keras打印loss对权重的导数方式

notes

怀疑模型梯度爆炸，想打印模型 loss 对各权重的导数看看。如果如果fit来训练的话，可以用keras.callbacks.tensorboard实现。

但此次使用train_on_batch来训练的，用k.gradients和k.function实现。

codes

以一份 vae 代码为例

# -*- coding: utf8 -*-
import keras
from keras.models import model
from keras.layers import input, lambda, conv2d, maxpooling2d, flatten, dense, reshape
from keras.losses import binary_crossentropy
from keras.datasets import mnist, fashion_mnist
import keras.backend as k
from scipy.stats import norm
import numpy as np
import matplotlib.pyplot as plt

batch = 128
n_class = 10
epoch = 5
in_dim = 28 * 28
h_dim = 128
z_dim = 2

(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()
x_train = x_train.reshape(len(x_train), -1).astype('float32') / 255.
x_test = x_test.reshape(len(x_test), -1).astype('float32') / 255.

def sampleing(args):
  """reparameterize"""
  mu, logvar = args
  eps = k.random_normal([k.shape(mu)[0], z_dim], mean=0.0, stddev=1.0)
  return mu + eps * k.exp(logvar / 2.)

# encode
x_in = input([in_dim])
h = dense(h_dim, activation='relu')(x_in)
z_mu = dense(z_dim)(h) # mean，不用激活
z_logvar = dense(z_dim)(h) # log variance，不用激活
z = lambda(sampleing, output_shape=[z_dim])([z_mu, z_logvar]) # 只能有一个参数
encoder = model(x_in, [z_mu, z_logvar, z], name='encoder')

# decode
z_in = input([z_dim])
h_hat = dense(h_dim, activation='relu')(z_in)
x_hat = dense(in_dim, activation='sigmoid')(h_hat)
decoder = model(z_in, x_hat, name='decoder')

# vae
x_in = input([in_dim])
x = x_in
z_mu, z_logvar, z = encoder(x)
x = decoder(z)
out = x
vae = model(x_in, [out, out], name='vae')

# loss_kl = 0.5 * k.sum(k.square(z_mu) + k.exp(z_logvar) - 1. - z_logvar, axis=1)
# loss_recon = binary_crossentropy(k.reshape(vae_in, [-1, in_dim]), vae_out) * in_dim
# loss_vae = k.mean(loss_kl + loss_recon)

def loss_kl(y_true, y_pred):
  return 0.5 * k.sum(k.square(z_mu) + k.exp(z_logvar) - 1. - z_logvar, axis=1)


# vae.add_loss(loss_vae)
vae.compile(optimizer='rmsprop',
      loss=[loss_kl, 'binary_crossentropy'],
      loss_weights=[1, in_dim])
vae.summary()

# 获取模型权重 variable
w = vae.trainable_weights
print(w)

# 打印 kl 对权重的导数
# kl 要是 tensor，不能是上面的函数 `loss_kl`
grad = k.gradients(0.5 * k.sum(k.square(z_mu) + k.exp(z_logvar) - 1. - z_logvar, axis=1),
          w)
print(grad) # 有些是 none 的
grad = grad[grad is not none] # 去掉 none，不然报错

# 打印梯度的函数
# k.function 的输入和输出必要是 list！就算只有一个
show_grad = k.function([vae.input], [grad])

# vae.fit(x_train, # y_train, # 不能传 y_train
#     batch_size=batch,
#     epochs=epoch,
#     verbose=1,
#     validation_data=(x_test, none))

''' 以 train_on_batch 方式训练 '''
for epoch in range(epoch):
  for b in range(x_train.shape[0] // batch):
    idx = np.random.choice(x_train.shape[0], batch)
    x = x_train[idx]
    l = vae.train_on_batch([x], [x, x])

  # 计算梯度
  gd = show_grad([x])
  # 打印梯度
  print(gd)

# show manifold
pixel = 28
n_pict = 30
grid_x = norm.ppf(np.linspace(0.05, 0.95, n_pict))
grid_y = grid_x

figure = np.zeros([n_pict * pixel, n_pict * pixel])
for i, xi in enumerate(grid_x):
  for j, yj in enumerate(grid_y):
    noise = np.array([[xi, yj]]) # 必须秩为 2，两层中括号
    x_gen = decoder.predict(noise)
    # print('x_gen shape:', x_gen.shape)
    x_gen = x_gen[0].reshape([pixel, pixel])
    figure[i * pixel: (i+1) * pixel,
        j * pixel: (j+1) * pixel] = x_gen

fig = plt.figure(figsize=(10, 10))
plt.imshow(figure, cmap='greys_r')
fig.savefig('./variational_autoencoder.png')
plt.show()

补充知识：keras 自定义损失 自动求导时出现none

问题记录，keras 自定义损失 自动求导时出现none，后来想到是因为传入的变量没有使用，所以keras无法求出偏导，修改后问题解决。就是不愿使用的变量×0,求导后还是0就可以了。

def my_complex_loss_graph(y_label, emb_uid, lstm_out,y_true_1,y_true_2,y_true_3,out_1,out_2,out_3):
 
  mse_out_1 = mean_squared_error(y_true_1, out_1)
  mse_out_2 = mean_squared_error(y_true_2, out_2)
  mse_out_3 = mean_squared_error(y_true_3, out_3)
  # emb_uid= k.reshape(emb_uid, [-1, 32])
  cosine_sim = tf.reduce_sum(0.5*tf.square(emb_uid-lstm_out))
 
  cost=0*cosine_sim+k.sum([0.5*mse_out_1 , 0.25*mse_out_2,0.25*mse_out_3],axis=1,keepdims=true)
  # print(mse_out_1)
  final_loss = cost
 
  return k.mean(final_loss)

以上这篇keras打印loss对权重的导数方式就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。