def main(opt):
# init model
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
Detector = detector_factory[opt.task]
detector = Detector(opt)
debug = 0 # return the detect result without show
threshold = 0.05
TASK = 'ctdet' # or 'multi_pose' for human pose estimation
input_h, intput_w = 512, 512
MODEL_PATH = '/home/jamesyen/my_project/face_detection/CenterNet/exp/ctdet/calface_mobile_l1/model_last_bk.pth'
opt = opts().init('--task {} --load_model {} --debug {} --vis_thresh {} --input_h {} --input_w {}'.format(
TASK, MODEL_PATH, debug, threshold, input_h, intput_w).split(' '))
print("222opt.models ", opt.load_model)
detector = detector_factory[opt.task](opt)
out_onnx_path = "../output/onnx_model/calface_mobilev2.onnx"
image = cv2.imread('../data/cal_face/image/AAEM3872.jpg')
torch_input, meta = detector.pre_process(image, scale=1)
torch_input = torch_input.cuda()
# pytorch output
torch_output = detector.model(torch_input)
torch.onnx.export(detector.model, torch_input, out_onnx_path, verbose=False)
sess = nxrun.InferenceSession(out_onnx_path)
print('save done')
input_name = sess.get_inputs()[0].name
output_onnx = sess.run(None, {input_name: torch_input.cpu().data.numpy()})
temp = 1
def prefetch_test(opt):
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
Dataset = dataset_factory[opt.dataset]
opt = opts().update_dataset_info_and_set_heads(opt, Dataset)
print(opt)
Logger(opt)
Detector = detector_factory[opt.task]
split = 'val' if not opt.trainval else 'test'
dataset = Dataset(opt, split)
detector = Detector(opt)
data_loader = torch.utils.data.DataLoader(PrefetchDataset(
opt, dataset, detector.pre_process),
batch_size=1,
shuffle=False,
num_workers=1,
pin_memory=True)
results_1, results_2 = {}, {}
num_iters = len(dataset)
print("!!!!!!!!!!!!!num_iters ", num_iters)
bar = Bar('{}'.format(opt.exp_id), max=num_iters)
time_stats = ['tot', 'load', 'pre', 'net', 'dec', 'post', 'merge']
avg_time_stats = {t: AverageMeter() for t in time_stats}
tos = time.time()
for ind, (img_id, pre_processed_images) in enumerate(data_loader):
ret = detector.run(pre_processed_images)
results_1[img_id.numpy().astype(np.int64)[0]] = ret['results_1']
results_2[img_id.numpy().astype(np.int64)[0]] = ret['results_2']
Bar.suffix = '[{0}/{1}]|Tot: {total:} |ETA: {eta:} '.format(
ind, num_iters, total=bar.elapsed_td, eta=bar.eta_td)
for t in avg_time_stats:
avg_time_stats[t].update(ret[t])
Bar.suffix = Bar.suffix + '|{} {tm.val:.3f}s ({tm.avg:.3f}s) '.format(
t, tm=avg_time_stats[t])
bar.next()
bar.finish()
print("it took", time.time() - tos, "seconds.")
print("############### ", avg_time_stats['tot'].sum)
dataset.run_eval(results_1, opt.save_dir)
dataset.run_eval(results_2, opt.save_dir)
def test(opt):
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
Dataset = dataset_factory[opt.dataset]
opt = opts().update_dataset_info_and_set_heads(opt, Dataset)
print(opt)
Logger(opt)
Detector = detector_factory[opt.task]
split = 'val' if not opt.trainval else 'test'
dataset = Dataset(opt, split)
detector = Detector(opt)
results = {}
num_iters = len(dataset)
bar = Bar('{}'.format(opt.exp_id), max=num_iters)
time_stats = ['tot', 'load', 'pre', 'net', 'dec', 'post', 'merge']
avg_time_stats = {t: AverageMeter() for t in time_stats}
for ind in range(num_iters):
img_id = dataset.images[ind]
img_info = dataset.coco.loadImgs(ids=[img_id])[0]
img_path = os.path.join(dataset.img_dir, img_info['file_name'])
if opt.task == 'ddd':
ret = detector.run(img_path, img_info['calib'])
else:
ret = detector.run(img_path)
results[img_id] = ret['results_2']
Bar.suffix = '[{0}/{1}]|Tot: {total:} |ETA: {eta:} '.format(
ind, num_iters, total=bar.elapsed_td, eta=bar.eta_td)
for t in avg_time_stats:
avg_time_stats[t].update(ret[t])
Bar.suffix = Bar.suffix + '|{} {:.3f} '.format(
t, avg_time_stats[t].avg)
bar.next()
bar.finish()
dataset.run_eval(results, opt.save_dir)
img_id = dataset.images[ind]
img_info = dataset.coco.loadImgs(ids=[img_id])[0]
img_path = os.path.join(dataset.img_dir, img_info['file_name'])
if opt.task == 'ddd':
ret = detector.run(img_path, img_info['calib'])
else:
ret = detector.run(img_path)
results[img_id] = ret['results_2']
Bar.suffix = '[{0}/{1}]|Tot: {total:} |ETA: {eta:} '.format(
ind, num_iters, total=bar.elapsed_td, eta=bar.eta_td)
for t in avg_time_stats:
avg_time_stats[t].update(ret[t])
Bar.suffix = Bar.suffix + '|{} {:.3f} '.format(
t, avg_time_stats[t].avg)
bar.next()
bar.finish()
dataset.run_eval(results, opt.save_dir)
if __name__ == '__main__':
opt = opts().parse()
print("111111111111111111111111111111opt.not_prefetch_test ",
opt.not_prefetch_test)
if opt.not_prefetch_test:
test(opt)
else:
prefetch_test(opt)
print("1222222222.not_prefetch_test ", opt.not_prefetch_test)
detector = Detector(opt)
debug = 0 # return the detect result without show
threshold = 0.05
TASK = 'ctdet' # or 'multi_pose' for human pose estimation
input_h, intput_w = 512, 512
MODEL_PATH = '/home/jamesyen/my_project/face_detection/CenterNet/exp/ctdet/calface_mobile_l1/model_last_bk.pth'
opt = opts().init('--task {} --load_model {} --debug {} --vis_thresh {} --input_h {} --input_w {}'.format(
TASK, MODEL_PATH, debug, threshold, input_h, intput_w).split(' '))
print("222opt.models ", opt.load_model)
detector = detector_factory[opt.task](opt)
out_onnx_path = "../output/onnx_model/calface_mobilev2.onnx"
image = cv2.imread('../data/cal_face/image/AAEM3872.jpg')
torch_input, meta = detector.pre_process(image, scale=1)
torch_input = torch_input.cuda()
# pytorch output
torch_output = detector.model(torch_input)
torch.onnx.export(detector.model, torch_input, out_onnx_path, verbose=False)
sess = nxrun.InferenceSession(out_onnx_path)
print('save done')
input_name = sess.get_inputs()[0].name
output_onnx = sess.run(None, {input_name: torch_input.cpu().data.numpy()})
temp = 1
if __name__ == '__main__':
opt = opts().init()
main(opt)