tensorflow实现GoogLeNet-InceptionV1
GoogLeNet Inception v1 结构 及 pytorch、tensorflow、keras、paddle实现ImageNet识别
环境
python3.6，tensorflow-gpu 1.12.0
代码
# -*- coding: utf-8 -*-
# @Time : 2020/2/3 9:56
# @Author : Zhao HL
# @File : InceptionV1-tensorflow.py
import sys, cv2, os
import numpy as np
import pandas as pd
from PIL import Image
import tensorflow as tf
from my_utils import process_show, draw_loss_acc, dataInfo_show, dataset_divide
tf.logging.set_verbosity(tf.logging.ERROR)
# region parameters
# region paths
Data_path = "./data/"
Data_csv_path = "./data/split.txt"
Model_path = 'model/'
Model_file_tf = "model/InceptionV1_tf.ckpt"
Model_file_keras = "model/InceptionV1_keras.h5"
Model_file_torch = "model/InceptionV1_torch.pth"
Model_file_paddle = "model/InceptionV1_paddle.model"
# endregion
# region image parameter
Img_size = 224
Img_chs = 3
Label_size = 1
Label_class = ['agricultural',
'airplane',
'baseballdiamond',
'beach',
'buildings',
'chaparral',
'denseresidential',
'forest',
'freeway',
'golfcourse',
'harbor',
'intersection',
'mediumresidential',
'mobilehomepark',
'overpass',
'parkinglot',
'river',
'runway',
'sparseresidential',
'storagetanks',
'tenniscourt']
Labels_nums = len(Label_class)
# endregion
# region net parameter
Conv1_kernel_size = 7
Conv1_chs = 64
Conv21_kernel_size = 1
Conv21_chs = 64
Conv2_kernel_size = 3
Conv2_chs = 192
Icp3a_size = (64, 96, 128, 16, 32, 32)
Icp3b_size = (128, 128, 192, 32, 96, 64)
Icp4a_size = (192, 96, 208, 16, 48, 64)
Icp4b_size = (160, 112, 224, 24, 64, 64)
Icp4c_size = (128, 128, 256, 24, 64, 64)
Icp4d_size = (112, 144, 288, 32, 64, 64)
Icp4e_size = (256, 160, 320, 32, 128, 128)
Icp5a_size = (256, 160, 320, 32, 128, 128)
Icp5b_size = (384, 192, 384, 48, 128, 128)
Out_chs1 = 128
Out_chs2 = 1024
# endregion
# region hpyerparameter
Learning_rate = 1e-3
Batch_size = 16
Buffer_size = 256
Infer_size = 1
Epochs = 20
Train_num = 1470
Train_batch_num = Train_num // Batch_size
Val_num = 210
Val_batch_num = Val_num // Batch_size
Test_num = 420
Test_batch_num = Test_num // Batch_size
# endregion
# endregion
class MyDataset():
def __init__(self, root_path, batch_size, files_list=None):
self.root_path = root_path
self.batch_size = batch_size
self.files_list = files_list if files_list else os.listdir(root_path)
self.size = len(files_list)
np.random.shuffle(self.files_list)
def __len__(self):
return self.size
def __getitem__(self, batch_index):
images, labels = [], []
start_index = batch_index * self.batch_size
end_index = (batch_index + 1) * self.batch_size
for index in range(start_index, end_index):
label_str = os.path.basename(self.files_list[index])[:-6]
label = Label_class.index(label_str)
img = Image.open(os.path.join(self.root_path, self.files_list[index]))
img, label = self.transform(img, label)
images.append(img)
labels.append(label)
images = np.array(images)
labels = np.array(labels)
if batch_index == self.size // self.batch_size - 1:
np.random.shuffle(self.files_list)
return images, labels
def transform(self, image, label):
def Normalize(image, means, stds):
for band in range(len(means)):
image[:, :, band] = image[:, :, band] / 255.0
image[:, :, band] = (image[:, :, band] - means[band]) / stds[band]
return image
def ToOnehot(labels):
labels = np.eye(Labels_nums)[labels].reshape(Labels_nums)
return labels
pass
image = image.resize((Img_size, Img_size), Image.BILINEAR)
image = Normalize(np.array(image).astype(np.float), [0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
label = ToOnehot(label)
return image, label
class InceptionV1:
def __init__(self, structShow=False,trainModel=True):
self.structShow = structShow
self.trainModel = trainModel
self.image = tf.placeholder(tf.float32, [Batch_size, Img_size, Img_size, Img_chs])
self.label = tf.placeholder(tf.float32, [Batch_size, Labels_nums])
self.predict = self.getNet()
def get_w(self, shape):
if np.size(shape) == 2:
n = shape[0] + shape[1]
else:
n = shape[0] * shape[1] * shape[2]
stddev = np.sqrt(2.0 / n)
return tf.Variable(tf.truncated_normal(shape, mean=0, stddev=stddev), trainable=True, name='w')
def get_b(self, shape):
return tf.Variable(tf.zeros(shape), name='b')
def InceptionV1_Model(self, input, input_chs, model_size):
con11_chs, con31_chs, con3_chs, con51_chs, con5_chs, pool11_chs = model_size
with tf.name_scope('conv1'):
conv11_w = self.get_w([1, 1, input_chs, con11_chs])
conv11_b = self.get_b([con11_chs])
conv11 = tf.nn.conv2d(input, conv11_w, strides=[1, 1, 1, 1], padding='SAME')
relu11 = tf.nn.relu(tf.nn.bias_add(conv11, conv11_b))
with tf.name_scope('conv3'):
conv31_w = self.get_w([1, 1, input_chs, con31_chs])
conv31_b = self.get_b([con31_chs])
conv31 = tf.nn.conv2d(input, conv31_w, strides=[1, 1, 1, 1], padding='SAME')
relu31 = tf.nn.relu(tf.nn.bias_add(conv31, conv31_b))
conv3_w = self.get_w([3, 3, con31_chs, con3_chs])
conv3_b = self.get_b([con3_chs])
conv3 = tf.nn.conv2d(relu31, conv3_w, strides=[1, 1, 1, 1], padding='SAME')
relu3 = tf.nn.relu(tf.nn.bias_add(conv3, conv3_b))
with tf.name_scope('conv5'):
conv51_w = self.get_w([1, 1, input_chs, con51_chs])
conv51_b = self.get_b([con51_chs])
conv51 = tf.nn.conv2d(input, conv51_w, strides=[1, 1, 1, 1], padding='SAME')
relu51 = tf.nn.relu(tf.nn.bias_add(conv51, conv51_b))
conv5_w = self.get_w([5, 5, con51_chs, con5_chs])
conv5_b = self.get_b([con5_chs])
conv5 = tf.nn.conv2d(relu51, conv5_w, strides=[1, 1, 1, 1], padding='SAME')
relu5 = tf.nn.relu(tf.nn.bias_add(conv5, conv5_b))
with tf.name_scope('pool'):
pool1 = tf.nn.max_pool(input, ksize=[1, 3, 3, 1], strides=[1, 1, 1, 1], padding='SAME')
conv1_w = self.get_w([1, 1, input_chs, pool11_chs])
conv1_b = self.get_b([pool11_chs])
conv1 = tf.nn.conv2d(pool1, conv1_w, strides=[1, 1, 1, 1], padding='SAME')
relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_b))
return relu11, relu3, relu5, relu1
def InceptionV1_Out(self, input, input_chs):
pool = tf.nn.avg_pool(input, ksize=[1, 5, 5, 1], strides=[1, 3, 3, 1], padding='VALID')
conv_w = self.get_w([1, 1, input_chs, Out_chs1])
conv_b = self.get_b([Out_chs1])
conv = tf.nn.conv2d(pool, conv_w, strides=[1, 1, 1, 1], padding='SAME')
relu = tf.nn.relu(tf.nn.bias_add(conv, conv_b))
flatten = tf.reshape(relu, [relu.shape[0], -1])
dropout1 = tf.nn.dropout(flatten, keep_prob=0.7)
fc1_w = self.get_w([int(dropout1.shape[1]), Out_chs2])
fc1 = tf.matmul(dropout1, fc1_w)
dropout2 = tf.nn.dropout(fc1, keep_prob=0.7)
fc2_w = self.get_w([int(dropout2.shape[1]), Labels_nums])
fc2 = tf.matmul(dropout2, fc2_w)
out = fc2
return out
def getNet(self):
with tf.name_scope('conv'):
conv1_w = self.get_w([Conv1_kernel_size, Conv1_kernel_size, Img_chs, Conv1_chs])
conv1_b = self.get_b([Conv1_chs])
conv1 = tf.nn.conv2d(self.image, conv1_w, strides=[1, 2, 2, 1], padding='SAME')
relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_b))
pool1 = tf.nn.max_pool(relu1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')
conv21_w = self.get_w([1, 1, Conv1_chs, Conv21_chs])
conv21_b = self.get_b([Conv21_chs])
conv21 = tf.nn.conv2d(pool1, conv21_w, strides=[1, 1, 1, 1], padding='SAME')
relu21 = tf.nn.relu(tf.nn.bias_add(conv21, conv21_b))
conv2_w = self.get_w([1, 1, Conv21_chs, Conv2_chs])
conv2_b = self.get_b([Conv2_chs])
conv2 = tf.nn.conv2d(relu21, conv2_w, strides=[1, 1, 1, 1], padding='SAME')
relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_b))
pool2 = tf.nn.max_pool(relu2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')
with tf.name_scope('inception3a'):
conv1, conv3, conv5, pool = self.InceptionV1_Model(pool2, 192, Icp3a_size)
inception3a = tf.concat([conv1, conv3, conv5, pool], 3)
with tf.name_scope('inception3b'):
conv1, conv3, conv5, pool = self.InceptionV1_Model(inception3a, 256, Icp3b_size)
inception3b = tf.concat([conv1, conv3, conv5, pool], 3)
pool3 = tf.nn.max_pool(inception3b, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')
with tf.name_scope('inception4a'):
conv1, conv3, conv5, pool = self.InceptionV1_Model(pool3, 480, Icp4a_size)
inception4a = tf.concat([conv1, conv3, conv5, pool], 3)
if self.trainModel == True:
output1 = self.InceptionV1_Out(inception4a, 512)
with tf.name_scope('inception4b'):
conv1, conv3, conv5, pool = self.InceptionV1_Model(inception4a, 512, Icp4b_size)
inception4b = tf.concat([conv1, conv3, conv5, pool], 3)
with tf.name_scope('inception4c'):
conv1, conv3, conv5, pool = self.InceptionV1_Model(inception4b, 512, Icp4c_size)
inception4c = tf.concat([conv1, conv3, conv5, pool], 3)
with tf.name_scope('inception4d'):
conv1, conv3, conv5, pool = self.InceptionV1_Model(inception4c, 512, Icp4d_size)
inception4d = tf.concat([conv1, conv3, conv5, pool], 3)
if self.trainModel == True:
output2 = self.InceptionV1_Out(inception4d, 528)
with tf.name_scope('inception4e'):
conv1, conv3, conv5, pool = self.InceptionV1_Model(inception4d, 528, Icp4e_size)
inception4e = tf.concat([conv1, conv3, conv5, pool], 3)
pool4 = tf.nn.max_pool(inception4e, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')
with tf.name_scope('inception5a'):
conv1, conv3, conv5, pool = self.InceptionV1_Model(pool4, 832, Icp5a_size)
inception5a = tf.concat([conv1, conv3, conv5, pool], 3)
with tf.name_scope('inception5b'):
conv1, conv3, conv5, pool = self.InceptionV1_Model(inception5a, 832, Icp5b_size)
inception5b = tf.concat([conv1, conv3, conv5, pool], 3)
pool5 = tf.nn.avg_pool(inception5b, ksize=[1, 7, 7, 1], strides=[1, 1, 1, 1], padding='VALID')
with tf.name_scope('output'):
flatten = tf.reshape(pool5, [pool5.shape[0], -1])
dropout = tf.nn.dropout(flatten, keep_prob=0.6)
fc_w = self.get_w([int(dropout.shape[1]), Labels_nums])
fc = tf.matmul(dropout, fc_w)
output = fc
# output = tf.nn.softmax(tf.nn.bias_add(fc, fc_b))
if self.structShow:
print(relu1.name, relu1.shape)
print(pool1.name, pool1.shape)
print(relu2.name, relu2.shape)
print(pool2.name, pool2.shape)
print(inception3a.name, inception3a.shape)
print(inception3b.name, inception3b.shape)
print(pool3.name, pool3.shape)
print(inception4a.name, inception4a.shape)
if self.trainModel == True:
print(output1.name, output1.shape)
print(inception4b.name, inception4b.shape)
print(inception4c.name, inception4c.shape)
print(inception4d.name, inception4d.shape)
if self.trainModel == True:
print(output2.name, output2.shape)
print(inception4e.name, inception4e.shape)
print(pool4.name, pool4.shape)
print(inception5a.name, inception5a.shape)
print(inception5b.name, inception5b.shape)
print(pool5.name, pool5.shape)
print(flatten.name, flatten.shape)
print(fc.name, fc.shape)
print(output.name, output.shape)
if self.trainModel == True:
return [output, output1, output2]
return output
def train():
df = pd.read_csv(Data_csv_path, header=0, index_col=0)
train_list = df[df['split'] == 'train']['filename'].tolist()
val_list = df[df['split'] == 'val']['filename'].tolist()
train_dataset = MyDataset(Data_path, batch_size=Batch_size, files_list=train_list)
val_dataset = MyDataset(Data_path, batch_size=Batch_size, files_list=val_list)
net = InceptionV1(structShow=True)
image, label, predict = net.image, net.label, net.predict
train_loss = tf.reduce_mean(-tf.reduce_sum(label * tf.log(tf.clip_by_value(predict[0], 1e-15, 1.0)), reduction_indices=1))
# train_loss = 0.6 * tf.reduce_mean(-tf.reduce_sum(label * tf.log(tf.clip_by_value(predict[0],1e-15,1.0)), reduction_indices=1))\
# + 0.2 * tf.reduce_mean(-tf.reduce_sum(label * tf.log(tf.clip_by_value(predict[1],1e-15,1.0)), reduction_indices=1))\
# + 0.2 * tf.reduce_mean(-tf.reduce_sum(label * tf.log(tf.clip_by_value(predict[2],1e-15,1.0)), reduction_indices=1))
val_loss = train_loss
# val_loss = 1 * tf.reduce_mean(-tf.reduce_sum(label * tf.log(tf.clip_by_value(predict[0],1e-15,1.0)), reduction_indices=1))\
# + 0 * tf.reduce_mean(-tf.reduce_sum(label * tf.log(tf.clip_by_value(predict[1],1e-15,1.0)), reduction_indices=1))\
# + 0 * tf.reduce_mean(-tf.reduce_sum(label * tf.log(tf.clip_by_value(predict[2],1e-15,1.0)), reduction_indices=1))
run_step = tf.train.AdamOptimizer(Learning_rate).minimize(train_loss)
correct = tf.equal(tf.argmax(predict[0], 1), tf.argmax(label, 1))
accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
model = tf.train.get_checkpoint_state(Model_file_tf)
# if model and model.model_checkpoint_path:
# saver.restore(sess, model.model_checkpoint_path)
train_losses = np.ones(Epochs)
train_accs = np.ones(Epochs)
val_losses = np.ones(Epochs)
val_accs = np.ones(Epochs)
best_loss = float("inf")
best_loss_epoch = 0
for epoch in range(Epochs):
print('Epoch %d/%d:' % (epoch + 1, Epochs))
train_sum_loss = 0
train_sum_acc = 0
val_sum_loss = 0
val_sum_acc = 0
for batch, (images, labels) in enumerate(train_dataset):
train_acc, t_loss, pre,cor,_ = sess.run(
[accuracy, train_loss,predict, correct,run_step], feed_dict={image: images, label: labels})
process_show(batch + 1, Train_batch_num, train_acc, t_loss, prefix='train:')
train_sum_acc += train_acc
train_sum_loss += t_loss
for batch, (images, labels) in enumerate(val_dataset):
val_acc, v_loss = sess.run([accuracy, val_loss], feed_dict={image: images, label: labels})
process_show(batch + 1, Val_batch_num, val_acc, v_loss, prefix='val:')
val_sum_acc += val_acc
val_sum_loss += v_loss
train_sum_loss /= Train_batch_num
train_sum_acc /= Train_batch_num
val_sum_loss /= Val_batch_num
val_sum_acc /= Val_batch_num
train_losses[epoch] = train_sum_loss
train_accs[epoch] = train_sum_acc
val_losses[epoch] = val_sum_loss
val_accs[epoch] = val_sum_acc
print('average summary:\ntrain acc %.4f, loss %.4f ; val acc %.4f, loss %.4f'
% (train_sum_acc, train_sum_loss, val_sum_acc, val_sum_loss))
if val_sum_loss < best_loss:
print('val_loss improve from %.4f to %.4f, model save to %s ! \n' % (
best_loss, val_sum_loss, Model_file_tf))
best_loss = val_sum_loss
best_loss_epoch = epoch + 1
saver.save(sess=sess, save_path=Model_file_tf)
else:
print('val_loss do not improve from %.4f \n' % (best_loss))
print('best loss %.4f at epoch %d \n' % (best_loss, best_loss_epoch))
draw_loss_acc(train_losses, train_accs, 'train')
draw_loss_acc(val_losses, val_accs, 'val')
if __name__ == '__main__':
pass
# dataset_divide(r'E:\_Python\01_deeplearning\04_GoogLeNet\Inception1\data\split.txt')
train()
my_utils.py
# -*- coding: utf-8 -*-
# @Time : 2020/1/21 11:39
# @Author : Zhao HL
# @File : my_utils.py
import sys,os,random
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from PIL import Image
def process_show(num, nums, train_acc, train_loss, prefix='', suffix=''):
rate = num / nums
ratenum = int(round(rate, 2) * 100)
bar = '\r%s batch %3d/%d:train accuracy %.4f, train loss %00.4f [%s%s]%.1f%% %s; ' % (
prefix, num, nums, train_acc, train_loss, '#' * (ratenum//2), '_' * (50 - ratenum//2), ratenum, suffix)
sys.stdout.write(bar)
sys.stdout.flush()
if num >= nums:
print()
def dataInfo_show(data_path,csv_pth,cls_dic_path,shapesShow=True,classesShow=True):
cls_dict = get_cls_dic(cls_dic_path)
if classesShow:
print('\n'+'*'*50)
df = pd.read_csv(csv_pth)
labels = df['label'].unique()
label_cls = {label:cls_dict[label] for label in labels}
print(label_cls)
cls_count = df['label'].value_counts()
cls_count = {cls_dict[k]:v for k,v in cls_count.items()}
for k,v in cls_count.items():
print(k,v)
if shapesShow:
print('\n'+'*'*50)
shapes = []
for filename in os.listdir(data_path):
img = Image.open(os.path.join(data_path, filename))
img = np.array(img)
shapes.append(img.shape)
shapes = pd.Series(shapes)
print(shapes.value_counts())
def get_cls_dic(cls_dic_path):
# 读取类标签字典，只取第一个逗号前的信息
cls_df = pd.read_csv(cls_dic_path)
cls_df['cls'] = cls_df['info'].apply(lambda x:x[:9]).tolist()
cls_df['label'] = cls_df['info'].apply(lambda x: x[10:]).tolist()
cls_df = cls_df.drop(columns=['info','other'])
cls_dict = cls_df.set_index('cls').T.to_dict('list')
cls_dict = {k:v[0] for k,v in cls_dict.items()}
return cls_dict
def dataset_divide(csv_pth):
cls_df = pd.read_csv(csv_pth, header=0,index_col=0)
cls_df.insert(1,'split',None)
filenames = list(cls_df['filename'])
random.shuffle(filenames)
train_num,train_val_num = int(len(filenames)*0.7),int(len(filenames)*0.8)
train_names = filenames[:train_num]
val_names = filenames[train_num:train_val_num]
test_names = filenames[train_val_num:]
cls_df.loc[cls_df['filename'].isin(train_names),'split'] = 'train'
cls_df.loc[cls_df['filename'].isin(val_names), 'split'] = 'val'
cls_df.loc[cls_df['filename'].isin(test_names), 'split'] = 'test'
cls_df.to_csv(csv_pth)
def draw_loss_acc(loss,acc,type='',save_path=None):
assert len(acc) == len(loss)
x = [epoch for epoch in range(len(acc))]
plt.subplot(2, 1, 1)
plt.plot(x, acc, 'o-')
plt.title(type+' accuracy vs. epoches')
plt.ylabel('accuracy')
plt.subplot(2, 1, 2)
plt.plot(x, loss, '.-')
plt.xlabel(type+' loss vs. epoches')
plt.ylabel('loss')
plt.show()
if save_path:
plt.savefig(os.path.join(save_path,type+"_acc_loss.png"))
if __name__ == '__main__':
pass
作者：GISer_Lin
