_argument(
"opts",
help="Modify model config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
# load config from file and command-line arguments
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
# prepare object that handles inference plus adds predictions on top of image
coco_demo = COCODemo(
cfg,
confidence_threshold=args.confidence_threshold,
show_mask_heatmaps=args.show_mask_heatmaps,
masks_per_dim=args.masks_per_dim,
min_image_size=args.min_image_size,
)
print("testing ...")
# val_path='./../datasets/linemod/ape_train'
# val_list=glob.glob(val_path+'/*.png')
# val_label=os.path.join(val_path,'val.txt')
# metric
val_img_list = glob.glob(val_path + '/test_data/*-color.png')
# K = np.array([[572.4114, 0., 325.2611],
# [0., 573.57043, 242.04899],
# [0., 0., 1.]])
add_v = 0
rep_v = 0
length = 0
# obj = {1: 2,
# 2: 3,
# 3: 4,
# 4: 5,
# 5: 6,
# 6: 7,
# 7: 8,
# 8: 9,
# 9: 10,
# 10: 11,
# 11: 19,
# 12:21,
# 13:24,
# 14:25,
# 16:35,
# 16:36,
# 17:37,
# 18:40,
# 19:51,
# 20:52,
# 21:61}
for imgpath in val_img_list[:]:
# per_dict = {}
img = cv2.imread(imgpath)
imgname = imgpath.split('/')[-1]
# print(imgname)
img = cv2.imread(imgpath)
try:
labels, box, score, kpts = coco_demo.run_on_opencv_image(img)
labels_np = labels.cpu().numpy()
np_kpts = kpts
ind = np.where(labels_np == obj_id)
# print(labels_np )
if len(ind[0]) == 0:
continue
# print(imgname)
# print(len(ind[0]))
# print(imgname)
obj_kpts = np_kpts[ind[0][0]] # [8,3]
add, rep = error_cp(val_path, obj_id, imgname, obj_kpts)
except:
continue
length += 1
# print(length)
if add:
add_v += 1
if rep:
rep_v += 1
print("ADD metric:{}".format(add_v / length))
print("REP metric:{}".format(rep_v / length))
return add_v / length, rep_v / length
import os
import cv2
import numpy as np
from maskrcnn_benchmark.config import cfg
from demo.predictor import ICDARDemo, RRPNDemo
from maskrcnn_benchmark.utils.visualize import vis_image, write_result_ICDAR_RRPN2polys, zip_dir
from PIL import Image
import time
config_file = "./configs/rrpn/e2e_rrpn_R_50_C4_1x_ICDAR13_15_17_trial_again_test.yaml"
# update the config options with the config file
cfg.merge_from_file(config_file)
# manual override some options
cfg.merge_from_list(["MODEL.DEVICE", "cuda"])
# cfg.freeze()
# cfg.MODEL.WEIGHT = 'models/IC-13-15-17-Trial/model_0155000.pth'
result_dir = os.path.join('results',
config_file.split('/')[-1].split('.')[0],
cfg.MODEL.WEIGHT.split('/')[-1].split('.')[0])
if not os.path.isdir(result_dir):
os.makedirs(result_dir)
coco_demo = RRPNDemo(
cfg,
min_image_size=1000,
confidence_threshold=0.85,
)
def main():
# apply_prior prior_mask
# 0 - -
# 1 Y -
# 2 - Y
# 3 Y Y
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--ckpt",
help=
"The path to the checkpoint for test, default is the latest checkpoint.",
default=None,
)
parser.add_argument(
"--dataset_name",
help="vcoco_test or vcoco_val_test",
default=None,
)
parser.add_argument('--num_iteration',
dest='num_iteration',
help='Specify which weight to load',
default=-1,
type=int)
parser.add_argument('--object_thres',
dest='object_thres',
help='Object threshold',
default=0.1,
type=float) # used to be 0.4 or 0.05
parser.add_argument('--human_thres',
dest='human_thres',
help='Human threshold',
default=0.8,
type=float)
parser.add_argument('--prior_flag',
dest='prior_flag',
help='whether use prior_flag',
default=1,
type=int)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
distributed = num_gpus > 1 and torch.cuda.is_available()
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
print('prior flag: {}'.format(args.prior_flag))
ROOT_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
# DATA_DIR = os.path.abspath(os.path.join(ROOT_DIR, 'Data'))
args.config_file = os.path.join(ROOT_DIR, args.config_file)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("DRG", save_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(cfg)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
model = build_detection_model(cfg)
# model.to(cfg.MODEL.DEVICE)
device = torch.device(
"cuda") if torch.cuda.is_available() else torch.device("cpu")
model.to(device)
# Initialize mixed-precision if necessary
use_mixed_precision = cfg.DTYPE == 'float16'
amp_handle = amp.init(enabled=use_mixed_precision, verbose=cfg.AMP_VERBOSE)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
if args.num_iteration != -1:
args.ckpt = os.path.join(cfg.OUTPUT_DIR,
'model_%07d.pth' % args.num_iteration)
ckpt = cfg.MODEL.WEIGHT if args.ckpt is None else args.ckpt
logger.info("Testing checkpoint {}".format(ckpt))
_ = checkpointer.load(ckpt, use_latest=args.ckpt is None)
# iou_types = ("bbox",)
output_folders = [None] * len(cfg.DATASETS.TEST)
# dataset_names = cfg.DATASETS.TEST
dataset_names = (args.dataset_name, )
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
if args.num_iteration != -1:
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference_sp",
dataset_name,
"model_%07d" % args.num_iteration)
else:
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference_sp",
dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
opt = {}
# opt['word_dim'] = 300
for output_folder, dataset_name in zip(output_folders, dataset_names):
data = DatasetCatalog.get(dataset_name)
data_args = data["args"]
im_dir = data_args['im_dir']
test_detection = pickle.load(open(data_args['test_detection_file'],
"rb"),
encoding='latin1')
prior_mask = pickle.load(open(data_args['prior_mask'], "rb"),
encoding='latin1')
action_dic = json.load(open(data_args['action_index']))
action_dic_inv = {y: x for x, y in action_dic.items()}
vcoco_test_ids = open(data_args['vcoco_test_ids_file'], 'r')
test_image_id_list = [int(line.rstrip()) for line in vcoco_test_ids]
vcocoeval = VCOCOeval(data_args['vcoco_test_file'],
data_args['ann_file'],
data_args['vcoco_test_ids_file'])
word_embeddings = pickle.load(open(data_args['word_embedding_file'],
"rb"),
encoding='latin1')
output_file = os.path.join(output_folder, 'detection.pkl')
output_dict_file = os.path.join(
output_folder, 'detection_human_{}_new.pkl'.format(dataset_name))
logger.info("Output will be saved in {}".format(output_file))
logger.info("Start evaluation on {} dataset({} images).".format(
dataset_name, len(test_image_id_list)))
run_test(model,
dataset_name=dataset_name,
im_dir=im_dir,
test_detection=test_detection,
word_embeddings=word_embeddings,
test_image_id_list=test_image_id_list,
prior_mask=prior_mask,
action_dic_inv=action_dic_inv,
output_file=output_file,
output_dict_file=output_dict_file,
object_thres=args.object_thres,
human_thres=args.human_thres,
prior_flag=args.prior_flag,
device=device,
cfg=cfg)
synchronize()
vcocoeval._do_eval(output_file, ovr_thresh=0.5)
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default=
"/private/home/fmassa/github/detectron.pytorch_v2/configs/e2e_faster_rcnn_R_50_C4_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--ckpt",
help=
"The path to the checkpoint for test, default is the latest checkpoint.",
default=None,
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
distributed = num_gpus > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = cfg.OUTPUT_DIR # ""
filename = f'test_log_{pathlib.PurePath(args.ckpt) if args.ckpt is not None else "last"}.txt'
test_result_filename = os.path.join(
save_dir,
pathlib.PurePath(filename).stem + '.pickle')
logger = setup_logger("maskrcnn_benchmark",
save_dir,
get_rank(),
filename=filename)
logger.info("Using {} GPUs".format(num_gpus))
logger.info(cfg)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
model = build_detection_model(cfg)
model.to(cfg.MODEL.DEVICE)
# Initialize mixed-precision if necessary
use_mixed_precision = cfg.DTYPE == 'float16'
amp_handle = amp.init(enabled=use_mixed_precision, verbose=cfg.AMP_VERBOSE)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
ckpt = cfg.MODEL.WEIGHT if args.ckpt is None else os.path.join(
save_dir, args.ckpt)
_ = checkpointer.load(ckpt, use_latest=args.ckpt is None)
iou_types = ()
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm", )
if cfg.MODEL.KEYPOINT_ON:
iou_types = iou_types + ("keypoints", )
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference",
dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
data_loaders_val = make_data_loader(cfg,
is_train=False,
is_distributed=distributed)
for output_folder, dataset_name, data_loader_val in zip(
output_folders, dataset_names, data_loaders_val):
inference(
model,
data_loader_val,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=False if cfg.MODEL.RETINANET_ON else cfg.MODEL.RPN_ONLY,
bbox_aug=cfg.TEST.BBOX_AUG.ENABLED,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
test_result_filename=test_result_filename,
)
synchronize()
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
'--test_path',
default=None,
help='test model path or a single model weight file, if it is a path, will test all models inside the path'
)
parser.add_argument(
"--config-file",
default="/private/home/fmassa/github/detectron.pytorch_v2/configs/e2e_faster_rcnn_R_50_C4_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
parser.add_argument("--gpuid", default='0', help='set gpu id')
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
distributed = num_gpus > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(
backend="nccl", init_method="env://"
)
else:
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpuid
#pdb.set_trace()
if args.test_path is not None:
_cfg = _find_yaml_in_dir(args.test_path, os.path.isdir(args.test_path))
model_list = _get_models_in_dir(args.test_path)
save_dir = args.test_path if os.path.isdir(
args.test_path) else '/'.join((args.test_path).split('/')[:-1])
else:
_cfg = args.config_file
model_list = [cfg.MODEL.WEIGHT]
save_dir = ""
#pdb.set_trace()
cfg.merge_from_file(_cfg)
cfg.merge_from_list(args.opts)
cfg.freeze()
logger = setup_logger("maskrcnn_benchmark", save_dir, get_rank(), test=True)
logger.info("Using {} GPUs".format(num_gpus))
logger.info(cfg)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
collect_evaluate_results = {}
for model_path in model_list:
results = test_once(cfg, save_dir, model_path, distributed)
# pdb.set_trace()
if cfg.DATASETS.MODE_IN_TEST =='test' and \
'isbi' in args.config_file:
sio.savemat(os.path.join(save_dir,
'isbi2015_%s.mat'%model_path.split(
'/')[-1].strip('.pth') ),
results[0])
continue
else:
collect_evaluate_results[model_path] = results[0].results['segm']
if cfg.DATASETS.MODE_IN_TEST == 'test' and 'isbi' in args.config_file:
return 0
# pdb.set_trace()
# pdb.set_trace()
# todo: prepare print
x_list = []
AJI = []
MAP = []
AP50 = []
AP75 = []
AP85 = []
best_student ={}
best_teacher = {}
for k,v in collect_evaluate_results.items():
if 't_model' not in k:
name = k.split('/')[-1].strip('.pth').strip('model_')
if 'fina' in name:
continue
name = int(name)
x_list.append(name)
aji = (v['AJI']['nuclei'] + v['AJI']['cytoplasm'])/2
map = v['mAP']['all']
ap50 = v['AP50']['all']
ap75 = v['AP75']['all']
ap85 = v['AP85']['all']
AJI.append(aji)
MAP.append(map)
AP50.append(ap50)
AP75.append(ap75)
AP85.append(ap85)
plt.plot(x_list, AJI,color='green',label='AJI')
plt.plot(x_list,MAP,color='red',label='mAP')
plt.plot(x_list,AP50,color = 'skyblue',label='AP50')
plt.plot(x_list,AP75,color='blue',label='AP75')
plt.plot(x_list, AP85, color='black', label='AP85')
# show number
anno_xs = []
anno_map = []
anno_aji = []
# pdb.set_trace()
idxmap = MAP.index(max(MAP))
idxaji = AJI.index(max(AJI))
anno_xs.append(x_list[idxmap])
anno_map.append(MAP[idxmap])
anno_aji.append(AJI[idxmap])
anno_xs.append(x_list[idxaji])
anno_map.append(MAP[idxaji])
anno_aji.append(AJI[idxaji])
best_student['map_best'] = {x_list[idxmap]: {'map':MAP[idxmap], 'aji':AJI[idxmap]}}
best_student['aji_best'] = {x_list[idxaji ]: {'map':MAP[idxaji ], 'aji':AJI[idxaji ]}}
for a, b in zip(anno_xs, anno_aji):
plt.annotate('(%.0f,%.4f)'%(a,b), (a,b))
for a, b in zip(anno_xs, anno_map):
plt.annotate('(%.0f,%.4f)'%(a,b), (a,b))
# for teacher
x_list = []
AJI = []
MAP = []
AP50 = []
AP75 = []
AP85 = []
for k, v in collect_evaluate_results.items():
if 't_model' in k:
name = k.split('/')[-1].strip('.pth').strip('model_')
if 'fina' in name:
continue
name = int(name)
x_list.append(name)
aji = (v['AJI']['nuclei'] + v['AJI']['cytoplasm']) / 2
map = v['mAP']['all']
ap50 = v['AP50']['all']
ap75 = v['AP75']['all']
ap85 = v['AP85']['all']
AJI.append(aji)
MAP.append(map)
AP50.append(ap50)
AP75.append(ap75)
AP85.append(ap85)
if len(AJI)>0:
plt.plot(x_list, AJI, '--', color='green', label='AJI')
plt.plot(x_list, MAP,'--', color='red', label='mAP')
plt.plot(x_list, AP50,'--', color='skyblue', label='AP50')
plt.plot(x_list, AP75,'--', color='blue', label='AP75')
plt.plot(x_list, AP85, '--',color='black', label='AP85')
# show number
anno_xs = []
anno_map = []
anno_aji = []
# pdb.set_trace()
idxmap = MAP.index(max(MAP))
idxaji = AJI.index(max(AJI))
anno_xs.append(x_list[idxmap])
anno_map.append(MAP[idxmap])
anno_aji.append(AJI[idxmap])
anno_xs.append(x_list[idxaji])
anno_map.append(MAP[idxaji])
anno_aji.append(AJI[idxaji])
best_teacher['map_best'] = {x_list[idxmap]: {'map': MAP[idxmap], 'aji': AJI[idxmap]}}
best_teacher['aji_best'] = {x_list[idxaji]: {'map': MAP[idxaji], 'aji': AJI[idxaji]}}
for a, b in zip(anno_xs, anno_aji):
plt.annotate('(%.0f,%.4f)' % (a, b), (a, b))
for a, b in zip(anno_xs, anno_map):
plt.annotate('(%.0f,%.4f)' % (a, b), (a, b))
plt.legend()
plt.savefig(os.path.join(save_dir,"result.jpg"))
with open(os.path.join(save_dir, 'result.json'), 'w') as f:
json.dump(collect_evaluate_results, f)
# write best result
with open(os.path.join(save_dir, 'best_result.json'), 'w') as f:
json.dump({'student':best_student, 'teacher':best_teacher},f)
plt.imshow(img[:, :, [2, 1, 0]])
plt.axis("off")
plt.title('Prediction of {name}'.format(name=img_name),
fontsize='xx-large')
plt.show()
if __name__ == '__main__':
start = time.time()
config_path = '/home/xia/maskrcnn-benchmark/configs/e2e_mask_rcnn_R_101_FPN_1x_predictor.yaml'
img_path = '/home/xia/bobbins/data/test/rgb/'
pylab.rcParams['figure.figsize'] = (12.0, 9.0)
# update the config options with the config file
cfg.merge_from_file(config_path)
# manual override some options
cfg.merge_from_list(["MODEL.DEVICE", "cpu"])
bobbin_demo = BobbinsDemo(
cfg,
min_image_size=720,
confidence_threshold=0.95,
)
# load image
#imgId = np.random.randint(0,200)
#imgId = 400 + imgId
imgId = np.random.randint(0, 20)
img_name = 'rgb_' + '{:0>4d}'.format(imgId) + '.png'
img_file = img_path + img_name
image = load(img_file)
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default=
"/workspace/object_detection/configs/e2e_mask_rcnn_R_50_FPN_1x.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--skip-eval",
dest="skip_eval",
help="Do not eval the predictions",
action="store_true",
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
distributed = num_gpus > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", save_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(cfg)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
model = build_detection_model(cfg)
model.to(cfg.MODEL.DEVICE)
# Initialize mixed-precision if necessary
use_mixed_precision = cfg.DTYPE == 'float16'
amp_handle = amp.init(enabled=use_mixed_precision, verbose=cfg.AMP_VERBOSE)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
iou_types = ("bbox", )
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm", )
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference",
dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
data_loaders_val = make_data_loader(cfg,
is_train=False,
is_distributed=distributed)
for output_folder, dataset_name, data_loader_val in zip(
output_folders, dataset_names, data_loaders_val):
inference(
model,
data_loader_val,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
skip_eval=args.skip_eval,
)
synchronize()
def main():
# Build a parser for arguments
parser = argparse.ArgumentParser(description="Action Prediction Training")
parser.add_argument(
"--config-file",
default=
"/home/SelfDriving/maskrcnn/maskrcnn-benchmark/configs/e2e_faster_rcnn_R_50_C4_1x.yaml",
metavar="FILE",
help="path to maskrcnn_benchmark config file",
type=str,
) # Just in order to get outdir
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
parser.add_argument(
"--imageroot",
type=str,
help="Directory to the images",
default=
"/home/SelfDriving/maskrcnn/maskrcnn-benchmark/datasets/bdd100k/features/val"
)
parser.add_argument(
"--gtroot",
type=str,
help="Directory to the groundtruth",
default=
"/home/SelfDriving/maskrcnn/maskrcnn-benchmark/datasets/bdd100k/annotations/val_gt_action.json"
)
parser.add_argument(
"--model_root",
type=str,
help="Directory to the trained model",
default="/data6/SRIP19_SelfDriving/Outputs/trained/netFinal_200.pth")
parser.add_argument("--imWidth",
type=int,
help="Crop to width",
default=1280)
parser.add_argument("--imHeight",
type=int,
help="Crop to height",
default=720)
parser.add_argument("--batch_size", type=int, help="Batch Size", default=1)
parser.add_argument("--experiment",
type=str,
help="Give this experiment a name",
default=str(datetime.datetime.now()))
args = parser.parse_args()
print(args)
# cfg.OUTPUT_DIR = "/data6/SRIP_SelfDriving/Outputs/"
# cfg.MODEL.WEIGHT = "/data6/SRIP_SelfDriving/Outputs/model_final.pth"
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
print(cfg)
cfg.freeze()
if torch.cuda.is_available():
print("CUDA device is available.")
test(cfg, args)
"/mrcnn_integrate/train_tools/pretrained_models/e2e_mask_rcnn_R-50-FPN_1x_no_last.pth",
help="path to save the converted model",
type=str,
)
parser.add_argument(
"--cfg",
default=
"/mrcnn_integrate/config/e2e_mask_rcnn_R_50_FPN_1x_caffe2_stick.yaml",
help="path to config file",
type=str,
)
args = parser.parse_args()
#
DETECTRON_PATH = os.path.expanduser(args.pretrained_path)
print('detectron path: {}'.format(DETECTRON_PATH))
cfg.merge_from_file(args.cfg)
_d = load_c2_format(cfg, DETECTRON_PATH)
newdict = _d
newdict['model'] = removekey(_d['model'], [
'cls_score.bias', 'cls_score.weight', 'bbox_pred.bias', 'bbox_pred.weight',
'mask_fcn_logits.weight', 'mask_fcn_logits.bias'
])
torch.save(newdict, args.save_path)
print('saved to {}.'.format(args.save_path))
if __name__ == '__main__':
pass
def main():
# Build a parser for arguments
parser = argparse.ArgumentParser(description="Action Prediction Training")
parser.add_argument(
"--config-file",
default=
"/home/SelfDriving/maskrcnn/maskrcnn-benchmark/configs/baseline.yaml",
metavar="FILE",
help="path to maskrcnn_benchmark config file",
type=str,
)
parser.add_argument(
"--weight_decay",
default=1e-4,
help="Weight decay",
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
parser.add_argument("--initLR",
help="Initial learning rate",
default=0.0001)
parser.add_argument(
"--freeze",
default=False,
help="If freeze faster rcnn",
)
parser.add_argument("--imageroot",
type=str,
help="Directory to the images",
default="/data6/SRIP19_SelfDriving/bdd12k/data1/")
parser.add_argument(
"--gtroot",
type=str,
help="Directory to the groundtruth",
default=
"/data6/SRIP19_SelfDriving/bdd12k/annotations/12k_gt_train_5_actions.json"
)
parser.add_argument(
"--reasonroot",
type=str,
help="Directory to the explanations",
default=
"/data6/SRIP19_SelfDriving/bdd12k/annotations/train_reason_img.json")
parser.add_argument("--imWidth",
type=int,
help="Crop to width",
default=1280)
parser.add_argument("--imHeight",
type=int,
help="Crop to height",
default=720)
parser.add_argument("--batch_size", type=int, help="Batch Size", default=1)
parser.add_argument("--experiment",
type=str,
help="Give this experiment a name",
default=str(datetime.datetime.now()))
parser.add_argument(
"--model_root",
type=str,
help="Directory to the trained model",
default=
"/data6/SRIP19_SelfDriving/bdd100k/trained_model/Outputs/model_final_apt.pth"
)
parser.add_argument("--val",
action='store_true',
default=False,
help='Validation or not')
parser.add_argument("--num_epoch",
default=20,
help="The number of epoch for training",
type=int)
parser.add_argument("--from_checkpoint",
default=False,
help="If we need load weights from checkpoint.")
parser.add_argument(
"--checkpoint",
default=".",
help="The path to the checkpoint weights.",
type=str,
)
args = parser.parse_args()
print(args)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
if torch.cuda.is_available():
print("CUDA device is available.")
# output directory
outdir = cfg.OUTPUT_DIR
print("Save path:", outdir)
if outdir:
mkdir(outdir)
# logger = setup_logger("training", outdir)
train(cfg, args)
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument(
'--reduce-batch',
type=int,
help=('Divide IMS_PER_BATCH by this amount. This appropriately '
'updates the learning rate, number of iterations, and so on.'))
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument(
"--use-tensorboard",
dest="use_tensorboard",
help="Use tensorboardX logger (Requires tensorboardX installed)",
action="store_true",
default=False)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
# Generate a unique experiment ID for this run.
# Note: uuid generation relies on os.urandom, so it is not affected by,
# e.g., random.seed.
experiment_id = uuid.uuid4()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
args.distributed = num_gpus > 1
if args.distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
cfg.merge_from_file(args.config_file)
# We want to get the OUTPUT_DIR from the args immediately, if it exists, so
# we can setup logging. We will merge the rest of the config in a few
# lines.
merge_keys(cfg, args.opts, ['OUTPUT_DIR'])
output_dir = cfg.OUTPUT_DIR
if output_dir:
mkdir(output_dir)
if get_rank() == 0:
file_logger = common_setup(__file__, output_dir, args)
else:
file_logger = common_setup(__file__ + '-worker%s' % get_rank(),
output_dir,
args,
log_console_level=logging.CRITICAL,
save_git_state=False)
# Automatically handle config changes as required by
# https://github.com/facebookresearch/maskrcnn-benchmark/tree/327bc29bcc4924e35bd61c59877d5a1d25bb75af#single-gpu-training
if args.reduce_batch:
# Update using --opts first, then override.
merge_keys(cfg, args.opts, [
'SOLVER.IMS_PER_BATCH', 'SOLVER.BASE_LR', 'SOLVER.MAX_ITER',
'SOLVER.STEPS', 'SOLVER.CHECKPOINT_PERIOD'
])
assert num_gpus in (1, 2, 4)
scale = args.reduce_batch
logging.info('Updating config for # GPUs = %s', num_gpus)
def update_config(key, new_value):
key_list = key.split('.')
d = cfg
for subkey in key_list[:-1]:
d = cfg[subkey]
subkey = key_list[-1]
old_value = d[subkey]
logging.info('Updating cfg.%s: %s -> %s', key, old_value,
new_value)
d[subkey] = new_value
update_config('SOLVER.IMS_PER_BATCH',
_safe_int(cfg.SOLVER.IMS_PER_BATCH / scale))
update_config('SOLVER.BASE_LR', cfg.SOLVER.BASE_LR / scale)
update_config('SOLVER.MAX_ITER',
_safe_int(cfg.SOLVER.MAX_ITER * scale))
update_config('SOLVER.CHECKPOINT_PERIOD',
_safe_int(cfg.SOLVER.CHECKPOINT_PERIOD * scale))
update_config('SOLVER.STEPS',
tuple(_safe_int(x * scale) for x in cfg.SOLVER.STEPS))
logging.info('Updating config from arguments')
cfg.merge_from_list(args.opts)
cfg.freeze()
logger = logging.getLogger("maskrcnn_benchmark")
logger.info("Using {} GPUs".format(num_gpus))
logger.info(args)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
file_logger.info(config_str)
file_logger.info("Running with config:\n{}".format(cfg))
if get_rank() == 0:
config_output = add_time_to_path(Path(output_dir) / 'config.yaml')
with open(config_output, 'w') as f:
f.write(cfg.dump())
logging.info('Experiment id: %s', experiment_id)
with open(os.path.join(output_dir, 'experiment_id.txt'), 'w') as f:
f.write('%s\n' % experiment_id)
output_config_path = os.path.join(cfg.OUTPUT_DIR, 'config.yml')
logger.info("Saving config into: {}".format(output_config_path))
# save overloaded model config in the output directory
save_config(cfg, output_config_path)
model = train(cfg,
args.local_rank,
args.distributed,
use_tensorboard=args.use_tensorboard)
if not args.skip_test:
run_test(cfg, model, args.distributed)
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Webcam Demo")
parser.add_argument(
"--config-file",
default="../configs/caffe2/e2e_mask_rcnn_R_50_FPN_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument(
"--predictions-out",
default="./test.json",
metavar="FILE",
help="path to file to output labels",
)
parser.add_argument(
"--test-image-dir",
default="/n/pana/scratch/ravi/bdd/bdd100k/images/100k/val/",
metavar="FILE",
help="path to test image directory",
)
parser.add_argument(
"--confidence-threshold",
type=float,
default=0.5,
help="Minimum score for the prediction to be shown",
)
parser.add_argument(
"--min-image-size",
type=int,
default=800,
help="Smallest size of the image to feed to the model. "
"Model was trained with 800, which gives best results",
)
parser.add_argument(
"--show-mask-heatmaps",
dest="show_mask_heatmaps",
help="Show a heatmap probability for the top masks-per-dim masks",
action="store_true",
)
parser.add_argument(
"--masks-per-dim",
type=int,
default=2,
help="Number of heatmaps per dimension to show",
)
parser.add_argument(
"opts",
help="Modify model config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
# load config from file and command-line arguments
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
# prepare object that handles inference plus adds predictions on top of image
coco_demo = COCODemo(
cfg,
confidence_threshold=args.confidence_threshold,
show_mask_heatmaps=args.show_mask_heatmaps,
masks_per_dim=args.masks_per_dim,
min_image_size=args.min_image_size,
)
image_paths = glob.glob(os.path.join(args.test_image_dir, '*.jpg'))
pred_list = []
coco_cat_to_bdd_cat = {
"person": "person",
"car": "car",
"traffic light": "traffic light",
"stop sign": "traffic sign",
"bus": "bus",
"truck": "truck",
"bicycle": "bike",
"motorcycle": "motor",
"train": "train"
}
for i in tqdm(image_paths):
img = cv2.imread(i)
image_id = i.split('/')[-1].split('.')[0]
start = time.time()
predictions = coco_demo.compute_prediction(img)
end = time.time()
scores = predictions.get_field('scores')
#high_conf_idx = scores > args.confidence_threshold
#predictions = predictions[high_conf_idx]
#scores = predictions.get_field('scores')
boxes = predictions.bbox
labels = predictions.get_field('labels')
labels = [coco_demo.CATEGORIES[l] for l in labels]
for b in range(len(labels)):
if labels[b] in coco_cat_to_bdd_cat:
label = coco_cat_to_bdd_cat[labels[b]]
obj_dict = {
'name':
image_id,
'bbox': [
float(boxes[b][0]),
float(boxes[b][1]),
float(boxes[b][2]),
float(boxes[b][3])
],
'category':
label,
'score':
float(scores[b])
}
pred_list.append(obj_dict)
with open(args.predictions_out, 'w') as fp:
json.dump(pred_list, fp)
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Webcam Demo")
parser.add_argument(
"--config-file",
default="../configs/caffe2/e2e_mask_rcnn_R_50_FPN_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument(
"--confidence-threshold",
type=float,
default=0.7,
help="Minimum score for the prediction to be shown",
)
parser.add_argument(
"--min-image-size",
type=int,
default=224,
help="Smallest size of the image to feed to the model. "
"Model was trained with 800, which gives best results",
)
parser.add_argument(
"--show-mask-heatmaps",
dest="show_mask_heatmaps",
help="Show a heatmap probability for the top masks-per-dim masks",
action="store_true",
)
parser.add_argument("--masks-per-dim",
type=int,
default=2,
help="Number of heatmaps per dimension to show")
parser.add_argument(
"opts",
help="Modify model config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
# load config from file and command-line arguments
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
# prepare object that handles inference plus adds predictions on top of image
coco_demo = COCODemo(
cfg,
confidence_threshold=args.confidence_threshold,
show_mask_heatmaps=args.show_mask_heatmaps,
masks_per_dim=args.masks_per_dim,
min_image_size=args.min_image_size,
)
video_file_id = "friends-unagi-640x480.mp4"
print("Read: ", video_file_id)
cam = cv2.VideoCapture(video_file_id)
# We need to check if camera
# is opened previously or not
if (cam.isOpened() == False):
print("Error reading video file")
while (cam.isOpened()):
start_time = time.time()
ret_val, img = cam.read()
composite = coco_demo.run_on_opencv_image(img)
print("Time: {:.2f} s / img".format(time.time() - start_time))
cv2.imshow("COCO detections", composite)
if cv2.waitKey(1) == 27:
break # esc to quit
cv2.destroyAllWindows()
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank",
type=int,
default=os.getenv('LOCAL_RANK', 0))
parser.add_argument("--max_steps",
type=int,
default=0,
help="Override number of training steps in the config")
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument("--fp16",
help="Mixed precision training",
action="store_true")
parser.add_argument("--amp",
help="Mixed precision training",
action="store_true")
parser.add_argument('--skip_checkpoint',
default=False,
action='store_true',
help="Whether to save checkpoints")
parser.add_argument(
"--json-summary",
help="Out file for DLLogger",
default="dllogger.out",
type=str,
)
parser.add_argument("--debug",
type=distutils.util.strtobool,
default=False,
help="debug")
parser.add_argument("--eval-loss",
action="store_true",
default=False,
help="evaluate loss(very buggy)")
parser.add_argument("--print-freq",
type=int,
default=100,
help="print freq for tensorboard")
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
args.fp16 = args.fp16 or args.amp
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
args.distributed = num_gpus > 1
if args.distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
if args.debug:
cfg.DEBUG = args.debug
# Redundant option - Override config parameter with command line input
if args.max_steps > 0:
cfg.SOLVER.MAX_ITER = args.max_steps
if args.skip_checkpoint:
cfg.SAVE_CHECKPOINT = False
cfg.freeze()
output_dir = cfg.OUTPUT_DIR
if output_dir:
mkdir(output_dir)
args.log_dir = save_path_formatter(args, cfg)
logger = setup_logger("maskrcnn_benchmark", output_dir, get_rank())
if is_main_process():
dllogger.init(backends=[
dllogger.JSONStreamBackend(verbosity=dllogger.Verbosity.VERBOSE,
filename=args.json_summary),
dllogger.StdOutBackend(verbosity=dllogger.Verbosity.VERBOSE,
step_format=format_step)
])
else:
dllogger.init(backends=[])
dllogger.log(step="PARAMETER", data={"gpu_count": num_gpus})
# dllogger.log(step="PARAMETER", data={"environment_info": collect_env_info()})
dllogger.log(step="PARAMETER", data={"config_file": args.config_file})
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
dllogger.log(step="PARAMETER", data={"config": cfg})
if is_main_process():
args.writer = SummaryWriter(args.log_dir, flush_secs=30)
if args.fp16:
fp16 = True
else:
fp16 = False
model, iters_per_epoch = train(cfg, args.local_rank, args.distributed,
fp16, dllogger, args)
if not args.skip_test:
#if not cfg.PER_EPOCH_EVAL:
test_model(cfg, model, args.distributed, iters_per_epoch, dllogger,
args)
def image_mask(image):
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Video")
parser.add_argument(
"--config-file",
default=
"lib/maskrcnn-benchmark/configs/caffe2/e2e_mask_rcnn_R_50_FPN_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument(
"--confidence-threshold",
type=float,
default=0.7,
help="Minimum score for the prediction to be shown",
)
parser.add_argument(
"--min-image-size",
type=int,
default=224,
help="Smallest size of the image to feed to the model. "
"Model was trained with 800, which gives best results",
)
parser.add_argument(
"--show-mask-heatmaps",
dest="show_mask_heatmaps",
help="Show a heatmap probability for the top masks-per-dim masks",
action="store_true",
)
parser.add_argument(
"--masks-per-dim",
type=int,
default=2,
help="Number of heatmaps per dimension to show",
)
parser.add_argument(
"opts",
help="Modify model config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
parser.add_argument(
"--show-mask-binary",
dest="show_mask_binary",
help="show a binary mask image for the top masks-per-dim masks",
action="store_true",
)
args = parser.parse_args()
# load config from file and command-line arguments
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
# prepare object that handles inference plus adds predictions on top of image
coco_demo = COCODemo(cfg,
confidence_threshold=args.confidence_threshold,
show_mask_heatmaps=False,
masks_per_dim=args.masks_per_dim,
min_image_size=args.min_image_size,
show_mask_binary=True)
# cam = cv2.VideoCapture("../../../figure/video.avi")
# while True:
# start_time = time.time()
# ret_val, img = cam.read()
# composite = coco_demo.run_on_opencv_image(img)
# print("Time: {:.2f} s / img".format(time.time() - start_time))
# cv2.imshow("COCO detections", composite)
# if cv2.waitKey(1) == 27:
# break # esc to quit
# cv2.destroyAllWindows()
composite = coco_demo.run_on_opencv_image(image)
# cv2.imshow("COCO detections", composite)
return composite
def test_net_on_wsi(config_file, ckpt, iteration):
#========test on monuseg
img_root = '/mnt/DATA_OTHER/moNuSeg/original_testing/tissue_Images/'
anno_root = '/mnt/DATA_OTHER/moNuSeg/original_testing/tissue_Images/'
# img_root = '/mnt/DATA_OTHER/moNuSeg/original_training/tissue_Images/'
# anno_root = '/mnt/DATA_OTHER/moNuSeg/original_training/tissue_Images/'
test_data = monuseg(img_root, anno_root)
# ###========test on monuseg
# img_root = '/mnt/DATA_OTHER/digestPath/Signet_ring_cell_dataset/sig-train-pos/validation/'
# test_data = ringcell(img_root, anno_root)
_, img_list, _, _ = test_data.walk_root_dir()
# config_file = args.config_file
# config_file = '/home/ys309/Dropbox/coding/maskrcnn-benchmark/configs/monuseg/rc_retinanet_R-50-FPN_1x.yaml'
# update the config options with the config file
cfg.merge_from_file(config_file)
# manual override some options
cfg.merge_from_list(["MODEL.DEVICE", "cuda:0"])
cfg.MODEL.WEIGHT = ckpt
# cfg.MODEL.WEIGHT = '/mnt/DATA_OTHER/moNuSeg/results/rc_retinanet_R-50-FPN_1x/model_0020000.pth'
histo_demo = HistoDemo(
cfg,
min_image_size=600,
confidence_threshold=0.5,
)
# ### confidence_threshold=0.5
# # plot bounding boxes
# from maskrcnn_benchmark.data.datasets.evaluation.histo import eval_detection_monuseg
# model_size = 600
# overlap = 200
# # l_scores=[]
# for i, fimg in enumerate(img_list):
# if i<90:
# print('%d/%d'%(i+1,len(img_list)))
# img = Image.open(fimg)
# boxlist=histo_demo.sliding_window_wsi(img, nms_thresh = 0.25)
# # l_scores.append(boxlist.get_field('scores'))
# boxes=boxlist.bbox.cpu().numpy()
# gt = test_data.get_groundtruth(i)
# gt_boxes = gt.bbox.cpu().numpy()
# result = eval_detection_monuseg([boxlist], [gt], iou_thresh=0.25,)
# print (result)
# else:
# break
# #
# # R-50-2500
### confidence_threshold=0.5
# all testing data
# plot bounding boxes
model_size = 600
overlap = 200
# l_scores=[]
predictions = []
gts = []
for i, fimg in enumerate(img_list):
if i<90:
print('%d/%d'%(i+1,len(img_list)))
img = Image.open(fimg)
boxlist=histo_demo.sliding_window_wsi(img, nms_thresh = 0.3)
predictions.append(boxlist)
gt = test_data.get_groundtruth(i)
gts.append(gt)
else:
break
output_folder = os.path.join(cfg.OUTPUT_DIR, cfg.OUTPUT_FOLDER)
result = eval_detection_monuseg(predictions, gts, iou_thresh=0.3, iteration=iteration, output_folder=output_folder)
print (result)
del histo_demo
return result
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
args.distributed = num_gpus > 1
if args.distributed:
# os.environ['MASTER_ADDR'] = '127.0.0.1'
# os.environ['MASTER_PORT'] = '29500'
torch.cuda.set_device(args.local_rank)
torch.distributed.deprecated.init_process_group(backend="nccl",
init_method="env://")
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
output_dir = cfg.OUTPUT_DIR
run_name = get_run_name() + '_step'
output_dir = get_output_dir(output_dir, args, run_name)
if output_dir:
mkdir(output_dir)
logger = setup_logger("maskrcnn_benchmark", output_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(args)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(cfg))
model = train(cfg, args.local_rank, args.distributed, output_dir)
if not args.skip_test:
test(cfg, model, args.distributed)
def main():
# Build a parser for arguments
parser = argparse.ArgumentParser(description="Action Prediction Training")
parser.add_argument(
"--config-file",
# default="/home/SelfDriving/maskrcnn/maskrcnn-benchmark/configs/e2e_faster_rcnn_R_101_FPN_1x.yaml",
default="/home/SelfDriving/maskrcnn/maskrcnn-benchmark/configs/e2e_faster_rcnn_R_50_C4_1x.yaml",
metavar="FILE",
help="path to maskrcnn_benchmark config file",
type=str,
)
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
default=False
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
parser.add_argument(
"--MaxIteration",
help="the iteration to end training",
type=int,
default=90000,
)
parser.add_argument(
"--initLR",
help="Initial learning rate",
default=0.001
)
parser.add_argument(
"--imageroot",
type=str,
help="Directory to the images",
default="/home/SelfDriving/maskrcnn/maskrcnn-benchmark/datasets/bdd100k/images/100k/train"
)
parser.add_argument(
"--gtroot",
type=str,
help="Directory to the groundtruth",
default="/home/SelfDriving/maskrcnn/maskrcnn-benchmark/datasets/bdd100k/annotations/train_gt_action.json"
)
parser.add_argument(
"--imWidth",
type=int,
help="Crop to width",
default=1280
)
parser.add_argument(
"--imHeight",
type=int,
help="Crop to height",
default=720
)
parser.add_argument(
"--batch_size",
type=int,
help="Batch Size",
default=1
)
parser.add_argument(
"--experiment",
type=str,
help="Give this experiment a name",
default=str(datetime.datetime.now())
)
args = parser.parse_args()
print(args)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
if torch.cuda.is_available():
print("CUDA device is available.")
# output directory
outdir = cfg.OUTPUT_DIR
print("Save path:", outdir)
if outdir:
mkdir(outdir)
# logger = setup_logger("training", outdir)
train(cfg, args)
# if validate
if not args.skip_test:
run_test()
import torchvision.models as models
from flashtorch.utils import apply_transforms, load_image
from flashtorch.saliency import Backprop
from flashtorch.activmax import GradientAscent
import matplotlib.pyplot as plt
import torch
from maskrcnn_benchmark.modeling.detector import build_detection_model
from maskrcnn_benchmark.config import cfg
import os
from tqdm import tqdm
cfg.merge_from_file('./maskrcnn-benchmark/configs/e2e_faster_rcnn_R_50_FPN_1x.yaml')
model=build_detection_model(cfg) # loaded from the checkpoint model
model=model.backbone
path='/home/wangfa/Workspace/jupiter/maskrcnn-benchmark/datasets/coco/train2014/'
for root,dirs,files in os.walk(path):
for file in tqdm(files):
backprop = Backprop(model)
image = load_image(os.path.join(root,file))
input_ = apply_transforms(image)
target_class = 0
backprop.visualize(input_,target_class,guided=True)
# model = models.vgg16(pretrained=True)
# g_ascent= GradientAscent(model.features)
# conv5_1=model.features[24]
# conv5_1_filters= [45,271,363,409]
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Webcam Demo")
parser.add_argument(
"--config-file",
default="../configs/caffe2/e2e_mask_rcnn_R_50_FPN_1x_caffe2.yaml",
# default="../configs/e2e_mask_rcnn_R_50_FPN_1x.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument(
"--confidence-threshold",
type=float,
default=0.7,
help="Minimum score for the prediction to be shown",
)
parser.add_argument(
"--min-image-size",
type=int,
default=224,
help="Smallest size of the image to feed to the model. "
"Model was trained with 800, which gives best results",
)
parser.add_argument(
"--show-mask-heatmaps",
dest="show_mask_heatmaps",
help="Show a heatmap probability for the top masks-per-dim masks",
action="store_true",
)
parser.add_argument(
"--masks-per-dim",
type=int,
default=2,
help="Number of heatmaps per dimension to show",
)
parser.add_argument(
"opts",
help="Modify model config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
# load config from file and command-line arguments
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
# prepare object that handles inference plus adds predictions on top of image
coco_demo = COCODemo(
cfg,
confidence_threshold=args.confidence_threshold,
show_mask_heatmaps=args.show_mask_heatmaps,
masks_per_dim=args.masks_per_dim,
min_image_size=args.min_image_size,
)
# cam = cv2.VideoCapture('/dev/C922')
cam = cv2.VideoCapture(0)
while True:
start_time = time.time()
ret_val, img = cam.read()
if ret_val:
composite = coco_demo.run_on_opencv_image(img)
print("Time: {:.2f} s / img".format(time.time() - start_time))
print("FPS: ", 1.0 /
(time.time() - start_time)) # FPS = 1 / time to process loop
cv2.imshow("COCO detections", composite)
else:
break
k = cv2.waitKey(1)
if k == 27 or k == ord('q'):
print('Exit with code 0')
break # esc to quit
cv2.destroyAllWindows()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('config_file')
parser.add_argument('ckpt_file')
parser.add_argument('image_dir')
parser.add_argument('name_file')
parser.add_argument('bbox_file')
parser.add_argument('output_dir')
parser.add_argument('--layer_name', default='fc7')
parser.add_argument('--start_id', type=int, default=0)
parser.add_argument('--end_id', type=int, default=None)
opts = parser.parse_args()
bbox_data = json.load(open(opts.bbox_file))
if not os.path.exists(opts.output_dir):
os.makedirs(opts.output_dir)
########### build model #############
# update the config options with the config file
cfg.merge_from_file(opts.config_file)
# manual override some options
cfg.merge_from_list(['MODEL.DEVICE', 'cuda:0'])
cfg.freeze()
device = torch.device(cfg.MODEL.DEVICE)
cpu_device = torch.device("cpu")
model = build_detection_model(cfg)
model.to(device)
model.eval()
checkpointer = DetectronCheckpointer(cfg, model)
_ = checkpointer.load(f=opts.ckpt_file, use_latest=False)
transform_fn = build_transform(cfg)
########### extract feature #############
names = np.load(opts.name_file)
if opts.end_id is None:
opts.end_id = len(names)
total_images = opts.end_id - opts.start_id
for i, name in enumerate(names):
if i < opts.start_id or i >= opts.end_id:
continue
outname = name.replace('/', '_')
outfile = os.path.join(opts.output_dir, '%s.hdf5'%outname)
if os.path.exists(outfile):
continue
img_file = os.path.join(opts.image_dir, name)
# apply pre-processing to image
original_image = cv2.imread(img_file)
height, width = original_image.shape[:-1]
image = transform_fn(original_image)
nheight, nwidth = image.size(1), image.size(2)
# convert to an ImageList, padded so that it is divisible by
# cfg.DATALOADER.SIZE_DIVISIBILITY
image_list = to_image_list(image, cfg.DATALOADER.SIZE_DIVISIBILITY)
image_list = image_list.to(device)
# compute predictions: one image one mini-batch
with torch.no_grad():
# features: tuples in FPN (batch, dim_ft: 256, h, w)
features = model.backbone(image_list.tensors)
if name in bbox_data:
cpu_boxes = bbox_data[name]
boxes = torch.FloatTensor(cpu_boxes).to(device)
cand_proposals = BoxList(boxes, (width, height), mode='xyxy')
cand_proposals = cand_proposals.resize((nwidth, nheight))
bbox_fts, _, _ = model.roi_heads.extract_features(features, [cand_proposals])
bbox_fts = bbox_fts[opts.layer_name].cpu()
# save to file
with h5py.File(outfile, 'w') as outf:
outf.create_dataset(outname, bbox_fts.size(), dtype='float', compression='gzip')
outf[outname][...] = bbox_fts.data.numpy()
outf[outname].attrs['image_w'] = width
outf[outname].attrs['image_h'] = height
outf[outname].attrs['boxes'] = np.array(cpu_boxes).astype(np.int32)
if i % 1000 == 0:
print('name %s shape %s, processing %d/%d (%.2f%% done)'%(name,
bbox_fts.shape, i-opts.start_id, total_images, (i-opts.start_id)*100/total_images))
def main(dir_path=None, config_file=None, model_file=None, save_dir=None):
dir_path = norm_path(dir_path) if dir_path else None
config_file = norm_path(config_file) if config_file else None
model_file = norm_path(model_file) if model_file else None
save_dir = norm_path(save_dir, makedirs=True) if save_dir else None
save_crop_dir = norm_path(os.path.join(save_dir, 'crop'),
makedirs=True) if save_dir else None
save_mask_dir = norm_path(os.path.join(save_dir, 'mask'),
makedirs=True) if save_dir else None
print('paths', save_dir, save_crop_dir, save_mask_dir)
# this makes our figures bigger
pylab.rcParams['figure.figsize'] = 20, 12
# update the config options with the config file
cfg.merge_from_file(config_file)
# manual override some options
cfg.merge_from_list(["MODEL.DEVICE", "cuda"])
cfg.merge_from_list(["MODEL.WEIGHT", model_file])
kidney_demo = KidneyDemo(
cfg,
min_image_size=512,
confidence_threshold=0.3,
)
class_names = ['', 'AKI', 'CKD', 'normal']
acc_meter = Acc_meter()
for filePath in image_list(dir_path):
print('file_path', filePath)
img = cv2.imread(filePath, cv2.IMREAD_COLOR)
# resize image for input size of model
img, resize_info = resize_aspect_ratio(img, (512, 512))
#find label high score
result, crops, masks, labels = kidney_demo.detection(img)
top_label = labels[0]
#find diagnosis in directory, it will be used as an correct answer
path = os.path.split(filePath)[0]
diagnosis, accno = path.split('/')[-2:]
#convert diagnosis to int(because labels is integer)
diag_class_no = class_names.index(diagnosis)
# print(diagnosis)
# print(top_label)
# evaluate(diagnosis,top_label)
acc_meter.update(diag_class_no, top_label)
# restore size of image to original size
result = resize_restore(result, resize_info)
# save result image
if save_dir:
save_file = os.path.join(save_dir, fileName(filePath))
cv2.imwrite(save_file, result)
else:
imshow(result)
# if found object, make corp and mask image
if len(labels) > 0:
for crop, mask, label in zip(crops, masks, labels):
if save_crop_dir:
save_file = os.path.join(save_crop_dir, fileName(filePath))
crop = resize_restore(crop, resize_info)
cv2.imwrite(save_file, crop)
if save_mask_dir:
save_file = os.path.join(save_mask_dir, fileName(filePath))
mask = resize_restore(mask, resize_info)
cv2.imwrite(save_file, mask)
print('acc:{:3.2f}'.format(acc_meter.get_acc()))
for class_num, class_acc in acc_meter.get_class_acc():
print('class {} acc {:3.2f}'.format(class_num, class_acc * 100))
def main():
mlperf_log.ROOT_DIR_MASKRCNN = os.path.dirname(os.path.abspath(__file__))
parser = argparse.ArgumentParser(description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
args.distributed = num_gpus > 1
if is_main_process:
# Setting logging file parameters for compliance logging
os.environ["COMPLIANCE_FILE"] = '/MASKRCNN_complVv0.5.0_' + str(datetime.datetime.now())
mlperf_log.LOG_FILE = os.getenv("COMPLIANCE_FILE")
mlperf_log._FILE_HANDLER = logging.FileHandler(mlperf_log.LOG_FILE)
mlperf_log._FILE_HANDLER.setLevel(logging.DEBUG)
mlperf_log.LOGGER.addHandler(mlperf_log._FILE_HANDLER)
if args.distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(
backend="nccl", init_method="env://"
)
synchronize()
print_mlperf(key=mlperf_log.RUN_START)
# setting seeds - needs to be timed, so after RUN_START
if is_main_process():
master_seed = random.SystemRandom().randint(0, 2 ** 32 - 1)
seed_tensor = torch.tensor(master_seed, dtype=torch.float32, device=torch.device("cuda"))
else:
seed_tensor = torch.tensor(0, dtype=torch.float32, device=torch.device("cuda"))
torch.distributed.broadcast(seed_tensor, 0)
master_seed = int(seed_tensor.item())
else:
print_mlperf(key=mlperf_log.RUN_START)
# random master seed, random.SystemRandom() uses /dev/urandom on Unix
master_seed = random.SystemRandom().randint(0, 2 ** 32 - 1)
# actually use the random seed
args.seed = master_seed
# random number generator with seed set to master_seed
random_number_generator = random.Random(master_seed)
print_mlperf(key=mlperf_log.RUN_SET_RANDOM_SEED, value=master_seed)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
output_dir = cfg.OUTPUT_DIR
if output_dir:
mkdir(output_dir)
logger = setup_logger("maskrcnn_benchmark", output_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(args)
# generate worker seeds, one seed for every distributed worker
worker_seeds = generate_seeds(random_number_generator, torch.distributed.get_world_size() if torch.distributed.is_initialized() else 1)
# todo sharath what if CPU
# broadcast seeds from rank=0 to other workers
worker_seeds = broadcast_seeds(worker_seeds, device='cuda')
# Setting worker seeds
logger.info("Worker {}: Setting seed {}".format(args.local_rank, worker_seeds[args.local_rank]))
torch.manual_seed(worker_seeds[args.local_rank])
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(cfg))
model = train(cfg, args.local_rank, args.distributed)
print_mlperf(key=mlperf_log.RUN_FINAL)
masks = prediction.get_field('mask').squeeze(1).numpy()
if show:
res = draw_masks_maskrcnn(image,
boxes,
scores,
labels,
masks,
human_label_list=CATEGORIES)
# print('fps: {}'.format(1/(time.time() - tic)))
return boxes, scores, labels, masks, res
else:
return boxes, scores, labels, masks, _
if __name__ == "__main__":
cfg.merge_from_file(
'../configs/caffe2/e2e_mask_rcnn_R_50_FPN_1x_caffe2.yaml')
cfg.merge_from_list(["MODEL.DEVICE", "cuda"])
cfg.freeze()
mask_rcnn_demo = MaskRCNNDemo(cfg)
v_f = sys.argv[1]
cap = cv2.VideoCapture(v_f)
fps = cap.get(cv2.CAP_PROP_FPS)
size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))
video_writer = cv2.VideoWriter('result.mp4',
cv2.VideoWriter_fourcc(*'DIVX'), fps, size)
while True:
start_time = time.time()
def main():
parser = argparse.ArgumentParser(description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default="configs/visual_genome_vqa/e2e_faster_rcnn_X-101-64x4d-FPN_1x_MLP_2048_FPN_512_vqa_single.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument(
"--save_path",
default="/checkpoint/meetshah/features/vqa/pytorch/resnext101_64x4d_mlp_2048_fpn_512/",
)
parser.add_argument(
"--feat_name",
default="fc6",
)
parser.add_argument(
"--n_groups",
default=0,
)
parser.add_argument(
"--group_id",
default=1,
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
if not os.path.exists(args.save_path):
os.makedirs(args.save_path)
num_gpus = int(os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
distributed = num_gpus > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl", init_method="env://")
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", save_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(cfg)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
model = build_detection_model(cfg)
model.to(cfg.MODEL.DEVICE)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
iou_types = ("bbox",)
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm",)
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
data_loaders_val = make_data_loader(cfg, is_train=False, is_distributed=distributed)
for output_folder, dataset_name, data_loader_val in zip(
output_folders, dataset_names, data_loaders_val
):
inference(
model,
data_loader_val,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
save_path=args.save_path,
feat_name=args.feat_name,
group_id=args.group_id,
n_groups=args.n_groups,
)
synchronize()
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default=
"/private/home/fmassa/github/detectron.pytorch_v2/configs/e2e_faster_rcnn_R_50_C4_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--ckpt",
help=
"The path to the checkpoint for test, default is the latest checkpoint.",
default=None,
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
distributed = num_gpus > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", save_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(cfg)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
model = build_detection_model(cfg)
model.to(cfg.MODEL.DEVICE)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
ckpt = cfg.MODEL.WEIGHT if args.ckpt is None else args.ckpt
_ = checkpointer.load(ckpt, use_latest=args.ckpt is None)
"""
# Initialize mixed-precision if necessary
use_mixed_precision = cfg.DTYPE == 'float16'
amp_handle = amp.init(enabled=use_mixed_precision, verbose=cfg.AMP_VERBOSE)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
ckpt = cfg.MODEL.WEIGHT if args.ckpt is None else args.ckpt
_ = checkpointer.load(ckpt, use_latest=args.ckpt is None)
iou_types = ("bbox",)
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm",)
if cfg.MODEL.KEYPOINT_ON:
iou_types = iou_types + ("keypoints",)
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
data_loaders_val = make_data_loader(cfg, is_train=False, is_distributed=distributed)
for output_folder, dataset_name, data_loader_val in zip(output_folders, dataset_names, data_loaders_val):
inference(
model,
data_loader_val,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=False if cfg.MODEL.RETINANET_ON else cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
)
synchronize()
"""
from maskrcnn_benchmark.data.transforms.build import build_transforms
from PIL import Image
import torchvision.transforms.functional as F
transform = build_transforms(cfg, is_train=False)
img_dir = "demo_imgs"
res_dir = "demo_res"
model.eval()
imgs = os.listdir(img_dir)
for img in imgs:
img_path = os.path.join(img_dir, img)
img_pil = Image.open(img_path)
# for i in range( 360 ):
original_img = img_pil
# original_img = F.rotate( img_pil, 45, expand=True )
origin_w, origin_h = original_img.size
img, target = transform(original_img, None)
print(img.shape)
img = img.view((1, img.shape[0], img.shape[1], img.shape[2]))
h, w = img.shape[2:]
if h % 32 != 0:
new_h = (h // 32 + 1) * 32
else:
new_h = h
if w % 32 != 0:
new_w = (w // 32 + 1) * 32
else:
new_w = w
ratio_w = 1. * new_w / w
ratio_h = 1. * new_h / h
padded_img = torch.zeros((1, 3, new_h, new_w)).float()
padded_img[:, :, :h, :w] = img
prediction = model(padded_img.cuda())[0]
prediction = prediction.resize(
(origin_w * ratio_w, origin_h * ratio_h))
hboxes = prediction.bbox.cpu()
rboxes = prediction.get_field("rboxes").cpu()
ratios = prediction.get_field("ratios").cpu()
scores = prediction.get_field("scores").cpu()
# labels = prediction.get_field( "labels" ).cpu()
for rbox, ratio, score in zip(rboxes, ratios, scores):
print(rbox)
print(ratio, score)
h_idx = ratios > 0.8
# print(hboxes)
h = hboxes[h_idx]
hboxes_vtx = torch.stack([
h[:, 0], h[:, 1], h[:, 2], h[:, 1], h[:, 2], h[:, 3], h[:, 0], h[:,
3]
]).permute(1, 0)
rboxes[h_idx] = hboxes_vtx
# rboxes = rboxes.data.numpy().astype( np.int32 )
rboxes = rboxes.data.numpy()
keep = poly_nms(
np.hstack([rboxes,
scores.cpu().data.numpy()[:, np.newaxis]
]).astype(np.double), 0.1)
rboxes = rboxes[keep].astype(np.int32)
scores = scores[keep]
hboxes = hboxes[keep]
keep = np.where(scores > 0.6)
rboxes = rboxes[keep]
scores = scores[keep].tolist()
hboxes = hboxes[keep]
# rboxes = list( map( minAreaRect, rboxes ) )
if len(rboxes) > 0:
rboxes = np.vstack(rboxes)
else:
rboxes = np.array(rboxes)
# vis( img_info["file_name"], rboxes )
# img = cv2.imread( original_img )
img = np.array(original_img.convert("RGB"))[:, :, ::-1].copy()
cv2.polylines(img,
rboxes.reshape(-1, 4, 2).astype(np.int32),
True, (0, 255, 255),
thickness=2,
lineType=cv2.LINE_AA)
filename = img_path.split("/")[-1]
cv2.imwrite("{}/{}".format(res_dir, filename), img)
def main():
parser = argparse.ArgumentParser(
description="PyTorch Relation Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
cfg.NUM_GPUS = num_gpus
args.distributed = num_gpus > 1
if args.distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
output_dir = cfg.OUTPUT_DIR
if output_dir:
mkdir(output_dir)
listener_dir = cfg.LISTENER_DIR
if listener_dir:
mkdir(listener_dir)
logger = setup_logger("maskrcnn_benchmark", output_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(args)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(cfg))
"""
output_config_path = os.path.join(cfg.OUTPUT_DIR, 'config.yml')
logger.info("Saving config into: {}".format(output_config_path))
# save overloaded model config in the output directory
save_config(cfg, output_config_path)
"""
listener_config_path = os.path.join(cfg.LISTENER_DIR, 'config.yml')
logger.info("Saving config into: {}".format(listener_config_path))
# save overloaded model config in the output directory
save_config(cfg, listener_config_path)
listener = train(cfg, args.local_rank, args.distributed, logger)
if not args.skip_test:
run_test(cfg, model, listener, args.distributed, logger)
def main():
parser = argparse.ArgumentParser(description="DPNet Demo")
parser.add_argument(
"--config-file",
default=
"configs/e2e_faster_rcnn_R_101_FPN_1x_rpc_syn_render_density_map.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument(
"--images_dir",
required=True,
type=str,
help="path to images file",
)
parser.add_argument(
"--save_dir",
default='rpc_results',
type=str,
help="path to images file",
)
parser.add_argument(
"--confidence-threshold",
type=float,
default=0.7,
help="Minimum score for the prediction to be shown",
)
parser.add_argument(
"--min-image-size",
type=int,
default=800,
help="Smallest size of the image to feed to the model. "
"Model was trained with 800, which gives best results",
)
parser.add_argument(
"--show-mask-heatmaps",
dest="show_mask_heatmaps",
help="Show a heatmap probability for the top masks-per-dim masks",
action="store_true",
)
parser.add_argument(
"--masks-per-dim",
type=int,
default=2,
help="Number of heatmaps per dimension to show",
)
parser.add_argument(
"opts",
help="Modify model config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
# load config from file and command-line arguments
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
# prepare object that handles inference plus adds predictions on top of image
coco_demo = COCODemo(
cfg,
confidence_threshold=args.confidence_threshold,
show_mask_heatmaps=args.show_mask_heatmaps,
masks_per_dim=args.masks_per_dim,
min_image_size=args.min_image_size,
)
if os.path.exists(args.save_dir):
shutil.rmtree(args.save_dir)
os.mkdir(args.save_dir)
with open('/data7/lufficc/rpc/instances_test2019.json') as fid:
data = json.load(fid)
images = {}
for x in data['images']:
images[x['id']] = x
annotations = defaultdict(list)
for x in data['annotations']:
annotations[images[x['image_id']]['file_name']].append(x)
annotations = dict(annotations)
counter = {
'easy': 0,
'medium': 0,
'hard': 0,
}
data_images = data['images'].copy()
random.shuffle(data_images)
FONT = ImageFont.truetype('/data7/lufficc/projects/DPNet/demo/arial.ttf',
8)
for image_ann in data_images:
if counter[image_ann['level']] >= 20:
continue
image_path = os.path.join(args.images_dir, image_ann['file_name'])
img = cv2.imread(image_path)
annotation = annotations[image_ann['file_name']]
prediction = coco_demo.run_on_opencv_image(img)
new_size = (400, 400)
img = cv2.resize(img, new_size)
prediction = prediction.resize(new_size)
boxes = prediction.bbox.numpy()
labels = prediction.get_field('labels').numpy()
scores = prediction.get_field('scores').numpy()
img = draw_boxes(img,
boxes,
labels,
scores,
COCODemo.CATEGORIES,
width=2,
font=FONT,
alpha=0.4)
gt_labels = sorted([ann['category_id'] for ann in annotation])
if gt_labels == sorted(labels.tolist()):
print('Get {}.'.format(image_ann['level']))
cv2.imwrite(
os.path.join(
args.save_dir,
image_ann['level'] + '_' + os.path.basename(image_path)),
img)
counter[image_ann['level']] += 1
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default=
"/private/home/fmassa/github/detectron.pytorch_v2/configs/e2e_faster_rcnn_R_50_C4_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
distributed = num_gpus > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.deprecated.init_process_group(backend="nccl",
init_method="env://")
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", save_dir, args.local_rank)
logger.info("Using {} GPUs".format(num_gpus))
logger.info(cfg)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
model = build_detection_model(cfg)
model.to(cfg.MODEL.DEVICE)
checkpointer = DetectronCheckpointer(cfg, model)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
iou_types = ("bbox", )
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm", )
output_folders = [None] * len(cfg.DATASETS.TEST)
if cfg.OUTPUT_DIR:
dataset_names = cfg.DATASETS.TEST
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference",
dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
data_loaders_val = make_data_loader(cfg,
is_train=False,
is_distributed=distributed)
for output_folder, data_loader_val in zip(output_folders,
data_loaders_val):
inference(
model,
data_loader_val,
iou_types=iou_types,
box_only=cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
)
synchronize()
def main():
parser = argparse.ArgumentParser(description="PyTorch Object Detection Webcam Demo")
parser.add_argument(
"--config-file",
default="../configs/caffe2/e2e_mask_rcnn_R_50_FPN_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument(
"--confidence-threshold",
type=float,
default=0.7,
help="Minimum score for the prediction to be shown",
)
parser.add_argument(
"--min-image-size",
type=int,
default=224,
help="Smallest size of the image to feed to the model. "
"Model was trained with 800, which gives best results",
)
parser.add_argument(
"--show-mask-heatmaps",
dest="show_mask_heatmaps",
help="Show a heatmap probability for the top masks-per-dim masks",
action="store_true",
)
parser.add_argument(
"--masks-per-dim",
type=int,
default=2,
help="Number of heatmaps per dimension to show",
)
parser.add_argument(
"opts",
help="Modify model config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
# load config from file and command-line arguments
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
# prepare object that handles inference plus adds predictions on top of image
coco_demo = COCODemo(
cfg,
confidence_threshold=args.confidence_threshold,
show_mask_heatmaps=args.show_mask_heatmaps,
masks_per_dim=args.masks_per_dim,
min_image_size=args.min_image_size,
)
cam = cv2.VideoCapture(0)
while True:
start_time = time.time()
ret_val, img = cam.read()
composite = coco_demo.run_on_opencv_image(img)
print("Time: {:.2f} s / img".format(time.time() - start_time))
cv2.imshow("COCO detections", composite)
if cv2.waitKey(1) == 27:
break # esc to quit
cv2.destroyAllWindows()
def main():
parser = argparse.ArgumentParser(description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default="/private/home/fmassa/github/detectron.pytorch_v2/configs/e2e_faster_rcnn_R_50_C4_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
distributed = num_gpus > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.deprecated.init_process_group(
backend="nccl", init_method="env://"
)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", save_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(cfg)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
model = build_detection_model(cfg)
model.to(cfg.MODEL.DEVICE)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
iou_types = ("bbox",)
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm",)
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
data_loaders_val = make_data_loader(cfg, is_train=False, is_distributed=distributed)
for output_folder, dataset_name, data_loader_val in zip(output_folders, dataset_names, data_loaders_val):
inference(
model,
data_loader_val,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
)
synchronize()
from maskrcnn_benchmark.data.datasets.evaluation import evaluate
from maskrcnn_benchmark.data.datasets.cityscapes import CityscapesDataset
import torch
from maskrcnn_benchmark.config import cfg
from maskrcnn_benchmark.data import make_data_loader
output_folder = '/home/brianyao/Documents/maskrcnn-benchmark/inference/cityscapes_fine_instanceonly_seg_val_cocostyle'
anno_file = '/media/DATA/Cityscapes/annotations/instancesonly_filtered_gtFine_val.json'
root = '/media/DATA/Cityscapes/leftImg8bit/val'
dataset = CityscapesDataset(anno_file, root, True)
cfg.merge_from_file('../configs/cityscapes/mask_rcnn_coco_eval.yaml')
cfg.merge_from_list([])
cfg.freeze()
data_loaders_val = make_data_loader(cfg, is_train=False, is_distributed=False)
data_loader = data_loaders_val[0]
extra_args = dict(
box_only=False,
iou_types=("bbox", "segm"),
expected_results=[],
expected_results_sigma_tol=4,
)
predictions = torch.load(
'../inference/cityscapes_fine_instanceonly_seg_val_cocostyle/predictions.pth'
)
evaluate(data_loader.dataset, predictions, output_folder, **extra_args)