bluemoon

If a decoder was added, will it work better?

1

这个实现在 encoder之后直接用 tf.image.resize_bilinear 把 (None, 16, 16, 5)的tensor转为 (None, 256, 256, 5), 16倍还原，，用deeplabv3 paper的解码器，分两次4倍还原会不会更好呢。。

there are some formula details in the Supplementary Material I can't understand, maybe others have the same problem

3

Q1：what is the **k** ?  I think it should be written as **w**, am i getting it right ?  --- Q2: what is the p, k in filter...

About the prediction mode. Are all the training processes in this article under "prediction-only" mode? is there any other prediction mode?

2

if we use and train the model in a "prediction-only" mode by setting Kt = 0, the PhyCell can not see any information of image. **Is this inappropriate?** --- I...

Is there a parenthesis missing here?

1

Is there a parenthesis missing here?  is the correct formula should be like this? 

about environment

5

I use these environment: 1) docker pull bitnami/mxnet:1.8.0-debian-10-r188 2) docker pull bitnami/mxnet:1.6.0 3) pip install mxnet 4) pip install mxnet-cu100 ... to run these code: ```python import sys sys.path.append('/mount/home/bluemoon/nas_194/repos-read/') from...

训练文件train.py可以开源吗？

18

您好，请问训练文件train.py会开源吗？