update readme

README.md

@@ -11,7 +11,7 @@ You can actually train them and reproduce the performance... not just to see how
 + [InceptionV3 on ImageNet](examples/Inception/inceptionv3.py)
 + [Fully-convolutional Network for Holistically-Nested Edge Detection](examples/HED)
 + [Spatial Transformer Networks on MNIST addition](examples/SpatialTransformer)
-+ [Generative Adversarial Networks](examples/GAN)
++ [Deep Convolutional Generative Adversarial Networks](examples/GAN)
 + [DQN variants on Atari games](examples/Atari2600)
 + [Asynchronous Advantage Actor-Critic(A3C) with demos on OpenAI Gym](examples/OpenAIGym)
 + [char-rnn language model](examples/char-rnn)

examples/DoReFa-Net/README.md

@@ -3,7 +3,7 @@ Code and model for the paper:
 [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](http://arxiv.org/abs/1606.06160), by Zhou et al.
 
 We hosted a demo at CVPR16 on behalf of Megvii, Inc, running a real-time 1/4-VGG size DoReFa-Net on ARM and half-VGG size DoReFa-Net on FPGA.
-We're not planning to release those runtime bit-op libraries for now. In these examples, bit operations are run in float32.
+We're not planning to release those runtime bit-op libraries for now. In this repo, bit operations are run in float32.
 
 Pretrained model for 1-2-6-AlexNet is available at
 [google drive](https://drive.google.com/a/%20megvii.com/folderview?id=0B308TeQzmFDLa0xOeVQwcXg1ZjQ).

examples/GAN/DCGAN-CelebA.py

@@ -126,7 +126,7 @@ def sample(model_path):
         o = o[:,:,:,::-1]
         viz = next(build_patch_list(o, nr_row=10, nr_col=10, viz=True))
 
-def interp(model_path):
+def vec(model_path):
     func = OfflinePredictor(PredictConfig(
        session_init=get_model_loader(model_path),
        model=Model(),
@@ -149,7 +149,7 @@ if __name__ == '__main__':
     parser.add_argument('--gpu', help='comma separated list of GPU(s) to use.')
     parser.add_argument('--load', help='load model')
     parser.add_argument('--sample', action='store_true', help='run sampling')
-    parser.add_argument('--interp', action='store_true', help='run interpolation')
+    parser.add_argument('--vec', action='store_true', help='run vec arithmetic demo')
     parser.add_argument('--data', help='`image_align_celeba` directory of the celebA dataset')
     global args
     args = parser.parse_args()
@@ -157,8 +157,8 @@ if __name__ == '__main__':
         os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
     if args.sample:
         sample(args.load)
-    elif args.interp:
-        interp(args.load)
+    elif args.vec:
+        vec(args.load)
     else:
         assert args.data
         config = get_config()

examples/GAN/README.md

@@ -2,7 +2,9 @@
 
 Reproduce DCGAN following the setup in [dcgan.torch](https://github.com/soumith/dcgan.torch).
 
-Samples from CelebA dataset:
+Play with the [pretrained model](https://drive.google.com/drive/folders/0B9IPQTvr2BBkLUF2M0RXU1NYSkE?usp=sharing) on CelebA face dataset.
+
+Generated samples:
 
 ![sample](demo/CelebA-samples.jpg)
 

examples/README.md

@@ -11,6 +11,7 @@ Training examples with __reproducible__ and meaningful performance.
 + [ResNet for ImageNet/Cifar10/SVHN](ResNet)
 + [Holistically-Nested Edge Detection](HED)
 + [Spatial Transformer Networks on MNIST addition](SpatialTransformer)
-+ [DisturbLabel, because I don't believe the paper](DisturbLabel)
++ [Generative Adversarial Networks](GAN)
++ [DisturbLabel -- I don't believe the paper](DisturbLabel)
 + Reinforcement learning (DQN, A3C) on [Atari games](Atari2600) and [demos on OpenAI Gym](OpenAIGym).
 + [char-rnn for fun](char-rnn)