xlhuang

Results 7 comments of xlhuang

RuntimeError: cannot reshape tensor of 0 elements into shape [0, -1] because the unspecified dimension size -1 can be any value and is ambiguous

我也遇到了这个问题，后来发现也是在loc2box的函数中，在计算dw，dh的时候出现了除0情况，发现是数据的问题，里面有些bbox是线和点，过滤一遍后就没了

RuntimeError: cannot reshape tensor of 0 elements into shape [0, -1] because the unspecified dimension size -1 can be any value and is ambiguous

> > 我也遇到了这个问题，后来发现也是在loc2box的函数中，在计算dw，dh的时候出现了除0情况，发现是数据的问题，里面有些bbox是线和点，过滤一遍后就没了 > > 请问可以说一下是怎么处理的吗？我也遇到同样的问题了 就是用bbox的坐标判断一下是否是一个矩形，不是就去掉

RuntimeError: cannot reshape tensor of 0 elements into shape [0, -1] because the unspecified dimension size -1 can be any value and is ambiguous

> 我换用torchvision的vgg16权重测试没有问题了，可能是caffe权重的问题。。。反正将就着用把先 ok，我用的数据集是coco，没用过voc，可能还是问题的原因不一样

Why gt_boxes all 1 in testing?

> I run test_net.py and got all 0 results. I have checked all the related issue and nothing could be done. I notice that in roibatchLoader.py, gt_boxes are make all...

compute capability mismatch for device 0: wanted 7.5, have 8.6

I tried these commands ``` git clone https://github.com/src-d/kmcuda cd src cmake -DCMAKE_BUILD_TYPE=Release -D DISABLE_R-y -D CUDA_ARCH=86 . && make ``` and got this ``` nvcc fatal : Value 'sm_86' is...

全参数精调 [launch.py:315:sigkill_handler] Killing subprocess

> ### Is there an existing issue for this? > * [x] I have searched the existing issues > > ### Current Behavior > > 7张24G的显卡 ![image](https://user-images.githubusercontent.com/11456239/259295223-40f1a478-f807-42ce-8b42-f5ac25632223.png) > > ###...

[BUG/Help] <lora微调遇到报错：RuntimeError: Subtraction, the `-` operator, with a bool tensor is not supported. If you are trying to invert a mask, use the `~` or `logical_not()` operator instead.>

> > ### Is there an existing issue for this? > > > > * [x] I have searched the existing issues > > > > ### Current Behavior >...