remove inceptionv3

examples/Inception/inception-bn.py

@@ -16,6 +16,7 @@ from tensorpack.utils.gpu import get_nr_gpu
 
 from imagenet_utils import fbresnet_augmentor, get_imagenet_dataflow
 
+# Change them if using different number of GPUs.
 TOTAL_BATCH_SIZE = 64 * 6
 NR_GPU = 6
 BATCH_SIZE = TOTAL_BATCH_SIZE // NR_GPU

examples/README.md

@@ -22,7 +22,7 @@ See [Unawareness of Deep Learning Mistakes](https://medium.com/@ppwwyyxx/unaware
 |	[Train Faster-RCNN / Mask-RCNN on COCO](FasterRCNN)				|	reproduce paper		|
 | [DoReFa-Net: training binary / low-bitwidth CNN on ImageNet](DoReFa-Net) | reproduce paper |
 | [Generative Adversarial Network(GAN) variants](GAN), including DCGAN, InfoGAN, <br/> Conditional GAN, WGAN, BEGAN, DiscoGAN, Image to Image, CycleGAN | visually reproduce |
-| [Inception-BN and InceptionV3](Inception) | reproduce reference code |
+| [Inception-BN](Inception) | reproduce reference code |
 | [Fully-convolutional Network for Holistically-Nested Edge Detection(HED)](HED) | visually reproduce |
 | [Spatial Transformer Networks on MNIST addition](SpatialTransformer) | reproduce paper |
 | [Visualize CNN saliency maps](Saliency) | visually reproduce |