PaddleSeg

PaddleSeg copied to clipboard

[Hint: 'CUBLAS_STATUS_EXECUTION_FAILED'. The GPU program failed to execute. This is often caused by a launch failure of the kernel on the GPU, which can be caused by multiple reasons.

5

paddlepaddle-gpu 2.3.0.post110 run errror ``` File "/data/PaddleSeg-2.5/paddleseg/core/train.py", line 204, in train logits_list = ddp_model(images) if nranks > 1 else model(images) File "/data/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 930, in __call__ return self._dygraph_call_func(*inputs, **kwargs) File...

fanweiya

CrossEntropyWithSoftmaxCUDAKernel

1

欢迎您反馈PaddleSeg使用问题，辛苦您提供以下信息，方便我们快速定位和解决问题： 1. PaddleSeg版本：无 2. PaddlePaddle版本：PaddlePaddle 2.3.0 3. 操作系统信息：Windows10 4. Python版本号：Python3.6 5. CUDA/cuDNN版本：CUDA10.2/cuDNN 7.6.5 6. 完整的代码：(若修改过原代码，请提供修改前后代码对比） 7. 详细的错误信息、相关log：Traceback (most recent call last): File "G:/学习/飞桨学习课程/语义分割/case_pet_seg/Unet.py", line 163, in batch_size=2) File "C:\Program Files\Python36\lib\site-packages\paddle\hapi\model.py",...

cccrice

关于label维度和logit维度不一致的问题

2

在使用自己数据进行训练的时候，发现报错 [Hint: Expected labels_dims[axis] == 1UL, but received labels_dims[axis]:3 != 1UL:1.] 猜测是label图片读取的时候，通道数为3，查了下dataset.py和transforms.py的代码，在Compose这个类中，关于label图片的读取是 label = np.asarray(Image.open(label)) 改成 label = cv2.imwrite(label, cv2.IMREAD_GRAYSCALE) 此时报错解除，但不确定是否有效 不知道是我的图片的问题还是哪里不对

ww451575464

CrossEntropyLoss的weights设置后报错

2


YangQiangli

[Bug] 训练模型，报 No stack in paddle，may be caused by external reasons

2

--- 欢迎您反馈PaddleSeg使用问题，辛苦您提供以下信息，方便我们快速定位和解决问题： 1. PaddleSeg版本：（，PaddleSeg release/2.5） 2. PaddlePaddle版本：（PaddlePaddle 2.3.0_GPU） 3. 操作系统信息：（Linux） 4. Python版本号：（Python3.7） 5. CUDA/cuDNN版本：（ 如CUDA10.2/cuDNN 8.1) 训练模型出错:   用deploy/python/infer.py推理模型出错：  

huangwan-jiayi

[General Issue] 文档中关于数据增强的方式不明确

1

README_CN.md中没有找到明确的关于transforms内容和写法的说明，希望可以补充或者提供相关介绍页面。

Liyulingyue

[Feature Request] c++ inference?

7

Hi! Thanks for making this code available. It would be great to be able to run inference for segmentation and matting in c++, is this possible? Or planned for the...

antithing

Preloading Pseudo Labels in EISeg

1

Thanks for having the EISEG annotation tool which i felt was really useful! I have one question regarding the tool. Will there be any feature for us to pre-load annotations...

aqx95

统计模型flops和params

4

请问paddleseg如何统计模型的flops和params 我原来直接使用paddle.flops统计paddleclas里的模型是没问题的，但统计paddleseg模型时报错 "Your model must be an instance of paddle.nn.Layer or paddle.static.Program."

caomao1111

[General Issue] Getting test results for my data

4

Hi, After I trained my UNET I would like to get the results of Dice, Iou,Kappa etc. for the test data. But unfortunately I can not achieve this. The model...

Yasminbr