WAI-f

I tried morph net with grouplasso, but my trained network report error with layer normalization, how to solve it?

I installed keras 2.2.4 and tensorflow 1.14, if I tried like this: input = tf.ones((1, 256, 256, 32, 3), dtype=tf.float32) x = DepthwiseConv3D(kernel_size=(3, 3, 3), depth_multiplier=2)(input) the result is ok....

你好，我目前在研究拓扑优化方向，想向您请教一些问题，能否加个联系方式方便交流，我的电话/微信：15071194757。非常期待您的回复。

CLIP::ImgEncoder implement wrong?

1

imgdata[index] = r; imgdata[224 * 224 + index] = r; imgdata[224 * 224 * 2 + index] = r; 这里为什么三个通道都用r分量？