TyrionChou

paper eq issue

3

In your paper，I think vt should be vi in eq.4, is it right?

hi~!when i use PerspectiveTransform，the fit_output is True, but i still have this picture! if i have some method to aviod the bounding box out of the picture? 

hi~, there are some problems at shrink_poly function in utils.py. for p in range(start, end + 1, r): res.append([p, int(k1 * p + b1), (p + 15), int(k1 * (p...

pretrain model

1

hi~, my csdn have not enough score， could you send me a pretrain model， my email is [email protected]， thank you very much！

InvalidArgumentError

1

作者好，我想问一下这个问题，如下： Caused by op u'attention_decoder/train_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits', defined at: File "train.py", line 171, in tf.app.run() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 126, in run _sys.exit(main(argv)) File "train.py", line 74, in main image_placeholder, groundtruth_text_placeholder, FLAGS.single_seq) File...

question about segmentation head

1

  Nice work!! i want to ask a question about above pic.M is mask_embed? if M is mask_embed, the formula is M(qc) ×（......）, not qc × M(......).Do I understand...

hi,there! when use dino to predict text box， i find that there is a overlapping problem because annotation（sometimes combine sometimes split）。Is there a solution? the picture like this！  this...

这是LCNetv2_base到LCNetv2_base_ShiTu的变化： from paddle.nn import Conv2D, Identity from ..legendary_models.pp_lcnet_v2 import MODEL_URLS, PPLCNetV2_base, RepDepthwiseSeparable, _load_pretrained __all__ = ["PPLCNetV2_base_ShiTu"] def PPLCNetV2_base_ShiTu(pretrained=False, use_ssld=False, **kwargs): """ An variant network of PPLCNetV2_base 1. remove ReLU layer...

No model hoster is available

2

### 🔎 Search before asking - [x] I have searched the PaddleOCR [Docs](https://paddlepaddle.github.io/PaddleOCR/) and found no similar bug report. - [x] I have searched the PaddleOCR [Issues](https://github.com/PaddlePaddle/PaddleOCR/issues) and found no...