decoli
decoli
The same problem.
> Just find out that you have to install the CoCO API. > > cd data > > git clone https://github.com/pdollar/coco.git cd coco/PythonAPI > > make > > cd ../../.....
same problem
> Hi ty for your tutorial. But I can't figure out why sometimes tensors have shape (input_size, hidden_size) and sometimes (hidden_size, hidden_size) I have the same question.
同求，好人一生平安
我也觉得有点奇怪... 因为**sknet.py**中， 在`if __name__=='__main__':` 实际上只运行了 `class SKConv(nn.Module):` 并没有涉及到 `class SKUnit(nn.Module):` 和 `class SKNet(nn.Module):` 我个人觉得， `class SKConv(nn.Module):` 其实就是**SKNet**的精髓了...
Thanks for your reply. I guess...before actual use of **gpuarray.dot()**, I can call it for the kernels being compiled, like code: ``` ... gpuarray.dot(like_coef_gpu, like_image_gpu) # just for the kernels...
Oh... I found **gpuarray.dot()** is different from **numpy.dot()**. It seems that ``` import skcuda.linalg as linalg linalg.dot() ``` can be regarded as a package that can run on the GPU...
Maybe my understanding is wrong, but I think it should be like this: ``` ... recs = [] precs = [] ... ... recs += [rec] precs += [prec] ......
> Hi, version of colab is PyTorch1.5.0, I modified detection.py and ssd.py. > so that it works without warning and error. > > Since detection.py have torch.autograd.Function, I delete def...