# model_path = 'output/psenet_icd2015_new_loss/final.pth'
image_root = 'Test Set/Image'
annotation_root = 'Test Set/Annotation'
Images = os.listdir(image_root)
Labels = os.listdir(annotation_root)
image_id = Images[np.random.randint(1, len(Images) + 1)].split('.jpg')[0]
img_path = image_root + os.sep + '{}.jpg'.format(image_id)
label_path = annotation_root + os.sep + '{}.txt'.format(image_id)
print('Predicting for image', img_path)
label = _get_annotation(label_path)
# 初始化网络
net = PSENet(backbone='resnet18', pretrained=False, result_num=config.n)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = Pytorch_model(model_path, net=net, scale=1, device=device)
# for i in range(100):
# models.predict(img_path)
preds, boxes_list, t = model.predict(img_path)
print(boxes_list)
show_img(preds)
img = draw_bbox(img_path, boxes_list, color=(0, 0, 255))
cv2.imwrite('result.jpg', img)
# img = draw_bbox(img, label,color=(0,0,255))
show_img(img, color=True)
plt.show()
if __name__ == '__main__':
import pathlib
from tqdm import tqdm
import matplotlib.pyplot as plt
from utils.utils import show_img, draw_bbox, save_result, get_file_list
args = init_args()
print(args)
# 初始化网络
model = DetModel(args.model_path, post_p_thre=args.thre, gpu_id=0)
img_folder = pathlib.Path(args.input_folder)
for img_path in tqdm(get_file_list(args.input_folder, p_postfix=['.jpg'])):
preds, boxes_list, score_list, t = model.predict(
img_path, is_output_polygon=args.polygon)
img = draw_bbox(cv2.imread(img_path)[:, :, ::-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)
save_result(output_path.replace('_result.jpg', '.txt'), boxes_list,
score_list, args.polygon)
from utils.utils import show_img
from tqdm import tqdm
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt
from torchvision import transforms
train_data = MyDataset(config.trainroot,
data_shape=config.data_shape,
n=config.n,
m=config.m,
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)
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()
if __name__ == '__main__':
import config
from model import CTPN_Model
import matplotlib.pyplot as plt
from utils.utils import show_img, draw_bbox, draw_anchor
# os.environ['CUDA_VISIBLE_DEVICES'] = str('2')
model_path = 'output/PSENet_298_loss0.001575.pth'
img_id = 1
img_path = 'D:/zj/dataset/ICD15/train/imgs/img_{}.jpg'.format(img_id)
# img_path = '0.jpg'
label_path = 'D:/zj/dataset/ICD15/train/gt/gt_img_{}.txt'.format(img_id)
label = _get_annotation(label_path)
# img_path = '/data1/gcz/拍照清单数据集_备份/87436979.jpg'
# 初始化网络
net = CTPN_Model(pretrained=False)
model = Pytorch_model(model_path, net=net, gpu_id=None)
# for i in range(100):
# model.predict(img_path)
boxes_list, t = model.predict(img_path)
print(boxes_list)
img = draw_bbox(img_path, boxes_list, color=(0, 0, 255))
cv2.imwrite('result.jpg', img)
# img = draw_bbox(img, label,color=(0,0,255))
show_img(img[:, :, ::-1], color=True)
plt.show()
img = draw_bbox(img_path, label)
cv2.imwrite(save_path, img)
return img
if __name__ == '__main__':
import torch
import utils.config_synthtext as config
from utils.utils import show_img
from tqdm import tqdm
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt
from torchvision import transforms
train_data = Synthtext(config.trainroot, data_shape=config.data_shape, n=config.n, m=config.m)
train_loader = DataLoader(dataset=train_data, batch_size=2, shuffle=False, num_workers=0)
pbar = tqdm(total=len(train_loader))
for i, (img, label, mask) in enumerate(train_loader):
print(label.shape)
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)*[0.229, 0.224, 0.225]+[0.485, 0.456, 0.406], color=True)
show_img(label[0])
show_img(mask[0])
plt.show()
break
pbar.close()
is_transform=True,
img_size=config.data_shape,
kernel_num=config.kernel_num,
min_scale=config.min_scale)
for i in range(len(train_data)):
img, kernel, mask = train_data[9]
# for i, (img, label, mask) in enumerate(train_data):
print(i)
print(kernel.shape)
print(img.shape)
print(kernel[0][-1].sum())
print(mask[0].sum())
show_img(((img.to(torch.float)).numpy().transpose(1, 2, 0) *
[0.229, 0.224, 0.225] + [0.485, 0.456, 0.406]),
color=True)
show_img(kernel)
show_img(mask)
plt.show()
break
# for i in trange(len(train_data)):
# img, kernel, mask = train_data[i]
# img = img.permute(1,2,0)
# img = img-img.min()
# img = img/img.max()*255
# img = img.data.cpu().numpy()
# img = img.astype('uint8')
# i=0
# cv2.imwrite('trash/img{}.png'.format(i), img)