def main():
global_config = config['Global']
device = torch.device('cpu')
if global_config['use_gpu'] and torch.cuda.is_available():
device = torch.device('cuda')
logger.info('使用设备：{}'.format(device))
logger.info('模型信息：{}'.format(config['Architecture']))
model = build_model(config['Architecture'])
model.to(device)
logger.info('加载预训练模型：{}'.format(global_config['pretrained_model']))
state_dict = torch.load(global_config['pretrained_model'])
model.load_state_dict(state_dict)
post_process_class = build_post_process(config['PostProcess'])
ops = []
for op in config['Eval']['dataset']['transforms']:
op_name = list(op)[0]
if 'Label' in op_name:
continue
elif op_name == "KeepKeys":
op[op_name]['keep_keys'] = ['image', 'shape']
ops.append(op)
transforms = create_transformers(ops)
save_res_path = global_config['save_res_path']
save_dir = os.path.dirname(save_res_path)
if not os.path.exists(save_dir):
os.makedirs(save_dir)
model.eval()
with open(save_res_path, 'wb') as fout:
for file in get_img_list(global_config['infer_img']):
logger.info(f"测试图像：{file}")
data = {'image': file}
batch = transforms(data)
images = np.expand_dims(batch[0], axis=0)
shape_list = np.expand_dims(batch[1], axis=0)
images = torch.from_numpy(images).to(device)
preds = model(images)
post_result = post_process_class(preds, shape_list)
boxes = post_result[0]['points']
dt_boxes_json = []
for box in boxes:
tmp_json = {"transcription": ""}
tmp_json['points'] = box.tolist()
dt_boxes_json.append(tmp_json)
otstr = file + "\t" + json.dumps(dt_boxes_json) + '\n'
fout.write(otstr.encode())
src_img = cv.imread(file)
draw_det_res(boxes, save_dir, src_img, file)
logger.info("结果已保存！")
def console_main():
URL, no_to_download, format_list, download_path, max_filesize, dump_urls, use_ghost = get_arguments(
)
print "\n ImageScraper\n ============\n Requesting page....\n"
page_html, page_url = get_html(URL, use_ghost)
images = get_img_list(page_html, page_url, format_list)
if len(images) == 0:
sys.exit("Sorry, no images found.")
if no_to_download == 0:
no_to_download = len(images)
print "Found %s images: " % len(images)
process_download_path(download_path)
for img_url in images:
if dump_urls:
print img_url
count = 0
percent = 0.0
failed = 0
over_max_filesize = 0
widgets = [
'Progress: ',
Percentage(), ' ',
Bar(marker=RotatingMarker()), ' ',
ETA(), ' ',
FileTransferSpeed()
]
pbar = ProgressBar(widgets=widgets, maxval=100).start()
for img_url in images:
flag, size_flag = download_image(img_url, download_path, max_filesize)
if not flag:
if not size_flag:
failed += 1
else:
over_max_filesize += 1
count += 1
percent = percent + 100.0 / no_to_download
pbar.update(percent % 100)
if count == no_to_download:
break
pbar.finish()
print "\nDone!\nDownloaded %s images" % (count - failed -
over_max_filesize)
return
def main():
global_config = config['Global']
device = torch.device('cpu')
if global_config['use_gpu'] is True and torch.cuda.is_available():
device = torch.device('cuda')
logger.info('使用设备：{}'.format(device))
post_process_class = build_post_process(config['PostProcess'],
global_config)
if hasattr(post_process_class, 'character'):
config['Architecture']["Head"]['out_channels'] = len(
getattr(post_process_class, 'character'))
logger.info('构建模型，字典包含{}个字'.format(
config['Architecture']["Head"]['out_channels']))
logger.info('模型结构：{}'.format(config['Architecture']))
model = build_model(config['Architecture'])
model.to(device)
logger.info('加载预训练模型 {}...'.format(global_config['pretrained_model']))
state_dict = torch.load(global_config['pretrained_model'])
model.load_state_dict(state_dict)
ops = []
for op in config['Eval']['dataset']['transforms']:
op_name = list(op)[0]
if 'Label' in op_name:
continue
elif op_name in ['RecResizeImg']:
op[op_name]['infer_mode'] = True
elif op_name == 'KeepKeys':
op[op_name]['keep_keys'] = ['image']
ops.append(op)
global_config['infer_mode'] = True
transforms = create_transformers(ops, global_config)
model.eval()
for file in get_img_list(config['Global']['infer_img']):
logger.info('输入图像：{}'.format(file))
data = {'image': file}
batch = transforms(data)
images = torch.from_numpy(batch[0]).to(device)
images = images.unsqueeze(0)
preds = model(images)
post_result = post_process_class(preds)
logger.info("result: {}".format(post_result))
def run():
data_dir = 'dataset'
data_names = sorted(os.listdir(data_dir))
try:
for data_name in data_names:
tracker = KernelizedCorrelationFilter(correlation_type='gaussian', feature='deep')
data_path = join(data_dir, data_name)
gts = get_ground_truthes(data_path)
img_dir = os.path.join(data_path, 'img')
frame_list = get_img_list(img_dir)
frame_list.sort()
poses = tracker.start(init_gt=gts[0], show=True, frame_list=frame_list)
print(poses)
except Exception as e:
print(e)
def __init__(self, path, transform=None, mode='train', val_path=None):
self.img_path = path + 'case/'
self.mask_path = path + 'mask/'
self.transform = transform
self.mode = mode
if self.mode == 'train':
if not (os.path.isfile(path + 'train.txt')):
utils.get_img_list(path, 'train')
with open(path + 'train.txt', 'r') as f_train:
log = f_train.readlines()
elif self.mode == 'validation':
self.val_path = val_path
if not (os.path.isfile(path + 'val_case.txt')):
utils.get_img_list(path, 'val', val_path=val_path)
with open(val_path + 'val.txt', 'r') as f_val:
log = f_val.readlines()
elif self.mode == 'test':
if not (os.path.isfile(path + 'test.txt')):
utils.get_img_list(path, 'test')
with open(path + 'test.txt', 'r') as f_test:
log = f_test.readlines()
self.log = log
def gen_img():
while True:
frame = get_img_list()
yield (b'--frame\r\n'
b'Content-Type: image/jpeg\r\n\r\n' + frame + b'\r\n')