Typo Fix (#6017)
This commit is contained in:
parent
3dd5fc88f7
commit
fa4c747b7e
@ -91,7 +91,7 @@ else:
|
|||||||
horizontal_flip=True, # randomly flip images
|
horizontal_flip=True, # randomly flip images
|
||||||
vertical_flip=False) # randomly flip images
|
vertical_flip=False) # randomly flip images
|
||||||
|
|
||||||
# Compute quantities required for featurewise normalization
|
# Compute quantities required for feature-wise normalization
|
||||||
# (std, mean, and principal components if ZCA whitening is applied).
|
# (std, mean, and principal components if ZCA whitening is applied).
|
||||||
datagen.fit(x_train)
|
datagen.fit(x_train)
|
||||||
|
|
||||||
|
@ -222,7 +222,7 @@ if __name__ == '__main__':
|
|||||||
noise = np.random.uniform(-1, 1, (2 * batch_size, latent_size))
|
noise = np.random.uniform(-1, 1, (2 * batch_size, latent_size))
|
||||||
sampled_labels = np.random.randint(0, 10, 2 * batch_size)
|
sampled_labels = np.random.randint(0, 10, 2 * batch_size)
|
||||||
|
|
||||||
# we want to train the genrator to trick the discriminator
|
# we want to train the generator to trick the discriminator
|
||||||
# For the generator, we want all the {fake, not-fake} labels to say
|
# For the generator, we want all the {fake, not-fake} labels to say
|
||||||
# not-fake
|
# not-fake
|
||||||
trick = np.ones(2 * batch_size)
|
trick = np.ones(2 * batch_size)
|
||||||
|
@ -26,7 +26,7 @@ Notes
|
|||||||
|
|
||||||
Experiments
|
Experiments
|
||||||
- Teacher model: a basic CNN model trained on MNIST for 3 epochs.
|
- Teacher model: a basic CNN model trained on MNIST for 3 epochs.
|
||||||
- Net2WiderNet exepriment:
|
- Net2WiderNet experiment:
|
||||||
+ Student model has a wider Conv2D layer and a wider FC layer.
|
+ Student model has a wider Conv2D layer and a wider FC layer.
|
||||||
+ Comparison of 'random-padding' vs 'net2wider' weight initialization.
|
+ Comparison of 'random-padding' vs 'net2wider' weight initialization.
|
||||||
+ With both methods, student model should immediately perform as well as
|
+ With both methods, student model should immediately perform as well as
|
||||||
|
@ -35,12 +35,12 @@ applied as a bias because we know the MNIST digits are mapped to [0,1].
|
|||||||
References:
|
References:
|
||||||
[3]
|
[3]
|
||||||
'Deep Residual Learning for Image Recognition'
|
'Deep Residual Learning for Image Recognition'
|
||||||
Kaiming He, xiangyu Zhang, Shaoqing Ren, Jian Sun
|
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
|
||||||
https://arxiv.org/abs/1512.03385v1
|
https://arxiv.org/abs/1512.03385v1
|
||||||
|
|
||||||
[4]
|
[4]
|
||||||
'Identity Mappings in Deep Residual Networks'
|
'Identity Mappings in Deep Residual Networks'
|
||||||
Kaiming He, xiangyu Zhang, Shaoqing Ren, Jian Sun
|
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
|
||||||
https://arxiv.org/abs/1603.05027v3
|
https://arxiv.org/abs/1603.05027v3
|
||||||
|
|
||||||
'''
|
'''
|
||||||
|
Loading…
Reference in New Issue
Block a user