PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector

Traceback (most recent call last): File "train.py", line 66, in train(train_img_path, train_gt_path, pths_path, batch_size, lr, num_workers, epoch_iter, save_interval) File "train.py", line 35, in train for i, (img, gt_score, gt_geo, ignored_map) in enumerate(train_loader): File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 637, in next return self._process_next_batch(batch) File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 658, in _process_next_batch raise batch.exc_type(batch.exc_msg) TypeError: function takes exactly 5 arguments (1 given)

How can I fix it?

你好，我想请教下，你有试过使用ResNet50或者ResNeXt等作为backbone吗，比起VGG16这些网络的效果应该会更好吧？ 另外，我想请问下，你复现的EAST是否用到一些trick，比起 @argman 的https://github.com/argman/EAST performance还提升了一些。 非常感谢！

Hi dear @SakuraRiven, great thanks for your practical re-implement. It's much more clearer than the other version.

I wanna know why you're doing find_min_rect_angle? Are you doing something like finding a best-matched AABB (Axis Aligned Bounding Box) by rotating each BBOX? (like below)

THANKS in advance!

Hello，thanks for your shre！ I meet two questions need your help. When I trained AdvanceEAST by Keras, it process quickly and result is accuracy. However. I trained slowly by your project and result is not accuracy. About 3500 images with input train. double 1080Ti spend 24 hours. But AdvanceEAST spend 1 hours.

C:\Users\Adnan\AppData\Local\Programs\Python\Python35\python.exe C:/Users/Adnan/EAST/train.py C:\Users\Adnan\AppData\Local\Programs\Python\Python35\lib\site-packages\torch\optim\lr_scheduler.py:82: UserWarning: Detected call of lr_scheduler.step() before optimizer.step(). In PyTorch 1.1.0 and later, you should call them in the opposite order: optimizer.step() before lr_scheduler.step(). Failure to do this will result in PyTorch skipping the first value of the learning rate schedule.See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate "https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate", UserWarning) Traceback (most recent call last): File "C:/Users/Adnan/EAST/train.py", line 66, in train(train_img_path, train_gt_path, pths_path, batch_size, lr, num_workers, epoch_iter, save_interval) File "C:/Users/Adnan/EAST/train.py", line 35, in train for i, (img, gt_score, gt_geo, ignored_map) in enumerate(train_loader): File "C:\Users\Adnan\AppData\Local\Programs\Python\Python35\lib\site-packages\torch\utils\data\dataloader.py", line 819, in next return self._process_data(data) File "C:\Users\Adnan\AppData\Local\Programs\Python\Python35\lib\site-packages\torch\utils\data\dataloader.py", line 846, in _process_data data.reraise() File "C:\Users\Adnan\AppData\Local\Programs\Python\Python35\lib\site-packages\torch_utils.py", line 369, in reraise raise self.exc_type(msg) ValueError: Caught ValueError in DataLoader worker process 0. Original Traceback (most recent call last): File "C:\Users\Adnan\AppData\Local\Programs\Python\Python35\lib\site-packages\torch\utils\data_utils\worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "C:\Users\Adnan\AppData\Local\Programs\Python\Python35\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "C:\Users\Adnan\AppData\Local\Programs\Python\Python35\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "C:\Users\Adnan\EAST\dataset.py", line 385, in getitem vertices, labels = extract_vertices(lines) File "C:\Users\Adnan\EAST\dataset.py", line 365, in extract_vertices vertices.append(list(map(int, line.rstrip('\n').lstrip('\ufeff').split(',')[:8]))) ValueError: invalid literal for int() with base 10: '555'

I'm not sure whether it's a bug or just difference in variable naming In loss.py, you define the width and height of the union box as:

w_union = torch.min(d3_gt, d3_pred) + torch.min(d4_gt, d4_pred)
h_union = torch.min(d1_gt, d1_pred) + torch.min(d2_gt, d2_pred)

while in original paper it is: wi= min(d2_gt,d2_pred) + min(d4_gt,d4_pred) hi= min(d1_gt,d1_pred) + min(d3_gt,d3_pred)

Could you please clarify?

I train the network from vgg16_bn-6c64b313.pth and eval it, got Calculated!{"precision": 0.7974987974987975, "recall": 0.79826673086182, "hmean": 0.7978825794032723, "AP": 0} in save/model_epoch_600.pth

BTW, I eval the east_vgg16.pth get your original score: Calculated!{"precision": 0.8435782108945528, "recall": 0.8127106403466539, "hmean": 0.8278567925453654, "AP": 0} So, I used the right code and model.

What's wrong in there? Should I use earlier epoch?

Yours, Neo

您好，谢谢您的工作。 我想问一下关于网络输出的部分： loc = self.sigmoid2(self.conv2(x)) * self.scope 1.这里self.scope的值是输入图片的尺寸512，对吗？ 2.self.scope如果是输入图片的尺寸，那么self.sigmoid2(self.conv2(x))的值应该很小对吗，比如都是0-0.1之间的值，有可能更小，这对训练回归影响大吗？

期待您的回复，谢谢！

Hi SakuraRiven, I have cloned your repository and try to run eval.py file, it outputs precision 0.014, recall 0.8574 and hmean 0.028. It is so strange to me, do you have any comment?

thanks for your clean code. but i doubt that if there is something wrong in crop_img() function or not : after while() loop, if cnt == 1000(flag==True), then there are still some vertices that are outside of the cropped img, these wrong ones should be removed from 'new_vertices' ? another question: suppose that after while() loop, if cnt <1000(flag==False), which means that all vertices are not cross-crop-boundry, but they don't include vertices whose label==0, because you just vertify vertices whose label==1. so if you train with ignored, the valid vertices may be not matched with the cropped img. waiting for your comment.

Traceback (most recent call last): File "train.py", line 66, in train(train_img_path, train_gt_path, pths_path, batch_size, lr, num_workers, epoch_iter, save_interval) File "train.py", line 38, in train pred_score, pred_geo = model(img) File "C:\Users\Tony\anaconda3\envs\EAST\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Tony\PycharmProjects\EAST\model.py", line 168, in forward return self.output(self.merge(self.extractor(x))) File "C:\Users\Tony\anaconda3\envs\EAST\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Tony\PycharmProjects\EAST\model.py", line 73, in forward x = m(x) File "C:\Users\Tony\anaconda3\envs\EAST\lib\site-packages\torch\nn\modules\module.py", line 489, in call result = self.forward(*input, **kwargs) File "C:\Users\Tony\anaconda3\envs\EAST\lib\site-packages\torch\nn\modules\batchnorm.py", line 76, in forward exponential_average_factor, self.eps) File "C:\Users\Tony\anaconda3\envs\EAST\lib\site-packages\torch\nn\functional.py", line 1623, in batch_norm training, momentum, eps, torch.backends.cudnn.enabled RuntimeError: CUDA out of memory. Tried to allocate 1.50 GiB (GPU 0; 6.00 GiB total capacity; 4.64 GiB already allocated; 0 bytes free; 516.50 KiB cached)

How to do RGBA support with png images ?

If dataset contains alpha channel. Its impossible to use for now. Then im using jpg file format.

However, my dataset has transparent background so can you make it happen ? :))

Error!ting 2304 image
The sample res_5350037-2005-0001-0808_scale(0.5) not present in GT

eval time is 705.596533536911

I cannot understand this error That file exists in gt.zip file and res file in submit but still this error occurred

Traceback (most recent call last):
  File "train.py", line 66, in <module>
    train(train_img_path, train_gt_path, pths_path, batch_size, lr, num_workers, epoch_iter, save_interval)	
  File "train.py", line 35, in train
    for i, (img, gt_score, gt_geo, ignored_map) in enumerate(train_loader):
  File "/home/***/miniconda3/envs/gpu38/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 530, in __next__
    data = self._next_data()
  File "/home/***/miniconda3/envs/gpu38/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1204, in _next_data
    return self._process_data(data)
  File "/home/***/miniconda3/envs/gpu38/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1250, in _process_data
    data.reraise()
  File "/home/***/miniconda3/envs/gpu38/lib/python3.8/site-packages/torch/_utils.py", line 457, in reraise
    raise exception
ZeroDivisionError: Caught ZeroDivisionError in DataLoader worker process 4.
Original Traceback (most recent call last):
  File "/home/***/miniconda3/envs/gpu38/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/***/miniconda3/envs/gpu38/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/***/miniconda3/envs/gpu38/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/***/EAST/dataset.py", line 389, in __getitem__
    img, vertices = crop_img(img, vertices, labels, self.length)
  File "/home/***/EAST/dataset.py", line 221, in crop_img
    flag = is_cross_text([start_w, start_h], length, new_vertices[labels==1,:])
  File "/home/***/EAST/dataset.py", line 181, in is_cross_text
    if 0.01 <= inter / p2.area <= 0.99:
ZeroDivisionError: float division by zero

Why is this error occurred?? I checked my custom dataset again and again, but no difference is shown with sample ICDAR dataset...

+) Exception was handled, but I don't think it's valid because it's a temporary method

@SakuraRiven For how many epochs did you train the pretrained model ? And how did you decide which checkpoint to use? based on the average loss per epoch?