SRGAN-tensorflow icon indicating copy to clipboard operation
SRGAN-tensorflow copied to clipboard

Tensorflow implementation of the SRGAN algorithm for single image super-resolution

Results 40 SRGAN-tensorflow issues
Sort by recently updated
recently updated
newest added
trafficstars

I am trying to use SRGAN for increasing resolution of some artwork. However, the results I got are super blurry, basically it seems to be doing opposite of what I...

Hi, I got this issue while training SRGAN with perceptual loss Traceback (most recent call last): File "main.py", line 231, in Net = SRGAN(data.inputs, data.targets, FLAGS) File ".../SRGAN-tensorflow/lib/model.py", line 372,...

either, h, w = im.shape ValueError: too many values to unpack (expected 2) either runs well but no result. thanks

``` Traceback (most recent call last): File "main.py", line 168, in inference_data = inference_data_loader(FLAGS) File "/home/ubuntu/SRGAN-tensorflow/lib/model.py", line 210, in inference_data_loader image_LR = [preprocess_test(_) for _ in image_list_LR] File "/home/ubuntu/SRGAN-tensorflow/lib/model.py", line...

Ok, say I want to train SRGAN, not SRResnet, the checkpoint here points to ./experiment_SRGAN_MSE/model-500000 but it doesn't exist! Is it created when we finished training the SRResnet? I got...

First of all,thanks for your model! And there is a question:when I use my own png image,I found it didn't work as well as the default image,I thought maybe it...

Hello! I am trying to run the test_SRGAN.sh but I am getting an error. **tensorflow.python.framework.errors_impl.InternalError: Failed to create session.** I am running tensor flow 1.4.1 in virtualenv Any ideas where...

So i wanted to if it would be a good idea to first train the model on the dataset initially trained and then using those weights and selected hyperparameters to...

Added FLAGS(sys.argv) to parse flags and avoid the error: ERROR:root:Trying to access flag --mode before flags were parsed.

Hello authors, I think SRGAN is somewhat in line with my research, and I would like to modify the functionality of SRGAN so that it can generate larger-scale images instead...