Has anyone managed to reproduce the exact results for semi-supervised learning using train_cifar_feature_matching.py? With the default hyperparameters and 4000 labeled examples, I'm overfitting and getting 32% test error after 48 epochs. Getting 0.5% training error. Paper claims to get test error of only 18.6% on this task.

Do I need to train longer (for the full 1200 epochs?), or are others having this same problem?

on the calculation of inception score, after pool3 = sess.graph.get_tensor_by_name('pool_3:0'), I get pool3 with shape of [?, 2048], which makes the other line tf.matmul(tf.squeeze(pool3, [1, 2]), w) hard to understand. why do you need to squeeze pool3 ?

Fixing two errors that arise when running inception_score/model.py with tensorflow 1.6.0, presumably due to bit rot and deprecations in current tensorflow versions.

The first error is

ValueError: Tensor._shape cannot be assigned, use Tensor.set_shape instead.

Commit a851dc2 addresses this error by replacing _shape with set_shape.

After addressing this error, the second error is

ValueError: Shape must be rank 2 but is rank 1 for 'MatMul' (op: 'MatMul') with input shapes: [2048], [2048,1008].

Commit dff7439 addresses this error by retaining a singleton dimension in the squeeze operation.

Quoting Nicolas Carlini:

attack = FastGradientMethod(model, sess)
adv_1 = attack.generate_np(test_data, eps=.5)
adv_2 = attack.generate_np(test_data, eps=.2)

will result in adv_1 == adv_2, a rather unexpected result.

This is because generate_np just stores one TensorFlow graph. It needs to have something like a dictionary mapping from argument values to graphs.

Hi, could you please share your script train_imagenet.sh to launch training on ImageNet? It is mentioned in the ImageNet README, but is not present in the repo. Thanks!

Hi, I am getting this error when I run cifar_feature_matching or cifar_minibatch_discrimination but not when I run mnist. Please help.

Traceback (most recent call last):
  File "train_cifar_feature_matching.py", line 51, in <module>
    gen_dat = ll.get_output(gen_layers[-1])
  File "/usr/local/lib/python2.7/dist-packages/lasagne/layers/helper.py", line 185, in get_output
    all_outputs[layer] = layer.get_output_for(layer_inputs, **kwargs)
  File "/home/bmi/Downloads/improved-gan-master/mnist_svhn_cifar10/nn.py", line 120, in get_output_for
    op = T.nnet.abstract_conv.AbstractConv2d_gradInputs(imshp=self.target_shape, kshp=self.W_shape, subsample=self.stride, border_mode='half')
AttributeError: 'module' object has no attribute 'abstract_conv'

I see most code here is under the MIT License, but what is the copyright status for the paper published on Arxiv? Is it under any copyleft license?

I would love to upload and distribute it on my website, but cannot do so unless the copyright allows it.

I don't know if this question belongs here, but I am currently making a custom tf keras gan with feature matching loss and I am struggling to understand when to use inference mode on a model, that is, making use of training layers like dropout and updating batch norm parameters. This goes both for discriminator and generator as I understand that they should be trained separately.

hello, when I run the bash train_imagenet.sh, here is an issue: TRAINING train_imagenet.sh: line 5: 4668 Segmentation fault CUDA_VISIBLE_DEVICES=0 python train_${word}.py --dataset imagenet_train --is_train True --checkpoint_dir gan/checkpoint_${word} --image_size ${pixels} --is_crop True --sample_dir gan/samples_${word} --image_width ${pixels} --batch_size 16

I am trying to run the train_mnist_feature_matching.py code with python 3.5 but getting the error as below: File "[path]/lib/python3.5/site-packages/nn/tf.py", line 1, in from tensorflow import * AttributeError: 'module' object has no attribute 'absolute_import'

Is this a bug?