SRGAN-tensorflow
SRGAN-tensorflow copied to clipboard
Tensorflow implementation of the SRGAN algorithm for single image super-resolution
Hi! I tried both on cpu and gpu for test_SRGAN.sh and inference_SRGAN.sh, but it is frozen at the step starting to evaluate, in which the data would be fed to...
I am reimplement the paper SRGAN in paddlepaddle, I should implement the pixelshuffle function. I dont understand the use of the phaseShift which u implement in https://github.com/brade31919/SRGAN-tensorflow/blob/de8d958186911ebd064e743e624e267a1d22405d/lib/ops.py#L107 Can u help...
I want to add some units in task SRGAN and those units contain new varibles both in generator and discriminator,when I trained SRGAN with the pre_trained model which is task...
Hi,I have a question when using perceptual loss, what kind of input data does the function VGG19_slim accept? elif FLAGS.perceptual_mode == 'VGG22': with tf.name_scope('vgg19_1') as scope: extracted_feature_gen = VGG19_slim(gen_output, FLAGS.perceptual_mode,...
Why do you normalize the low-resolution image to [0, 1] and the high-resolution image to [-1, 1] While feeding data into VGG network, should it be normalized to [0, 1]?
So I set up an instance with 16 cores, and 32GB RAM with Tesla P100. Anyways to increase training speed by editing the shell script for SRResNet and SRGAN? Right...
When testing, if I change the size of the input image, the test time on the GPU will be very long, do not change the size of the image, the...
Hello. Thanks for this great piece of software. I have an issue. I'm begining the training with: "python main.py --output_dir ./experiment_SRResnet/ --summary_dir ./experiment_SRResnet/log/ --mode train --is_training True --task SRResnet --batch_size...
#change return keras.layers.LeakyReLU(alpha=alpha).call(inputs) #to return tf.keras.layers.LeakyReLU(alpha=alpha).call(inputs)
When running the test script I get the following error message: Traceback (most recent call last): File "main.py", line 88, in FLAGS.crop_size = None [...] AttributeError: Flag --crop_size must be...