Hao comments

Results 146 comments of

Hao

valueerror :no variables to optimize.

please report your environment - tf , tl, python version

valueerror :no variables to optimize.

I cannot found the reason, could you update TF and TL to the latest version and have a try again?

Your hardware + GPU setup for training and average time to complete training

Hi, I am using Titan X Pascal, 32GB RAM. I think 1080 Ti should be ok ~~ It is unnormal to wait 10 mins to let it start to train....

Your hardware + GPU setup for training and average time to complete training

`SubpixelConv2d` takes long time to compile, but it is a important part in the original paper. However, if you like, you can use resize-convolution i.e. use `UpSamplingLayer` and `Conv2d` instead...

OOM with 11GB of ram

1080 should be enough Sent from Netease Mail On 04/18/2018 17:58, andreas wrote: How large does my GPU have to be to run the SRGAN? — You are receiving this...

for model, add two more sub-pixel convolutional layers. for data, down-sampled the images by 8

add more subpixel blocks? https://github.com/tensorlayer/srgan/blob/master/model.py#L31

resources exhausted

I see, this way could help: use the method in the following link to load images for each batch instead of reading the entire dataset into the RAM at the...

Bugs and suggestions

I see, this way could help: use the method in the following link to load images for each batch instead of reading the entire dataset into the RAM at the...

where is 'easydict' and 'joblib' module

install it

Input shape axis 0 must equal 4, got shape [3]

``` Epoch: [0/20] step: [187/2] time: 0.309s, mse: 0.003 (218, 178)