post_p_thre=args.thre,
gpu_id=0,
imageH=960,
imageW=480)
img_folder = pathlib.Path(args.input_folder)
for img_path in tqdm(get_file_list(args.input_folder, p_postfix=['.jpg'])):
img = cv2.imread(img_path)
# if img.shape[0] /img.shape[1] > 2 or img.shape[1]/img.shape[0] > 2:
# continue
preds, boxes_list, score_list, t = model.predict(
img_path, is_output_polygon=args.polygon, runtime='trt')
print('time cost: {}s'.format(t))
crops = crop_bbox(img[:, :, ::-1], boxes_list)
img = draw_bbox(img[:, :, ::-1], boxes_list)
if args.show:
show_img(preds)
show_img(img, title=os.path.basename(img_path))
plt.show()
# 保存结果到路径
os.makedirs(args.output_folder, exist_ok=True)
img_path = pathlib.Path(img_path)
output_path = os.path.join(args.output_folder,
img_path.stem + '_result.jpg')
pred_path = os.path.join(args.output_folder,
img_path.stem + '_pred.jpg')
cv2.imwrite(output_path, img[:, :, ::-1])
cv2.imwrite(pred_path, preds * 255)
for i, crop in enumerate(crops):
cv2.imwrite(
os.path.join(args.output_folder,
img_path.stem + '_text_{:02d}.jpg'.format(i)),
tensor = tensor.unsqueeze_(0)
tensor = tensor.to(self.device)
with torch.no_grad():
start = time.time()
preds = self.net(tensor)[0]
preds[:2] = torch.sigmoid(preds[:2])
preds = preds.cpu().numpy()
t = time.time() - start
return preds, t
if __name__ == '__main__':
import matplotlib.pyplot as plt
from utils.util import show_img
os.environ['CUDA_VISIBLE_DEVICES'] = str('2')
model_path = 'output/PAN_resnet18/checkpoint/model_best.pth'
# model_path = 'output/psenet_icd2015_new_loss/final.pth'
img_id = 10
img_path = '/data1/ocr/icdar2015/test/img/img_{}.jpg'.format(img_id)
# 初始化网络
show_img(cv2.imread(img_path)[:, :, ::-1], color=True)
model = Pytorch_model(model_path, gpu_id=0)
preds, t = model.predict(img_path)
show_img(preds)
plt.show()
import matplotlib.pyplot as plt
from torchvision import transforms
train_data = ImageDataset(data_list=[
(r'E:/zj/dataset/icdar2015/train/img/img_15.jpg',
'E:/zj/dataset/icdar2015/train/gt/gt_img_15.txt')
],
input_size=640,
img_channel=3,
shrink_ratio=0.5,
transform=transforms.ToTensor())
train_loader = DataLoader(dataset=train_data,
batch_size=1,
shuffle=False,
num_workers=0)
pbar = tqdm(total=len(train_loader))
for i, (img, shrink_label_map,
threshold_label_map) in enumerate(train_loader):
print(shrink_label_map.shape, shrink_label_map[0][0].max())
print(img.shape)
print(shrink_label_map[0][-1].sum())
# pbar.update(1)
show_img((img[0].to(torch.float)).numpy().transpose(1, 2, 0),
color=True)
show_img((shrink_label_map[0].to(torch.float)).numpy(), color=False)
show_img((threshold_label_map[0].to(torch.float)).numpy(), color=False)
plt.show()
pbar.close()
torch.cuda.synchronize(self.device)
box_list, score_list = self.post_process(batch, preds)
box_list, score_list = box_list[0], score_list[0]
if len(box_list) > 0:
idx = box_list.reshape(box_list.shape[0], -1).sum(axis=1) > 0
box_list, score_list = box_list[idx], score_list[idx]
else:
box_list, score_list = [], []
t = time.time() - start
return preds[0, 0, :, :].detach().cpu().numpy(), box_list, t
if __name__ == '__main__':
import matplotlib.pyplot as plt
from utils.util import show_img, draw_bbox
os.environ['CUDA_VISIBLE_DEVICES'] = str('0')
model_path = '../output/DBNet_resnet18_FPN_DBHead/checkpoint/DBNet_latest.pth'
img_id = 10
img_path = 'E:/zj/dataset/icdar2015/test/img/img_{}.jpg'.format(img_id)
# 初始化网络
model = Pytorch_model(model_path, gpu_id=0)
preds, boxes_list, t = model.predict(img_path)
show_img(preds)
img = draw_bbox(cv2.imread(img_path)[:, :, ::-1], boxes_list)
show_img(img)
plt.show()
if __name__ == '__main__':
import torch
from utils.util import show_img
from tqdm import tqdm
import matplotlib.pyplot as plt
from torchvision import transforms
train_data = ImageDataset(
data_list=[
(r'/data1/zj/ocr/icdar2015/train/img/img_713.jpg', '/data1/zj/ocr/icdar2015/train/gt/gt_img_713.txt')],
input_size=640,
img_channel=3,
shrink_ratio=0.5,
transform=transforms.ToTensor()
)
train_loader = DataLoader(dataset=train_data, batch_size=1, shuffle=False, num_workers=0)
pbar = tqdm(total=len(train_loader))
for i, (img, label, mask) in enumerate(train_loader):
print(label.shape, label[0][0].max())
print(img.shape)
print(label[0][-1].sum())
print(mask[0].shape)
# pbar.update(1)
show_img((img[0] * mask[0].to(torch.float)).numpy().transpose(1, 2, 0), color=True)
show_img(label[0])
show_img(mask[0])
plt.show()
pbar.close()
with torch.no_grad():
start = time.time()
preds = self.net(tensor)[0]
print('net time:', time.time() - start)
preds, boxes_list = decode(preds)
scale = (preds.shape[1] / w, preds.shape[0] / h)
if len(boxes_list):
boxes_list = boxes_list / scale
t = time.time() - start
return preds, boxes_list, t
if __name__ == '__main__':
import matplotlib.pyplot as plt
from utils.util import show_img, draw_bbox
os.environ['CUDA_VISIBLE_DEVICES'] = str('0')
model_path = 'output/PAN_pred_mask_resnet50/checkpoint/model_best.pth'
img_id = 10
img_path = 'E:/zj/dataset/icdar2015/test/img/img_{}.jpg'.format(img_id)
# 初始化网络
model = Pytorch_model(model_path, gpu_id=None)
preds, boxes_list, t = model.predict(img_path)
show_img(preds)
img = draw_bbox(cv2.imread(img_path)[:, :, ::-1], boxes_list)
show_img(img, color=True)
plt.show()
train_data = ImageDataset(
data_list=[
(r'/home1/surfzjy/data/ic13/train_images/100.jpg', '/home1/surfzjy/data/ic13/train_gts/100.txt')],
input_size=640,
img_channel=3,
shrink_ratio=0.4,
transform=transforms.ToTensor()
)
train_loader = DataLoader(dataset=train_data, batch_size=1, shuffle=False, num_workers=0)
pbar = tqdm(total=len(train_loader))
for i, (img, label, mask, G_d) in enumerate(train_loader):
print('==========shape=============')
print(img.shape)
print(label.shape)
print(mask.shape)
print(G_d.shape)
print('AAAAAAAAAAAAAAAAAAAAAAAAAAAA')
print(label.shape, label[0][0].max()) # torch.Size([1, 2, 640, 640]) tensor(1.)
print(img.shape) # torch.Size([1, 3, 640, 640])
print(label[0][-1].sum())
print(mask[0].shape)
# pbar.update(1)
show_img(label[0])
# show_img(mask[0] * 255)
show_img(G_d[0] * 255)
plt.show()
pbar.close()
start = time.time()
preds = self.net(tensor)[0]
if str(self.device).__contains__('cuda'):
torch.cuda.synchronize(self.device)
preds, boxes_list = decode(preds)
scale = (preds.shape[1] / w, preds.shape[0] / h)
if len(boxes_list):
boxes_list = boxes_list / scale
t = time.time() - start
return preds, boxes_list, t
if __name__ == '__main__':
import matplotlib.pyplot as plt
from utils.util import show_img, draw_bbox
os.environ['CUDA_VISIBLE_DEVICES'] = str('0')
model_path = 'output/PAN_shufflenetv2_FPEM_FFM.pth'
img_path = "/big_disk/evjeny/data/perimetry_cut_circles/0.jpg"
# 初始化网络
model = Pytorch_model(model_path, gpu_id=0)
preds, boxes_list, t = model.predict(img_path)
show_img(preds)
img = draw_bbox(cv2.imread(img_path)[:, :, ::-1], boxes_list)
# show_img(img, color=True)
# plt.show()
cv2.imwrite("result.jpg", img)
