GoogLeNet Inception v3 結構 及 pytorch、tensorflow、keras、paddle實現ImageNet識別
環境
python3.6, keras2.2.4, tensorflow-gpu 1.12.0
代碼
# -*- coding: utf-8 -*-
# @Time : 2020/2/21 13:53
# @Author : Zhao HL
# @File : InceptionV3-paddle.py
import os, sys
from PIL import Image
import numpy as np
import pandas as pd
import paddle
from paddle import fluid
from paddle.fluid.layers import data, conv2d, pool2d, flatten, fc, cross_entropy, accuracy, mean, concat, dropout,batch_norm,softmax
from my_utils import process_show, draw_loss_acc
# 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 = 299
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_chs = 32
Conv2_chs = 32
Conv3_chs = 64
Conv4_chs = 80
Conv5_chs = 192
Conv6_chs = 288
Icp3a_size = (288, 64, 64, 96, 48, 64, 64)
Icp3b_size = (288, 64, 64, 96, 48, 64, 64)
Icp3c_size = (288, 0, 192, 384, 64, 96, 288)
Icp5a_size = (768, 192, 160, 192, 160, 192, 192)
Icp5b_size = (768, 192, 160, 192, 160, 192, 192)
Icp5c_size = (768, 192, 160, 192, 160, 192, 192)
Icp5d_size = (768, 192, 160, 192, 160, 192, 192)
Icp5e_size = (768, 0, 192, 320, 192, 192, 768)
Icp2a_size = (1280, 320, 384, 384, 448, 384, 192)
Icp2b_size = (2048, 320, 384, 384, 448, 384, 192)
# endregion
# region hpyerparameter
Learning_rate = 0.045
Batch_size = 1
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
place = fluid.CUDAPlace(0) if fluid.cuda_places() else fluid.CPUPlace()
# endregion
class MyDataset():
def __init__(self, root_path, batch_size, files_list=None, ):
self.root_path = root_path
self.files_list = files_list if files_list else os.listdir(root_path)
self.size = len(files_list)
self.batch_size = batch_size
def __len__(self):
return self.size
def dataset_reader(self):
pass
files_list = self.files_list if self.files_list is not None else os.listdir(self.root_path)
def reader():
np.random.shuffle(files_list)
for file_name in files_list:
label_str = os.path.basename(file_name)[:-6]
label = Label_class.index(label_str)
img = Image.open(os.path.join(self.root_path, file_name))
yield img, label
return paddle.batch(paddle.reader.xmap_readers(self.transform, reader, 2, Buffer_size),
batch_size=self.batch_size)
def transform(self, sample):
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]
image = np.transpose(image, [2, 1, 0])
return image
pass
image, label = sample
image = image.resize((Img_size, Img_size), Image.ANTIALIAS)
image = Normalize(np.array(image).astype(np.float), [0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
return image, label
class InceptionV3:
def __init__(self, structShow=False):
self.structShow = structShow
self.image = data(shape=[Img_chs, Img_size, Img_size], dtype='float32', name='image')
self.label = data(shape=[Label_size], dtype='int64', name='label')
self.predict = self.get_Net()
def InceptionV3_ModelA(self, input, model_size, downsample=False):
input_chs, con1_chs, con31_chs, con3_chs, con51_chs, con5_chs, pool1_chs = model_size
stride = 2 if downsample else 1
padding = 'VALID' if downsample else 'SAME'
if downsample == False:
conv1 = conv2d(input, con1_chs, filter_size=1, padding='SAME', act='relu')
conv1 = batch_norm(conv1)
conv31 = conv2d(input, con31_chs, filter_size=1, padding='SAME', act='relu')
conv31 = batch_norm(conv31)
conv3 = conv2d(conv31, con3_chs, filter_size=3, stride = stride, padding=padding, act='relu')
conv3 = batch_norm(conv3)
conv51 = conv2d(input, con51_chs, filter_size=1, padding='SAME', act='relu')
conv51 = batch_norm(conv51)
conv5 = conv2d(conv51, con5_chs, filter_size=3, padding='SAME', act='relu')
conv5 = batch_norm(conv5)
conv5 = conv2d(conv5, con5_chs, filter_size=3, stride = stride, padding=padding, act='relu')
conv5 = batch_norm(conv5)
pool1 = pool2d(input, pool_size=3, pool_stride=stride, pool_padding=padding, pool_type='max')
convp = conv2d(pool1, pool1_chs, filter_size=1, padding='SAME', act='relu')
convp = batch_norm(convp)
if downsample:
return concat([conv3, conv5, convp], axis=1)
return concat([conv1, conv3, conv5, convp], axis=1)
def InceptionV3_ModelB(self, input, model_size, downsample=False):
input_chs, con1_chs, con31_chs, con3_chs, con51_chs, con5_chs, pool1_chs = model_size
stride = 2 if downsample else 1
padding = 'VALID' if downsample else 'SAME'
pool1 = pool2d(input, pool_size=3, pool_stride=stride, pool_padding=padding, pool_type='max')
convp = conv2d(pool1, pool1_chs, filter_size=1, padding='SAME', act='relu')
convp = batch_norm(convp)
if downsample:
conv31 = conv2d(input, con31_chs, filter_size=1, padding='SAME', act='relu')
conv31 = batch_norm(conv31)
conv3 = conv2d(conv31, con3_chs, filter_size=3, stride=stride, padding=padding, act='relu')
conv3 = batch_norm(conv3)
conv51 = conv2d(input, con51_chs, filter_size=1, padding='SAME', act='relu')
conv51 = batch_norm(conv51)
conv5 = conv2d(conv51, con5_chs, filter_size=(1, 7), padding='SAME', act='relu')
conv5 = batch_norm(conv5)
conv5 = conv2d(conv5, con5_chs, filter_size=(7, 1), padding='SAME', act='relu')
conv5 = batch_norm(conv5)
conv5 = conv2d(conv5, con5_chs, filter_size=3, stride=stride, padding=padding, act='relu')
conv5 = batch_norm(conv5)
else:
conv1 = conv2d(input, con1_chs, filter_size=1, padding='SAME', act='relu')
conv1 = batch_norm(conv1)
conv31 = conv2d(input, con31_chs, filter_size=1, padding='SAME', act='relu')
conv31 = batch_norm(conv31)
conv3 = conv2d(conv31, con3_chs, filter_size=(1, 7), stride=stride, padding=padding, act='relu')
conv3 = batch_norm(conv3)
conv3 = conv2d(conv3, con3_chs, filter_size=(7, 1), stride=stride, padding=padding, act='relu')
conv3 = batch_norm(conv3)
conv51 = conv2d(input, con51_chs, filter_size=1, padding='SAME', act='relu')
conv51 = batch_norm(conv51)
conv5 = conv2d(conv51, con5_chs, filter_size=(1, 7), padding='SAME', act='relu')
conv5 = batch_norm(conv5)
conv5 = conv2d(conv5, con5_chs, filter_size=(7, 1), padding='SAME', act='relu')
conv5 = batch_norm(conv5)
conv5 = conv2d(conv5, con5_chs, filter_size=(1, 7), padding='SAME', act='relu')
conv5 = batch_norm(conv5)
conv5 = conv2d(conv5, con5_chs, filter_size=(7, 1), padding='SAME', act='relu')
conv5 = batch_norm(conv5)
if downsample:
return concat([conv3, conv5, convp], axis=1)
return concat([conv1, conv3, conv5, convp], axis=1)
def InceptionV3_ModelC(self, input, model_size):
input_chs, con1_chs, con31_chs, con3_chs, con51_chs, con5_chs, pool1_chs = model_size
pool1 = pool2d(input, pool_size=3, pool_stride=1, pool_padding='SAME', pool_type='max')
convp = conv2d(pool1, pool1_chs, filter_size=1, padding='SAME', act='relu')
convp = batch_norm(convp)
conv1 = conv2d(input, con1_chs, filter_size=1, padding='SAME', act='relu')
conv1 = batch_norm(conv1)
conv30 = conv2d(input, con31_chs, filter_size=1, padding='SAME', act='relu')
conv30 = batch_norm(conv30)
conv31 = conv2d(conv30, con3_chs, filter_size=(1, 3), stride=1, padding='SAME', act='relu')
conv31 = batch_norm(conv31)
conv32 = conv2d(conv30, con3_chs, filter_size=(3, 1), stride=1, padding='SAME', act='relu')
conv32 = batch_norm(conv32)
conv3 = concat([conv31,conv32],axis=1)
conv50 = conv2d(input, con51_chs, filter_size=1, padding='SAME', act='relu')
conv50 = batch_norm(conv50)
conv50 = conv2d(conv50, con51_chs, filter_size=3, padding='SAME', act='relu')
conv50 = batch_norm(conv50)
conv51 = conv2d(conv50, con5_chs, filter_size=(1, 3), padding='SAME', act='relu')
conv51 = batch_norm(conv51)
conv52 = conv2d(conv50, con5_chs, filter_size=(3, 1), padding='SAME', act='relu')
conv52 = batch_norm(conv52)
conv5 = concat([conv51, conv52], axis=1)
return concat([conv1, conv3, conv5, convp], axis=1)
def InceptionV1_Out(self, input, name=None):
pool = pool2d(input, pool_size=5, pool_stride=3, pool_type='max', pool_padding='VALID')
conv1 = conv2d(pool, 128, filter_size=1, padding='SAME', act='relu')
conv1 = batch_norm(conv1)
conv2 = conv2d(conv1, 128, filter_size=1, padding='SAME', act='relu')
conv2 = batch_norm(conv2)
flat = flatten(conv2, axis=1)
dp = dropout(flat, 0.3)
output = fc(dp, Labels_nums, act='softmax',name=name)
return output
def get_Net(self):
# region conv pool
conv1 = conv2d(self.image, Conv1_chs, filter_size=3, stride=2, padding='VALID', act='relu')
conv1 = batch_norm(conv1)
conv2 = conv2d(conv1, Conv2_chs, filter_size=3, padding='VALID', act='relu')
conv2 = batch_norm(conv2)
conv3 = conv2d(conv2, Conv3_chs, filter_size=3, padding='SAME', act='relu')
conv3 = batch_norm(conv3)
pool1 = pool2d(conv3, pool_size=3, pool_stride=2, pool_type='max', pool_padding='SAME')
conv4 = conv2d(pool1, Conv4_chs, filter_size=3, padding='VALID', act='relu')
conv4 = batch_norm(conv4)
conv5 = conv2d(conv4, Conv5_chs, filter_size=3, stride=2, padding='VALID', act='relu')
conv5 = batch_norm(conv5)
conv6 = conv2d(conv5, Conv6_chs, filter_size=3, stride=1, padding='SAME', act='relu')
conv6 = batch_norm(conv6)
# endregion
# region inception3
inception3a = self.InceptionV3_ModelA(conv6, Icp3a_size)
inception3b = self.InceptionV3_ModelA(inception3a, Icp3b_size)
inception3c = self.InceptionV3_ModelA(inception3b, Icp3c_size, downsample=True)
# endregion
# region inception3
inception5a = self.InceptionV3_ModelB(inception3c, Icp5a_size)
inception5b = self.InceptionV3_ModelB(inception5a, Icp5b_size)
inception5c = self.InceptionV3_ModelB(inception5b, Icp5c_size)
inception5d = self.InceptionV3_ModelB(inception5c, Icp5d_size)
auxout = self.InceptionV1_Out(inception5d, 'auxout')
inception5e = self.InceptionV3_ModelB(inception5d, Icp5e_size,downsample=True)
# endregion
# region inception5
inception2a = self.InceptionV3_ModelC(inception5e, Icp2a_size)
inception2b = self.InceptionV3_ModelC(inception2a, Icp2b_size)
# endregion
# region output
pool = pool2d(inception2b, pool_size=8, pool_stride=1, pool_type='max', pool_padding='VALID')
flat = flatten(pool, axis=1)
dp = dropout(flat, 0.4)
output = fc(dp, Labels_nums, act='softmax',name='output')
# endregion
if self.structShow:
print(conv1.name, conv1.shape)
print(conv2.name, conv2.shape)
print(conv3.name, conv3.shape)
print(pool1.name, pool1.shape)
print(conv4.name, conv4.shape)
print(conv5.name, conv5.shape)
print(conv6.name, conv6.shape)
print(inception3a.name, inception3a.shape)
print(inception3b.name, inception3b.shape)
print(inception3c.name, inception3c.shape)
print(inception5a.name, inception5a.shape)
print(inception5b.name, inception5b.shape)
print(inception5c.name, inception5c.shape)
print(inception5d.name, inception5d.shape)
print(inception5e.name, inception5e.shape)
print(inception2a.name, inception2a.shape)
print(inception2b.name, inception2b.shape)
print(pool.name, pool.shape)
print(flat.name, flat.shape)
print(output.name, output.shape)
# if self.trainModel == True:
# return [output, auxout]
# return output
return [output, auxout]
def train():
net = InceptionV3(structShow=True)
image, label, [predict, predict1] = net.image, net.label, net.predict
feeder = fluid.DataFeeder(place=place, feed_list=[image, label])
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_reader = MyDataset(Data_path, batch_size=Batch_size, files_list=train_list).dataset_reader()
val_reader = MyDataset(Data_path, batch_size=Batch_size, files_list=val_list).dataset_reader()
loss = cross_entropy(input=predict, label=label)
loss1 = cross_entropy(input=predict1, label=label)
loss_mean = mean(loss)
loss1_mean = mean(loss1)
loss_total = loss_mean * 0.7 + loss1_mean * 0.3
acc = accuracy(input=predict, label=label,k=1)
optimizer = fluid.optimizer.AdamOptimizer(learning_rate=Learning_rate)
optimizer.minimize(loss_total)
val_program = fluid.default_main_program().clone(for_test=True)
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
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_num, data in enumerate(train_reader()):
train_loss, train_acc = exe.run(program=fluid.default_main_program(), # 運行主程序
feed=feeder.feed(data), # 給模型喂入數據
fetch_list=[loss_total, acc]) # fetch 誤差、準確率
train_sum_loss += train_loss[0]
train_sum_acc += train_acc[0]
process_show(batch_num + 1, Train_num / Batch_size, train_acc, train_loss, prefix='train:')
for batch_num, data in enumerate(val_reader()):
val_loss, val_acc = exe.run(program=val_program, # 執行訓練程序
feed=feeder.feed(data), # 喂入數據
fetch_list=[loss_total, acc]) # fetch 誤差、準確率
val_sum_loss += val_loss[0]
val_sum_acc += val_acc[0]
process_show(batch_num + 1, Val_num / Batch_size, val_acc, val_loss, prefix='train:')
train_sum_loss /= (Train_num // Batch_size)
train_sum_acc /= (Train_num // Batch_size)
val_sum_loss /= (Val_num // Batch_size)
val_sum_acc /= (Val_num // Batch_size)
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_paddle))
best_loss = val_sum_loss
best_loss_epoch = epoch + 1
fluid.io.save_inference_model(Model_file_paddle, # 保存推理model的路徑
['image'], # 推理（inference）需要 feed 的數據
[predict], # 保存推理（inference）結果的 Variables
exe) # executor 保存 inference model
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
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):
# 讀取類標籤字典，只取第一個逗號前的信息
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