用tensorlayer導入Slim模型遷移學習

　　上一篇博客【用tensorflow遷移學習貓狗分類】筆者講到用tensorlayer的【VGG16模型】遷移學習圖像分類，那麼問題來了，tensorlayer沒提供的模型怎麼辦呢？別擔憂，tensorlayer提供了tensorflow中的【slim模型】導入功能，代碼例子在tutorial_inceptionV3_tfslim。
　　那麼什麼是slim？slim到底有什麼用？
slim是一個使構建，訓練，評估神經網絡變得簡單的庫。它能夠消除原生tensorflow裏面不少重複的模板性的代碼，讓代碼更緊湊，更具有可讀性。另外slim提供了不少計算機視覺方面的著名模型（VGG, AlexNet等），咱們不只能夠直接使用，甚至能以各類方式進行擴展。（筆者注：總之功能跟tensorlayer差很少嘛）更多介紹能夠看這篇文章：【Tensorflow】輔助工具篇——tensorflow slim(TF-Slim)介紹】
　　要進行遷移學習，首先須要slim模型代碼以及預訓練好的權重參數，這些谷歌都有提供下載，能夠看到主頁下面有各個模型以及在imagenet訓練集下的參數地址。

列表還列出了各個模型的top一、top5的正確率，模型不少了。
　　好了咱們下載Inception-ResNet-v2以及inception_resnet_v2_2016_08_30.tar.gz，py文件和解壓出來的.ckpt文件放到項目根目錄下面。至於爲何不用tensorlayer例子提供的Inception V3？由於Inception-ResNet-v2正確率高啊。（哈哈真正緣由最後來說）。
　　咱們依舊進行貓狗分類，按照教程導入模型修改num_classes再導入訓練數據，直接訓練是會報錯的，由於最後的Logits層幾個參數在恢復時維度不匹配。
最後幾個參數是不能恢復了，筆者也沒有找到選擇性恢復.ckpt參數的tensorflow方法。怎麼辦呢？幸虧羣裏面有位朋友提供了一個方法，參見【Tensorflow 遷移學習】：

主要思想是：先把全部.ckpt參數恢復成npz格式，再選擇恢復npz中的參數，恢復npz中的參數就跟前一篇博客操做同樣的了。
因此整個過程分兩步走：
1.將參數恢復而後保存爲npz格式：
　　下面是具體代碼：

import os
import time
from recordutil import *
import numpy as np
# from tensorflow.contrib.slim.python.slim.nets.resnet_v2 import resnet_v2_152
# from tensorflow.contrib.slim.python.slim.nets.vgg import vgg_16
import skimage
import skimage.io
import skimage.transform
import tensorflow as tf
from tensorlayer.layers import *
# from scipy.misc import imread, imresize
# from tensorflow.contrib.slim.python.slim.nets.alexnet import alexnet_v2
from inception_resnet_v2 import (inception_resnet_v2_arg_scope, inception_resnet_v2)
from scipy.misc import imread, imresize
from tensorflow.python.ops import variables
import tensorlayer as tl

slim = tf.contrib.slim
try:
from data.imagenet_classes import *
except Exception as e:
raise Exception(
"{} / download the file from: https://github.com/zsdonghao/tensorlayer/tree/master/example/data".format(e))

n_epoch = 200
learning_rate = 0.0001
print_freq = 2
batch_size = 32
## InceptionV3 / All TF-Slim nets can be merged into TensorLayer
x = tf.placeholder(tf.float32, shape=[None, 299, 299, 3])
# 輸出
y_ = tf.placeholder(tf.int32, shape=[None, ], name='y_')
net_in = tl.layers.InputLayer(x, name='input_layer')
with slim.arg_scope(inception_resnet_v2_arg_scope()):
network = tl.layers.SlimNetsLayer(
prev_layer=net_in,
slim_layer=inception_resnet_v2,
slim_args={
'num_classes': 1001,
'is_training': True,
},
name='InceptionResnetV2' # <-- the name should be the same with the ckpt model
)
# network = fc_layers(net_cnn)
sess = tf.InteractiveSession()
network.print_params(False)
# network.print_layers()
saver = tf.train.Saver()

# 加載預訓練的參數
# tl.files.assign_params(sess, npz, network)

tl.layers.initialize_global_variables(sess)

saver.restore(sess, "inception_resnet_v2.ckpt")
print("Model Restored")
all_params = sess.run(network.all_params)
np.savez('inception_resnet_v2.npz', params=all_params)
sess.close()

 

　　執行成功以後，咱們獲得模型全部的908個參數。
2.部分恢復npz參數而後訓練模型：
　　首先咱們修改模型最後一層參數，因爲進行的是2分類學習，因此作以下修改：

with slim.arg_scope(inception_resnet_v2_arg_scope()):
network = tl.layers.SlimNetsLayer(
prev_layer=net_in,
slim_layer=inception_resnet_v2,
slim_args={
'num_classes': 2,
'is_training': True,
},
name='InceptionResnetV2' # <-- the name should be the same with the ckpt model
)

　　num_classes改成2，is_training爲True。
　　接着定義輸入輸出以及損失函數：

sess = tf.InteractiveSession()
# saver = tf.train.Saver()
y = network.outputs
y_op = tf.argmax(tf.nn.softmax(y), 1)
cost = tl.cost.cross_entropy(y, y_, name='cost')
correct_prediction = tf.equal(tf.cast(tf.argmax(y, 1), tf.float32), tf.cast(y_, tf.float32))
acc = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

 

　　下面是定義訓練參數，咱們只訓練最後一層的參數，打印參數出來咱們看到：

[TL] param 900: InceptionResnetV2/AuxLogits/Conv2d_2a_5x5/weights:0 (5, 5, 128, 768) float32_ref
[TL] param 901: InceptionResnetV2/AuxLogits/Conv2d_2a_5x5/BatchNorm/beta:0 (768,) float32_ref
[TL] param 902: InceptionResnetV2/AuxLogits/Conv2d_2a_5x5/BatchNorm/moving_mean:0 (768,) float32_ref
[TL] param 903: InceptionResnetV2/AuxLogits/Conv2d_2a_5x5/BatchNorm/moving_variance:0 (768,) float32_ref
[TL] param 904: InceptionResnetV2/AuxLogits/Logits/weights:0 (768, 2) float32_ref
[TL] param 905: InceptionResnetV2/AuxLogits/Logits/biases:0 (2,) float32_ref
[TL] param 906: InceptionResnetV2/Logits/Logits/weights:0 (1536, 2) float32_ref
[TL] param 907: InceptionResnetV2/Logits/Logits/biases:0 (2,) float32_ref
[TL] num of params: 56940900

 

　　從param 904開始訓練就好了，參數恢復到param 903
　　下面是訓練函數以及恢復部分參數，加載樣本數據：

# 定義 optimizer
train_params = network.all_params[904:]
print('訓練參數:', train_params)
# # 加載預訓練的參數
# tl.files.assign_params(sess, params, network)
train_op = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost, var_list=train_params)
img, label = read_and_decode("D:\\001-Python\\train299.tfrecords")
# 使用shuffle_batch能夠隨機打亂輸入
X_train, y_train = tf.train.shuffle_batch([img, label],
batch_size=batch_size, capacity=200,
min_after_dequeue=100)
tl.layers.initialize_global_variables(sess)
params = tl.files.load_npz('', 'inception_resnet_v2.npz')
params = params[0:904]
print('當前參數大小：', len(params))
tl.files.assign_params(sess, params=params, network=network)

 

　　下面依舊是訓練模型的代碼，跟上一篇同樣：

# # 訓練模型
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
step = 0
filelist = getfilelist()
for epoch in range(n_epoch):
start_time = time.time()
val, l = sess.run([X_train, y_train])#next_data(filelist, batch_size) #
for X_train_a, y_train_a in tl.iterate.minibatches(val, l, batch_size, shuffle=True):
sess.run(train_op, feed_dict={x: X_train_a, y_: y_train_a})
if epoch + 1 == 1 or (epoch + 1) % print_freq == 0:
print("Epoch %d of %d took %fs" % (epoch + 1, n_epoch, time.time() - start_time))
train_loss, train_acc, n_batch = 0, 0, 0
for X_train_a, y_train_a in tl.iterate.minibatches(val, l, batch_size, shuffle=True):
err, ac = sess.run([cost, acc], feed_dict={x: X_train_a, y_: y_train_a})
train_loss += err
train_acc += ac
n_batch += 1
print(" train loss: %f" % (train_loss / n_batch))
print(" train acc: %f" % (train_acc / n_batch))
# tl.files.save_npz(network.all_params, name='model_vgg_16_2.npz', sess=sess)
coord.request_stop()
coord.join(threads)

 

　　batchsize爲20訓練200代，部分結果以下：

Epoch 156 of 200 took 12.568609s
train loss: 0.382517
train acc: 0.950000
Epoch 158 of 200 took 12.457161s
train loss: 0.382509
train acc: 0.850000
Epoch 160 of 200 took 12.385407s
train loss: 0.320393
train acc: 1.000000
Epoch 162 of 200 took 12.489218s
train loss: 0.480686
train acc: 0.700000
Epoch 164 of 200 took 12.388841s
train loss: 0.329189
train acc: 0.850000
Epoch 166 of 200 took 12.446472s
train loss: 0.379127
train acc: 0.900000
Epoch 168 of 200 took 12.888571s
train loss: 0.365938
train acc: 0.900000
Epoch 170 of 200 took 12.850605s
train loss: 0.353434
train acc: 0.850000
Epoch 172 of 200 took 12.855129s
train loss: 0.315443
train acc: 0.950000
Epoch 174 of 200 took 12.906666s
train loss: 0.460817
train acc: 0.750000
Epoch 176 of 200 took 12.830738s
train loss: 0.421025
train acc: 0.900000
Epoch 178 of 200 took 12.852572s
train loss: 0.418784
train acc: 0.800000
Epoch 180 of 200 took 12.951322s
train loss: 0.316057
train acc: 0.950000
Epoch 182 of 200 took 12.866213s
train loss: 0.363328
train acc: 0.900000
Epoch 184 of 200 took 13.012520s
train loss: 0.379462
train acc: 0.850000
Epoch 186 of 200 took 12.934583s
train loss: 0.472857
train acc: 0.750000
Epoch 188 of 200 took 13.038168s
train loss: 0.236005
train acc: 1.000000
Epoch 190 of 200 took 13.056378s
train loss: 0.266042
train acc: 0.950000
Epoch 192 of 200 took 13.016137s
train loss: 0.255430
train acc: 0.950000
Epoch 194 of 200 took 13.013147s
train loss: 0.422342
train acc: 0.900000
Epoch 196 of 200 took 12.980659s
train loss: 0.353984
train acc: 0.900000
Epoch 198 of 200 took 13.033676s
train loss: 0.320018
train acc: 0.950000
Epoch 200 of 200 took 12.945982s
train loss: 0.288049
train acc: 0.950000

 

　　好了，遷移學習Inception-ResNet-v2結束。
　　做者說SlimNetsLayer是能導入任何Slim Model的。筆者已經驗證過導入Inception-ResNet-v2和VGG16成功，Inception V3導入後訓練了兩三天，正確率一直在10到70之間波動（跟筆者的心情同樣不穩定），筆者一直找不出緣由，心累，但願哪位朋友再去驗證一下Inception V3咯。