falrom

I encountered the same problem when using the pretrained checkpoint.  I have no problem with my own retraining.

I haven't finished the training yet (about two days). If the test works, I will give you the ckpt. But I have some problems with the [BN layers](https://github.com/cameronfabbri/Underwater-Color-Correction/issues/5). So, emmm....I...

@cameronfabbri The fish picture above was processed by the pretrained checkpoint downloaded from the [project page](http://irvlab.cs.umn.edu/enhancing-underwater-imagery-using-generative-adversarial-networks). I retrained the network and got good results like this:  I don't know...

CPU : intel i7 7800X RAM : 32GB DDR4 GPU : GeForce GTX 1080Ti OS : Ubuntu 16.04 LTS

You can just assign the value to EXPERIMENT_DIR directly in the python code. ```python # EXPERIMENT_DIR = 'checkpoints/LOSS_METHOD_'+LOSS_METHOD\ # +'/NETWORK_'+NETWORK\ # +'/L1_WEIGHT_'+str(L1_WEIGHT)\ # +'/IG_WEIGHT_'+str(IG_WEIGHT)\ # +'/AUGMENT_'+str(AUGMENT)\ # +'/DATA_'+DATA+'/'\ EXPERIMENT_DIR =...

I know what you mean. I did not change their network structure. But I don't think they used the Tensorflow BN layer API in the right way.

@IPNUISTlegal 非要改动的话，只能把BN按照正确的方式重写了。只是发论文看效果的话我感觉不改问题也不大。 我没有改他的代码。我测了一下，大体上讲一张一张送进去（batch size=1）测试是效果比较好的（最接近他们论文的插图），而且一张一张送进去不会出现输出不稳定的情况。一个多张图片的batch送进去会导致不同的batch情况下，同一张图结果不同。

The same problem as you, "All authentication methods failed" And FileZilla works fine.

I can use the same key file to connect on FileZilla, or directly using SSH: ```bash ssh [email protected] -p 1922 -i /home/username/id_rsa -o HostKeyAlgorithms=+ssh-rsa -o PubkeyAcceptedKeyTypes=+ssh-rsa ``` My dart code...

Is there any way to specify `HostKeyAlgorithms` like in the SSH command? I tried modifying the values of the algorithms list, but it doesn't seem to work.