def main():
import problem_unittests as tests
tests.test_model_inputs(model_inputs)
tests.test_discriminator(discriminator, tf)
tests.test_generator(generator, tf)
tests.test_model_loss(model_loss)
tests.test_model_opt(model_opt, tf)
#x4 = tf.layers.batch_normalization(x4, training=is_train)
#x4 = tf.maximum(0.2*x4, x4)#1,28,28,64
logits = tf.layers.conv2d_transpose(x3,
out_channel_dim,
5,
strides=2,
padding='same')
out = tf.tanh(logits) #1,28,28,3
return out
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_generator(generator, tf)
# ### 损失函数（Loss）
# 部署 `model_loss` 函数训练并计算 GANs 的损失。该函数应返回形如 (discriminator loss, generator loss) 的元组。
#
# 使用你已实现的函数：
# - `discriminator(images, reuse=False)`
# - `generator(z, out_channel_dim, is_train=True)`
# In[8]:
def model_loss(input_real, input_z, out_channel_dim):
"""
Get the loss for the discriminator and generator
:param input_real: Images from the real dataset
:return: A 32x32x3 Tensor image as output
"""
# define feedforward behavior
out = self.fc(x)
out = out.view(-1, self.conv_dim * 8, 2, 2)
out = F.relu(self.deconv1(out))
out = F.relu(self.deconv2(out))
out = F.relu(self.deconv3(out))
out = torch.tanh(self.deconv4(out))
return out
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_generator(Generator)
def weights_init_normal(m):
"""
Applies initial weights to certain layers in a model .
The weights are taken from a normal distribution
with mean = 0, std dev = 0.02.
:param m: A module or layer in a network
"""
# classname will be something like:
# `Conv`, `BatchNorm2d`, `Linear`, etc.
print("Initializing weights")
classname = m.__class__.__name__
# if ('Conv' in classname) or ('Linear' in classname):
# m.weight.data.normal_(0.0, 0.02)
padding='same')
x2 = tf.layers.batch_normalization(x2, training=is_train)
x2 = tf.maximum(0.1 * x2, x2)
# 14x14x128
logits = tf.layers.conv2d_transpose(x2, out_channel_dim, 5, strides=2,
padding='same')
# 28x28x3 now
out = tf.tanh(logits)
return out
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_generator(generator, tf)
# ### 损失函数（Loss）
# 部署 `model_loss` 函数训练并计算 GANs 的损失。该函数应返回形如 (discriminator loss, generator loss) 的元组。
#
# 使用你已实现的函数：
# - `discriminator(images, reuse=False)`
# - `generator(z, out_channel_dim, is_train=True)`
# In[121]:
def model_loss(input_real, input_z, out_channel_dim):
"""
Get the loss for the discriminator and generator
:param input_real: Images from the real dataset
def unit_test(self):
tests.test_model_inputs(self.model_inputs)
tests.test_discriminator(self.discriminator, tf)
tests.test_generator(self.generator, tf)
tests.test_model_loss(self.model_loss)
tests.test_model_opt(self.model_opt, tf)
def test_structure(self):
test_generator(Generator)
