我有一个关于对 BatchNorm (稍后是 BN)的理解的问题。
我有一个运行良好的卷积网络,我正在编写测试来检查形状和输出范围。我注意到,当我设置 batch_size = 1 时,我的模型输出零(logits 和激活)。
我用 BN 制作了最简单的 convnet 原型:
Input => Conv + ReLU => BN => Conv + ReLU => BN => Conv Layer + Tanh
该模型使用xavier 初始化进行初始化。我猜想 BN在训练期间做了一些需要 Batch_size > 1 的计算。
我在 PyTorch 中发现了一个似乎在谈论这个的问题:https ://github.com/pytorch/pytorch/issues/1381
谁能解释一下?对我来说还是有点模糊。
示例运行:
重要提示:运行此脚本需要 Tensorlayer 库:pip install tensorlayer
import tensorflow as tf
import tensorlayer as tl
import numpy as np
def conv_net(inputs, is_training):
xavier_initilizer = tf.contrib.layers.xavier_initializer(uniform=True)
normal_initializer = tf.random_normal_initializer(mean=1., stddev=0.02)
# Input Layers
network = tl.layers.InputLayer(inputs, name='input')
fx = [64, 128, 256, 256, 256]
for i, n_out_channel in enumerate(fx):
with tf.variable_scope('h' + str(i + 1)):
network = tl.layers.Conv2d(
network,
n_filter = n_out_channel,
filter_size = (5, 5),
strides = (2, 2),
padding = 'VALID',
act = tf.identity,
W_init = xavier_initilizer,
name = 'conv2d'
)
network = tl.layers.BatchNormLayer(
network,
act = tf.identity,
is_train = is_training,
gamma_init = normal_initializer,
name = 'batch_norm'
)
network = tl.layers.PReluLayer(
layer = network,
a_init = tf.constant_initializer(0.2),
name ='activation'
)
############# OUTPUT LAYER ###############
with tf.variable_scope('h' + str(len(fx) + 1)):
'''
network = tl.layers.FlattenLayer(network, name='flatten')
network = tl.layers.DenseLayer(
network,
n_units = 100,
act = tf.identity,
W_init = xavier_initilizer,
name = 'dense'
)
'''
output_filter_size = tuple([int(i) for i in network.outputs.get_shape()[1:3]])
network = tl.layers.Conv2d(
network,
n_filter = 100,
filter_size = output_filter_size,
strides = (1, 1),
padding = 'VALID',
act = tf.identity,
W_init = xavier_initilizer,
name = 'conv2d'
)
network = tl.layers.BatchNormLayer(
network,
act = tf.identity,
is_train = is_training,
gamma_init = normal_initializer,
name = 'batch_norm'
)
net_logits = network.outputs
network.outputs = tf.nn.tanh(
x = network.outputs,
name = 'activation'
)
net_output = network.outputs
return network, net_output, net_logits
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.DEBUG)
#################################################
# MODEL DEFINITION #
#################################################
PLH_SHAPE = [None, 256, 256, 3]
input_plh = tf.placeholder(tf.float32, PLH_SHAPE, name='input_placeholder')
convnet, net_out, net_logits = conv_net(input_plh, is_training=True)
with tf.Session() as sess:
tl.layers.initialize_global_variables(sess)
convnet.print_params(details=True)
#################################################
# LAUNCH A RUN #
#################################################
for BATCH_SIZE in [1, 2]:
INPUT_SHAPE = [BATCH_SIZE, 256, 256, 3]
batch_data = np.random.random(size=INPUT_SHAPE)
output, logits = sess.run(
[net_out, net_logits],
feed_dict={
input_plh: batch_data
}
)
if tf.logging.get_verbosity() == tf.logging.DEBUG:
print("\n\n###########################")
print("\nBATCH SIZE = %d\n" % BATCH_SIZE)
tf.logging.debug("output => Shape: %s - Mean: %e - Std: %f - Min: %f - Max: %f" % (
output.shape,
output.mean(),
output.std(),
output.min(),
output.max()
))
tf.logging.debug("logits => Shape: %s - Mean: %e - Std: %f - Min: %f - Max: %f" % (
logits.shape,
logits.mean(),
logits.std(),
logits.min(),
logits.max()
))
if tf.logging.get_verbosity() == tf.logging.DEBUG:
print("###########################")
给出以下输出:
###########################
BATCH SIZE = 1
DEBUG:tensorflow:output => Shape: (1, 1, 1, 100) - Mean: 0.000000e+00 - Std: 0.000000 - Min: 0.000000 - Max: 0.000000
DEBUG:tensorflow:logits => Shape: (1, 1, 1, 100) - Mean: 0.000000e+00 - Std: 0.000000 - Min: 0.000000 - Max: 0.000000
###########################
###########################
BATCH SIZE = 2
DEBUG:tensorflow:output => Shape: (2, 1, 1, 100) - Mean: -1.430511e-08 - Std: 0.760749 - Min: -0.779634 - Max: 0.779634
DEBUG:tensorflow:logits => Shape: (2, 1, 1, 100) - Mean: -4.768372e-08 - Std: 0.998715 - Min: -1.044437 - Max: 1.044437
###########################