datawhalechina / dive-into-cv-pytorch Goto Github PK

xmin = int(bbox.find('xmin').text) - 1 ymin = int(bbox.find('ymin').text) - 1 xmax = int(bbox.find('xmax').text) - 1 ymax = int(bbox.find('ymax').text) - 1为什么要减1呢？原始图片左上角的坐标是从(0,0)开始吗

大家好，我是datawhale成员安晟，也是本项目《动手学CV-pytorch版》的组织者。经过CV小组几周的努力，我们初步完成了前两章内容的构建。内容涉及环境安装、pytorch基本使用、CNN基本概念，分类问题实战等较基础的知识点。

我们希望能够更好的发扬datawhale的开源精神，帮助到有决心有动力想要进入CV领域的入门者。同时，项目还处于初期阶段，不免会有各种不够完美的地方，因此非常希望听听大家的意见建议，尤其是入门学习者的声音。

如果你刚刚入门CV，或者正在参加我们组织的《零基础入门CV赛事- 街景字符编码识别》新人赛，非常希望大家将本项目的内容当作学习材料，并且把在学习中遇到的问题，发现的我们的教程不全面，不细致的部分指出，帮助我们更好的输出优质内容。

因此，我发布了本次活动：

• 大家可以在本issue下发表评论，指出你的意见和改进建议。点赞最多的两个评论将会获得我本人赞助的大红包一个或深度学习优质书籍一本~

• 同时，大家也可以评论指出你认为写的最好的章节，来支持内容创作者，同样获得认可(点赞)最多章节的主要作者也会获得我本人赞书的红包一个~

期待大家积极响应，活动截至时间2020/6/5日晚12点。
注：获得奖励的前提是评论必须为有建设性的意见和建议，恶意刷赞是禁止的。平票时将会由本项目组成员根据评论质量来决定奖品归属。

第二章2.1节第二部分最后一个代码块，开头import的时候少了一个r~
from torch.utils.data import DataLoade
ps. 感觉这部分写的很棒，也很清晰！

在2.1中的 读取示例2(示例1基础上附带数据增强)， 代码上面是custom_transform，下面是custom_transforms

D:\anaconda\envs\transformer_ocr\lib\site-packages\torch\nn_reduction.py:44: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
warnings.warn(warning.format(ret))

epoch 0
train...
D:\anaconda\envs\transformer_ocr\lib\site-packages\torch\nn_reduction.py:44: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
warnings.warn(warning.format(ret))
D:\anaconda\envs\transformer_ocr\lib\site-packages\torch\nn_reduction.py:44: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
warnings.warn(warning.format(ret))
D:\anaconda\envs\transformer_ocr\lib\site-packages\torch\nn_reduction.py:44: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
warnings.warn(warning.format(ret))
D:\anaconda\envs\transformer_ocr\lib\site-packages\torch\nn_reduction.py:44: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
warnings.warn(warning.format(ret))
Epoch Step: 1 Loss: 5.298872 Tokens per Sec: 69.338173
Traceback (most recent call last):
File "E:/pycharmproject/dive-into-cv-pytorch-master/dive-into-cv-pytorch-master/code/chapter06_transformer/6.2_recognition_by_transformer/ocr_by_transformer.py", line 341, in
train_mean_loss = run_epoch(train_loader, ocr_model, loss_compute, device)
File "E:/pycharmproject/dive-into-cv-pytorch-master/dive-into-cv-pytorch-master/code/chapter06_transformer/6.2_recognition_by_transformer/ocr_by_transformer.py", line 230, in run_epoch
for i, batch in enumerate(data_loader):
File "D:\anaconda\envs\transformer_ocr\lib\site-packages\torch\utils\data\dataloader.py", line 435, in next
data = self._next_data()
File "D:\anaconda\envs\transformer_ocr\lib\site-packages\torch\utils\data\dataloader.py", line 1085, in _next_data
return self._process_data(data)
File "D:\anaconda\envs\transformer_ocr\lib\site-packages\torch\utils\data\dataloader.py", line 1111, in _process_data
data.reraise()
File "D:\anaconda\envs\transformer_ocr\lib\site-packages\torch_utils.py", line 428, in reraise
raise self.exc_type(msg)
KeyError: Caught KeyError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "D:\anaconda\envs\transformer_ocr\lib\site-packages\torch\utils\data_utils\worker.py", line 198, in _worker_loop
data = fetcher.fetch(index)
File "D:\anaconda\envs\transformer_ocr\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:\anaconda\envs\transformer_ocr\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "E:\pycharmproject\dive-into-cv-pytorch-master\dive-into-cv-pytorch-master\code\chapter06_transformer\6.2_recognition_by_transformer\ocr_by_transformer.py", line 109, in getitem
gt.append(self.lbl2id_map[lbl])
KeyError: 'Â'

进程已结束,退出代码1

Hi, thanks for your significant work. Some bugs may not be found if you use markdown, so I was wondering if you could use jupyter notebook? Thanks!

实际图片如下图, 未加载不限于此小节, 前1.1节也碰到类似状况

每次在首页点击 Get started 都要在新的标签页中加载

gan章节的代码什么时候可以放出来啊

IoU intersection 的计算是不是不对