improved-gan
improved-gan copied to clipboard
openai
Code for the paper "Improved Techniques for Training GANs"
IMO，there are tow ways to calculate Inception score of conditional GANs. 1. For every "condition", calculate a IS and Average them. 2. Sample "condition" from "real condition distribution" and generate...
I'm hitting the error below when using using the code with a different generator and optimizer. Python3 and tensorflow 1.3.0. with any number between 2 or 4 gpus. The error...
The supervisied loss function used for mnist feature matching is [loss_lab = -T.mean(l_lab) + T.mean(z_exp_lab)](https://github.com/openai/improved-gan/blob/master/mnist_svhn_cifar10/train_mnist_feature_matching.py#L69) Why not use softmax loss function?
the readme seems not very specific.What file path should I edited? Download the dataset and set the file path in the code? Hope for help.
What is disc_param_avg used for here? Why its updates should be considered into parameters update. If gradients already be got by disc_param_updates, why couldn't we directly apply these gradients to...
Now I am trying to regenerate the best Inception score in the paper. It seems the default parameter setup of the cifar mininatch discrimination may not be the one used...
I don't see big differences before and after removing the extra 8 classes in the 1008 classes of inception model output, but I guess that should be done?
Hi, I've been trying to reproduce a minibatch discrimination GAN for MNIST based on the paper, but I keep getting poor results. Would it be possible for "train_mnist_minibatch_discrimination.py" to be...
In train_mnist_feature_matching.py and other similar files, the generator uses nn.batch_norm, but it seems your implementation `self.bn_updates = [(self.avg_batch_mean, new_m), (self.avg_batch_var, new_v)]` is not updated in the train_mnist_feature_matching.py. (I saw the...
