generative-compression
generative-compression copied to clipboard
TensorFlow Implementation of Generative Adversarial Networks for Extreme Learned Image Compression
Hi Justin, May I ask if I can train this model on RTX 3090 GPU? It seems that tensorflow1.8 doesn't work properly on RTX3090. Sincerely, Zihang
Do you have Arithmetic codes for this one?
Hello! I've found a performance issue in your project: `batch()` should be called before `map()`, which could make your program more efficient. Here is [the tensorflow document](https://tensorflow.google.cn/guide/data_performance?hl=zh_cn#vectorized_mapping) to support it....
Hello,[this issue](https://github.com/Justin-Tan/generative-compression/issues/43) shows the reason that I commit this PR. I sincerely wish my PR will help you.And if you think my PR has a little work,Hoping you could merge...
Hello,I found a performance issue in the definition of `load_dataset` , data.py, [dataset = dataset.map(_parser)](https://github.com/Justin-Tan/generative-compression/blob/38d34c8538360dc350f935da0fb1caa0b346688d/data.py#L77) was called without **num_parallel_calls**. I think it will increase the efficiency of your program if...
1. I found that you have used "tf.stop_gradient()" to deal with the nondifferentiable properties of "tf.argmin()", "tf.round()". However, "tf.stop_gradient()" is used to ignore the gradient contirbution of present node, which...
This is my first use HDF5 dataset in neural network and I am clueless about how to generate the file with required format. Could anyone offer a example code about...
Hi there, first of all, thanks a lot for your reimplementation on the paper! I wanted to see how it works on compressing an image of mine. I downloaded the...
tensorflow.python.framework.errors_impl.NotFoundError: data/leftImg8bit/train/bochum/bochum_000000_023435_leftImg8bit.png; No such file or directory
Training on dataset ADE20k Building computational graph ... Training on ADE20k Training on ADE20k Sampling noise... Traceback (most recent call last): File "/home/tq/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1567, in _create_c_op c_op = c_api.TF_FinishOperation(op_desc)...