inception name

examples/Inception/inceptionv3.py

@@ -23,6 +23,7 @@ This config follows the official inceptionv3 setup (https://github.com/tensorflo
 with much much fewer lines of code.
 It reaches 74.5% single-crop validation accuracy, slightly better than the official code,
 and has the same running speed as well.
+The hyperparameters here are for 8 GPUs, so the effective batch size is 8*64 = 512.
 """
 
 BATCH_SIZE = 64

examples/README.md

@@ -9,6 +9,6 @@ Examples with __reproducible__ and meaningful performance.
 + [char-rnn for fun](char-rnn)
 + [DisturbLabel, because I don't believe the paper](DisturbLabel)
 + [DoReFa-Net: binary / low-bitwidth CNN on ImageNet](DoReFa-Net)
-+ [GoogleNet-InceptionV1 with 71% accuracy](Inception/inception-bn.py)
-+ [GoogleNet-InceptionV3 with 74.5% accuracy (similar to the official code)](Inception/inceptionv3.py)
++ [Inception-BN with 71% accuracy](Inception/inception-bn.py)
++ [InceptionV3 with 74.5% accuracy (similar to the official code)](Inception/inceptionv3.py)
 + [ResNet for Cifar10 and SVHN](ResNet)