DCGAN
DCGAN copied to clipboard
tensorlayer
The Simplest DCGAN Implementation
Hello! I've found a performance issue in /data.py: `ds.batch(batch_size)`[(here)](https://github.com/tensorlayer/dcgan/blob/f1c0b9d5e2b6c07f0c13c69e96513a6f149da8e0/data.py#L52) should be called before `ds.map(_map_fn, num_parallel_calls=4)`[(here)](https://github.com/tensorlayer/dcgan/blob/f1c0b9d5e2b6c07f0c13c69e96513a6f149da8e0/data.py#L51), 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....
I would like to train on an existing saved checkpoint but it seems the GAN learn from scratches. Is there some way to load a existing checkpoint ? Thanks in...
I have this error! can you help me, please? WARNING: Logging before flag parsing goes to stderr. I0718 14:45:17.243686 140030963623808 tl_logging.py:99] [!] checkpoint exists ... I0718 14:45:17.247771 140030963623808 tl_logging.py:99] [!]...
Hi Does any one know how to generate new images? There is no file to test the images and generate samples. Thanks in advance
@zsdonghao How can i use discriminator layers to take a vector of features for every image in own dataset not celeba?. As paragraph 5.1 in "UNSUPERVISED REPRESENTATION LEARNING WITH DEEP...
I can't seem to understand the error I am getting while running the main.py Use `tf.global_variables_initializer` instead. Traceback (most recent call last): File "D:\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1139, in _do_call return fn(*args)...
