ikalista
ikalista
> It should be a bug of skimage.rescale. same problem here: https://github.com/YadiraF/PRNet/pull/154#issue-329571724 关于 ``` if max_size> 1000: image = rescale(image, 1000./max_size) image = (image*255).astype(np.uint8) ``` 可能出现的问题 The rescale algorithm will...
REALLY helpful! I was wondering why the number of channels of the image was reduced from 3 to 2 after the rescale()  and your suggestion works 
The code will download the dataset by itself (line 23-27) from tflearn.datasets import cifar10 (X, Y), (X_test, Y_test) = cifar10.load_data() X, Y = shuffle(X, Y) Y = to_categorical(Y, nb_classes=10) Y_test...
Same problem and I've confirmed several times that I have Microsoft Visual C++ 14.0  So I guess that's not the problem. Does this have to run on Linux?
I have a very evil method you can say try it, I'm getting a recompile with -fPIC error, then I solved it by doing this #59 . RUN: find /...
> Your gcc version is very old and I think that's the rootcause but I'm honestly not sure. I'm building from Dockerfile-cuda The curl in the [nvidia/cuda:12.2.0-devel-ubuntu22.04] seemed to have...