反卷积层不接受带有双线性填充的 5D blob

debugcn 发表于 Dev

用户4911648

有没有人有解决这个问题的方法？任何其他可能类似的填充选项？还是我应该省略填充重量选项？

用户4911648

我已经调整了文件github，以便它对 5D blob 执行双线性填充：

def upsample_filt(size):
        """
        Make a 2D bilinear kernel suitable for upsampling of the given (h, w) size.
        """
        factor = (size + 1) // 2
        if size % 2 == 1:
            center = factor - 1
        else:
            center = factor - 0.5
        og = np.ogrid[:size, :size, :size]

        return (1 - abs(og[0] - center) / factor) * \
               (1 - abs(og[1] - center) / factor) * \
               (1 - abs(og[2] - center) / factor)

def interp(net, layers):
    """
    Set weights of each layer in layers to bilinear kernels for interpolation.
    """
    for l in layers:
        m, k, d, h, w = net.params[l][0].data.shape

        if m != k and k != 1:
            print('input + output channels need to be the same or |output| == 1')
            raise
        if h != w or h != d or w != d:
            print('filters need to be square')
            raise
        filt = upsample_filt(h)
        net.params[l][0].data[range(m), range(k), :, :, :] = filt


caffe.set_device(0)
caffe.set_mode_gpu()

solver = caffe.SGDSolver('solver.prototxt')

# surgeries
interp_layers = [k for k in solver.net.params.keys() if 'Deconv' in k]
interp(solver.net, interp_layers)

#print(interp_layers)

solver.solve();

本文收集自互联网，转载请注明来源。

如有侵权，请联系[email protected] 删除。