Open 541435721 opened 7 years ago
comparing your model.py with tf_unet/unet.py, i find that you just changed the names of conv2d and deconv2d. And the sizes of convolution kernels are never changed. Accrording to the official apis, the filter size of conv3d must be 5-D.
@541435721 yes, tensorflow-base implementation is work in progress. Chainer version can work now.
comparing your model.py with tf_unet/unet.py, i find that you just changed the names of conv2d and deconv2d. And the sizes of convolution kernels are never changed. Accrording to the official apis, the filter size of conv3d must be 5-D.