解決Pytorch中Batch Normalization layer踩過的坑
1. 注意momentum的定義
Pytorch中的BN層的動量平滑和常見的動量法計算方式是相反的，默認的momentum=0.1
BN層里的表達式為：
其中γ和β是可以學習的參數(shù)。在Pytorch中，BN層的類的參數(shù)有：
CLASS torch.nn.BatchNorm2d(num_features, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
每個參數(shù)具體含義參見文檔，需要注意的是，affine定義了BN層的參數(shù)γ和β是否是可學習的(不可學習默認是常數(shù)1和0).
2. 注意BN層中含有統(tǒng)計數(shù)據(jù)數(shù)值，即均值和方差
track_running_stats – a boolean value that when set to True, this module tracks the running mean and variance, and when set to False, this module does not track such statistics and always uses batch statistics in both training and eval modes. Default: True
在訓練過程中model.train()，train過程的BN的統(tǒng)計數(shù)值—均值和方差是通過當前batch數(shù)據(jù)估計的。
并且測試時，model.eval()后，若track_running_stats=True，模型此刻所使用的統(tǒng)計數(shù)據(jù)是Running status 中的，即通過指數(shù)衰減規(guī)則，積累到當前的數(shù)值。否則依然使用基于當前batch數(shù)據(jù)的估計值。
3. BN層的統(tǒng)計數(shù)據(jù)更新
是在每一次訓練階段model.train()后的forward()方法中自動實現(xiàn)的，而不是在梯度計算與反向傳播中更新optim.step()中完成
4. 凍結BN及其統(tǒng)計數(shù)據(jù)
從上面的分析可以看出來，正確的凍結BN的方式是在模型訓練時，把BN單獨挑出來，重新設置其狀態(tài)為eval (在model.train()之后覆蓋training狀態(tài)）.
解決方案：
You should use apply instead of searching its children, while named_children() doesn't iteratively search submodules.
def set_bn_eval(m):
classname = m.__class__.__name__
if classname.find('BatchNorm') != -1:
m.eval()
model.apply(set_bn_eval)
或者，重寫module中的train()方法：
def train(self, mode=True):
"""
Override the default train() to freeze the BN parameters
"""
super(MyNet, self).train(mode)
if self.freeze_bn:
print("Freezing Mean/Var of BatchNorm2D.")
if self.freeze_bn_affine:
print("Freezing Weight/Bias of BatchNorm2D.")
if self.freeze_bn:
for m in self.backbone.modules():
if isinstance(m, nn.BatchNorm2d):
m.eval()
if self.freeze_bn_affine:
m.weight.requires_grad = False
m.bias.requires_grad = False
5. Fix/frozen Batch Norm when training may lead to RuntimeError: expected scalar type Half but found Float
解決辦法：
import torch
import torch.nn as nn
from torch.nn import init
from torchvision import models
from torch.autograd import Variable
from apex.fp16_utils import *
def fix_bn(m):
classname = m.__class__.__name__
if classname.find('BatchNorm') != -1:
m.eval()
model = models.resnet50(pretrained=True)
model.cuda()
model = network_to_half(model)
model.train()
model.apply(fix_bn) # fix batchnorm
input = Variable(torch.FloatTensor(8, 3, 224, 224).cuda().half())
output = model(input)
output_mean = torch.mean(output)
output_mean.backward()
Please do
def fix_bn(m):
classname = m.__class__.__name__
if classname.find('BatchNorm') != -1:
m.eval().half()
Reason for this is, for regular training it is better (performance-wise) to use cudnn batch norm, which requires its weights to be in fp32, thus batch norm modules are not converted to half in network_to_half. However, cudnn does not support batchnorm backward in the eval mode , which is what you are doing, and to use pytorch implementation for this, weights have to be of the same type as inputs.
補充：深度學習總結：用pytorch做dropout和Batch Normalization時需要注意的地方，用tensorflow做dropout和BN時需要注意的地方
用pytorch做dropout和BN時需要注意的地方
pytorch做dropout:
就是train的時候使用dropout,訓練的時候不使用dropout,
pytorch里面是通過net.eval()固定整個網(wǎng)絡參數(shù)，包括不會更新一些前向的參數(shù)，沒有dropout，BN參數(shù)固定，理論上對所有的validation set都要使用net.eval()
net.train()表示會納入梯度的計算。
net_dropped = torch.nn.Sequential(
torch.nn.Linear(1, N_HIDDEN),
torch.nn.Dropout(0.5), # drop 50% of the neuron
torch.nn.ReLU(),
torch.nn.Linear(N_HIDDEN, N_HIDDEN),
torch.nn.Dropout(0.5), # drop 50% of the neuron
torch.nn.ReLU(),
torch.nn.Linear(N_HIDDEN, 1),
)
for t in range(500):
pred_drop = net_dropped(x)
loss_drop = loss_func(pred_drop, y)
optimizer_drop.zero_grad()
loss_drop.backward()
optimizer_drop.step()
if t % 10 == 0:
# change to eval mode in order to fix drop out effect
net_dropped.eval() # parameters for dropout differ from train mode
test_pred_drop = net_dropped(test_x)
# change back to train mode
net_dropped.train()
pytorch做Batch Normalization:
net.eval()固定整個網(wǎng)絡參數(shù)，固定BN的參數(shù)，moving_mean 和moving_var，不懂這個看下圖:
if self.do_bn:
bn = nn.BatchNorm1d(10, momentum=0.5)
setattr(self, 'bn%i' % i, bn) # IMPORTANT set layer to the Module
self.bns.append(bn)
for epoch in range(EPOCH):
print('Epoch: ', epoch)
for net, l in zip(nets, losses):
net.eval() # set eval mode to fix moving_mean and moving_var
pred, layer_input, pre_act = net(test_x)
net.train() # free moving_mean and moving_var
plot_histogram(*layer_inputs, *pre_acts)
moving_mean 和moving_var
用tensorflow做dropout和BN時需要注意的地方
dropout和BN都有一個training的參數(shù)表明到底是train還是test, 表明test那dropout就是不dropout，BN就是固定住了BN的參數(shù)；
tf_is_training = tf.placeholder(tf.bool, None) # to control dropout when training and testing
# dropout net
d1 = tf.layers.dense(tf_x, N_HIDDEN, tf.nn.relu)
d1 = tf.layers.dropout(d1, rate=0.5, training=tf_is_training) # drop out 50% of inputs
d2 = tf.layers.dense(d1, N_HIDDEN, tf.nn.relu)
d2 = tf.layers.dropout(d2, rate=0.5, training=tf_is_training) # drop out 50% of inputs
d_out = tf.layers.dense(d2, 1)
for t in range(500):
sess.run([o_train, d_train], {tf_x: x, tf_y: y, tf_is_training: True}) # train, set is_training=True
if t % 10 == 0:
# plotting
plt.cla()
o_loss_, d_loss_, o_out_, d_out_ = sess.run(
[o_loss, d_loss, o_out, d_out], {tf_x: test_x, tf_y: test_y, tf_is_training: False} # test, set is_training=False
)
# pytorch
def add_layer(self, x, out_size, ac=None):
x = tf.layers.dense(x, out_size, kernel_initializer=self.w_init, bias_initializer=B_INIT)
self.pre_activation.append(x)
# the momentum plays important rule. the default 0.99 is too high in this case!
if self.is_bn: x = tf.layers.batch_normalization(x, momentum=0.4, training=tf_is_train) # when have BN
out = x if ac is None else ac(x)
return out
當BN的training的參數(shù)為train時，只是表示BN的參數(shù)是可變化的，并不是代表BN會自己更新moving_mean 和moving_var，因為這個操作是前向更新的op,在做train之前必須確保moving_mean 和moving_var更新了，更新moving_mean 和moving_var的操作在tf.GraphKeys.UPDATE_OPS
# !! IMPORTANT !! the moving_mean and moving_variance need to be updated,
# pass the update_ops with control_dependencies to the train_op
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
self.train = tf.train.AdamOptimizer(LR).minimize(self.loss)
以上為個人經(jīng)驗，希望能給大家一個參考，也希望大家多多支持腳本之家。
相關文章
這篇文章主要介紹了python中的metaclass詳情，在python中的metaclass就是幫助developer實現(xiàn)元編程，更多詳細內(nèi)容需要的小伙伴可以參考一下2022-05-05
這篇文章主要介紹了Python數(shù)據(jù)類型之Set集合,結合實例形式詳細分析了Python數(shù)據(jù)類型中集合的概念、原理、創(chuàng)建、遍歷、交集、并集等相關操作技巧,需要的朋友可以參考下2019-05-05
在本篇文章里小編給大家分享的是關于python3.x中安裝web.py步驟方法，需要的朋友們可以學習下。2020-06-06
最近搞安裝ssl模塊每天都弄到很晚,所以這里給大家整理下,這篇文章主要給大家介紹了關于python3.10及以上版本編譯安裝ssl模塊的詳細過程,文中介紹的非常詳細,需要的朋友可以參考下2023-05-05
這篇文章主要為大家介紹了Pyinstaller加密打包成可執(zhí)行文件方法示例。有需要的朋友可以借鑒參考下，希望能夠有所幫助，祝大家多多進步，早日升職加薪2022-06-06
在本篇文章里小編給大家整理了一篇關于去除python中的字符串空格的簡單方法，有興趣的朋友們可以學習下。2020-12-12
這篇文章主要介紹了Python獲取當前函數(shù)名稱方法實例分享，具有一定借鑒價值2018-01-01
這篇文章主要介紹了python 在不同層級目錄import 模塊的方法,需要的朋友可以參考下2016-01-01
python數(shù)據(jù)可視化之初探?Seaborn
Seaborn?是一個基于?Matplotlib?的?Python?數(shù)據(jù)可視化庫，它提供了更高級別的接口，使得創(chuàng)建美觀的統(tǒng)計圖形變得非常簡單，在這篇文章中，我們將討論?Seaborn?的基礎使用方法，包括如何創(chuàng)建各種常見的統(tǒng)計圖形2023-07-07
這篇文章主要介紹了Python線程和進程的相關知識,包括線程與進程的區(qū)別，通過示例代碼介紹了進程與線程的操作方法，需要的朋友可以參考下2022-04-04