Ivan Lee
Ivan Lee
@rshah7924 you can just use the package by python. `>>> import zipfile >>> zf = zipfile.ZipFile('test.zip', mode='w') >>> zf.write('test.jpg') >>> zf.close() >>> exit()`
i have same problem >>>THC_API cudaError_t THCudaMalloc(THCState *state, void **ptr, size_t size)
i modify the code, isolate the relu in forward and back propagation the performance look like better ```py for i in range(len(images)): layer_0 = images[i:i+1] layer_1 = np.dot(layer_0,weights_0_1) # modify...
please follow this issue gyus -> https://github.com/meta-llama/llama/issues/380