好的楼主，但是我在测试ctpn的train.py时使用了代码内自带的和我自己测试，都报出下面的错误：

[szzwy]

          好的楼主，但是我在测试ctpn的train.py时使用了代码内自带的测试集和我自己测试集，都报出下面的错误：

Traceback (most recent call last): File "/mnt/workspace/OCR-Invoice_Identification/train_code/ctpn_train_code/train.py", line 106, in out_cls, out_regr = model(imgs) File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, *kwargs) File "/mnt/workspace/OCR-Invoice_Identification/train_code/ctpn_train_code/ctpn/ctpn.py", line 127, in forward x = self.base_layers(x) File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(args, kwargs) File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, kwargs) File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/container.py", line 215, in forward input = module(input) File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(args, kwargs) File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 460, in forward return self._conv_forward(input, self.weight, self.bias) File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 456, in _conv_forward return F.conv2d(input, weight, bias, self.stride, RuntimeError: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [0]

是我环境的问题吗

_Originally posted by @szzwy in https://github.com/Cooduck/OCR-Invoice_Identification/issues/1#issuecomment-2076874191_

[Cooduck]

你好，我认为是数据集没能正确导入的问题。请检查图像维度是否正确，这可以在out_cls, out_regr = model(imgs)加上print(imgs.size())来看图像是否为[1, 3, hight, wide]，若不是，则说明输入的图像维度有问题，这可能需要在数据预处理或数据加载处做修改。

[szzwy]

好的，明天我重新装一下后试一下，楼主你的环境py、tf、pytroch、cuda是什么版本的呀

[Cooduck]

你好，我的环境分别是python:3.10，tensorflow:2.14.0，pytorch:1.13.1+cpu，没有安装cuda，我是用电脑cpu训练的。

[szzwy]

你好楼主，我换了个服务器，分别用无卡模式和3090跑，测试代码里自带的数据集没问题，换成我的数据集就报错了： Traceback (most recent call last): File "train.py", line 86, in for batch_i, (imgs, clss, regrs) in enumerate(dataloader): File "/root/miniconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 631, in next data = self._next_data() File "/root/miniconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1346, in _next_data return self._process_data(data) File "/root/miniconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1372, in _process_data data.reraise() File "/root/miniconda3/lib/python3.8/site-packages/torch/_utils.py", line 705, in reraise raise exception ValueError: Caught ValueError in DataLoader worker process 0. Original Traceback (most recent call last): File "/root/miniconda3/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop data = fetcher.fetch(index) # type: ignore[possibly-undefined] File "/root/miniconda3/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/root/miniconda3/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/root/OCR-Invoice_Identification/train_code/ctpn_train_code/ctpn/dataset.py", line 104, in getitem [cls, regr] = cal_rpn((h, w), (int(h / 16), int(w / 16)), 16, gtbox) File "/root/OCR-Invoice_Identification/train_code/ctpn_train_code/ctpn/utils.py", line 144, in cal_rpn anchor_argmax_overlaps = overlaps.argmax(axis=1) ValueError: attempt to get argmax of an empty sequence

我分别打开了自带的和我自己的标注json文件，我这样的json文件是不是有问题应该换一个标注软件？

[Cooduck]

你好，不好意思，昨日有点忙，没能及时回复你。你的json文件没有问题，但由于你json文件里的标注框（即第二张图片中points的内容）给出的是四个点，而本项目的json文件的标注框只有两点，所以你需要修改dataset.py中readxml函数中x2, y2 = points[1]，把其修改为x2, y2 = points[2]，即确保读入的标注框坐标为左上角和右下角两点。

[szzwy]

感谢楼主您在忙碌之中抽空回复，根据楼主的提示修改已经成功了！非常感谢！: ) ![Uploading screenshot-1714293824590.png…]()

有一个问题是跑完之后貌似有什么缓存之类的东西没有自动删除，我的磁盘空间快爆满了T_T

[szzwy]

楼主我OK了，找到服务器里的缓存文件了 ：）