6.2使用pytorch搭建ResNet并基于迁移学习训练
参考文献
K. He, X. Zhang, S. Ren and J. Sun, “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90.
霹雳吧啦Wz 6.2使用pytorch搭建ResNet并基于迁移学习训练
霹雳吧啦Wz GitHub deep-learning-for-image-processing
花分类数据集下载
(1)在data_set文件夹下创建新文件夹"flower_data"
print(image_path) # ...\PyCharm\data_set\flower_data
(2)点击链接下载花分类数据集 http://download.tensorflow.org/example_images/flower_photos.tgz
(3)解压数据集到flower_data文件夹下
(4)执行"split_data.py"脚本自动将数据集划分成训练集train和验证集val
split_data.py
import os
from shutil import copy, rmtree
import random
def mk_file(file_path: str):
if os.path.exists(file_path):
# 如果文件夹存在,则先删除原文件夹在重新创建
rmtree(file_path)
os.makedirs(file_path)
def main():
# 保证随机可复现
random.seed(0)
# 将数据集中10%的数据划分到验证集中
split_rate = 0.1
# 指向你解压后的flower_photos文件夹
cwd = os.getcwd()
data_root = os.path.join(cwd, "flower_data")
origin_flower_path = os.path.join(data_root, "flower_photos")
assert os.path.exists(origin_flower_path), "path '{}' does not exist.".format(origin_flower_path)
flower_class = [cla for cla in os.listdir(origin_flower_path)
if os.path.isdir(os.path.join(origin_flower_path, cla))]
# 建立保存训练集的文件夹
train_root = os.path.join(data_root, "train")
mk_file(train_root)
for cla in flower_class:
# 建立每个类别对应的文件夹
mk_file(os.path.join(train_root, cla))
# 建立保存验证集的文件夹
val_root = os.path.join(data_root, "val")
mk_file(val_root)
for cla in flower_class:
# 建立每个类别对应的文件夹
mk_file(os.path.join(val_root, cla))
for cla in flower_class:
cla_path = os.path.join(origin_flower_path, cla)
images = os.listdir(cla_path)
num = len(images)
# 随机采样验证集的索引
eval_index = random.sample(images, k=int(num*split_rate))
for index, image in enumerate(images):
if image in eval_index:
# 将分配至验证集中的文件复制到相应目录
image_path = os.path.join(cla_path, image)
new_path = os.path.join(val_root, cla)
copy(image_path, new_path)
else:
# 将分配至训练集中的文件复制到相应目录
image_path = os.path.join(cla_path, image)
new_path = os.path.join(train_root, cla)
copy(image_path, new_path)
print("\r[{}] processing [{}/{}]".format(cla, index+1, num), end="") # processing bar
print()
print("processing done!")
if __name__ == '__main__':
main()
model.py: ResNet模型搭建
import torch.nn as nn
import torch
# 18-layer and 34-layer residual残差结构
class BasicBlock(nn.Module):
# 残差结构中主分支所采用的卷积核个数有没有发生变化
expansion = 1 # 18-layer and 34-layer 第一层和第二层卷积核个数一样
# in_channel输入特征矩阵深度;out_channel输出特征矩阵深度 主分支上卷积核的个数;kernel_size卷积核大小
# stride=1实线残差结构 output=(input-3+2*1)/1+1=input
# stride=2虚线残差结构 output=(input-3+2*1)/2+1=input/2+0.5=input/2(向下取整)
def __init__(self, in_channel, out_channel, stride=1, downsample=None, **kwargs):
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(out_channel)
self.relu = nn.ReLU()
self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(out_channel)
self.downsample = downsample
def forward(self, x):
identity = x
if self.downsample is not None:
identity = self.downsample(x)
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out += identity
out = self.relu(out)
return out
# 50-layer 101-layer and 152-layer residual残差结构
class Bottleneck(nn.Module):
"""
注意:原论文中,在虚线残差结构的主分支上,第一个1x1卷积层的步距是2,第二个3x3卷积层步距是1。
但在pytorch官方实现过程中是第一个1x1卷积层的步距是1,第二个3x3卷积层步距是2,
这么做的好处是能够在top1上提升大概0.5%的准确率。
可参考Resnet v1.5 https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch
"""
expansion = 4 #50 101 152-layer 第三层卷积核个数是第一层、第二层的四倍
def __init__(self, in_channel, out_channel, stride=1, downsample=None,
groups=1, width_per_group=64):
super(Bottleneck, self).__init__()
width = int(out_channel * (width_per_group / 64.)) * groups
self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=width,
kernel_size=1, stride=1, bias=False) # squeeze channels
self.bn1 = nn.BatchNorm2d(width)
# -----------------------------------------
self.conv2 = nn.Conv2d(in_channels=width, out_channels=width, groups=groups,
kernel_size=3, stride=stride, bias=False, padding=1)
self.bn2 = nn.BatchNorm2d(width)
# -----------------------------------------
self.conv3 = nn.Conv2d(in_channels=width, out_channels=out_channel*self.expansion,
kernel_size=1, stride=1, bias=False) # unsqueeze channels
self.bn3 = nn.BatchNorm2d(out_channel*self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
def forward(self, x):
identity = x
if self.downsample is not None:
identity = self.downsample(x)
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
out += identity
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self,
block,
blocks_num, #如果是34-layer 那就是[3,4,6,3]
num_classes=5, #训练集分类个数 num_classes=1000
include_top=True,
groups=1,
width_per_group=64):
super(ResNet, self).__init__()
self.include_top = include_top
self.in_channel = 64
self.groups = groups
self.width_per_group = width_per_group
# 3:输入特征矩阵深度为3 RGB图像;为了让输出特征矩阵高宽减半将padding设置为3 7//2=3
self.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2,
padding=3, bias=False)
self.bn1 = nn.BatchNorm2d(self.in_channel)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
# conv2_x conv3_x conv4_x conv5_x 所对应的残差结构
self.layer1 = self._make_layer(block, 64, blocks_num[0])
self.layer2 = self._make_layer(block, 128, blocks_num[1], stride=2)
self.layer3 = self._make_layer(block, 256, blocks_num[2], stride=2)
self.layer4 = self._make_layer(block, 512, blocks_num[3], stride=2)
if self.include_top:
self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) # output size = (1, 1)
self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
def _make_layer(self, block, channel, block_num, stride=1):
downsample = None
if stride != 1 or self.in_channel != channel * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(channel * block.expansion))
#接下来构建conv3_x所对应一系列残差结构的第一层
layers = []
layers.append(block(self.in_channel,
channel,
downsample=downsample,
stride=stride,
groups=self.groups,
width_per_group=self.width_per_group))
self.in_channel = channel * block.expansion
for _ in range(1, block_num):
layers.append(block(self.in_channel,
channel,
groups=self.groups,
width_per_group=self.width_per_group))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
if self.include_top:
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.fc(x)
return x
def resnet34(num_classes=5, include_top=True): #num_classes=1000
# https://download.pytorch.org/models/resnet34-333f7ec4.pth
return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)
def resnet50(num_classes=1000, include_top=True):
# https://download.pytorch.org/models/resnet50-19c8e357.pth
return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)
def resnet101(num_classes=1000, include_top=True):
# https://download.pytorch.org/models/resnet101-5d3b4d8f.pth
return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top)
def resnext50_32x4d(num_classes=1000, include_top=True):
# https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth
groups = 32
width_per_group = 4
return ResNet(Bottleneck, [3, 4, 6, 3],
num_classes=num_classes,
include_top=include_top,
groups=groups,
width_per_group=width_per_group)
def resnext101_32x8d(num_classes=1000, include_top=True):
# https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth
groups = 32
width_per_group = 8
return ResNet(Bottleneck, [3, 4, 23, 3],
num_classes=num_classes,
include_top=include_top,
groups=groups,
width_per_group=width_per_group)
train.py: 训练脚本
import os
import sys
import json
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import transforms, datasets
from tqdm import tqdm
from model import resnet34
#import torchvision.models.resnet
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print("using {} device.".format(device))
data_transform = {
"train": transforms.Compose([transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
"val": transforms.Compose([transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])}
data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path
#print(data_root) #D:\software\PyCharm
image_path = os.path.join(data_root, "data_set", "flower_data") # flower data set path
#print(image_path) #D:\software\PyCharm\data_set\flower_data
assert os.path.exists(image_path), "{} path does not exist.".format(image_path)
train_dataset = datasets.ImageFolder(root=os.path.join(image_path, "train"),
transform=data_transform["train"])
train_num = len(train_dataset)
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
batch_size = 4
#batch_size = 16 跑不动
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8]) # number of workers
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size, shuffle=True,
num_workers=nw)
validate_dataset = datasets.ImageFolder(root=os.path.join(image_path, "val"),
transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=batch_size, shuffle=False,
num_workers=nw)
print("using {} images for training, {} images for validation.".format(train_num,
val_num))
net = resnet34()
# load pretrain weights
# download url: https://download.pytorch.org/models/resnet34-333f7ec4.pth
# -----------------------------------------迁移学习
# model_weight_path = "./resnet34-pre.pth"
model_weight_path = "D:/software/PyCharm/resnet34-pre.pth"
assert os.path.exists(model_weight_path), "file {} does not exist.".format(model_weight_path)
net.load_state_dict(torch.load(model_weight_path, map_location='cpu'))
# for param in net.parameters():
# param.requires_grad = False
# change fc layer structure
in_channel = net.fc.in_features
net.fc = nn.Linear(in_channel, 5) #花分类 类别个数为5
# -----------------------------------------迁移学习
net.to(device)
# define loss function
loss_function = nn.CrossEntropyLoss()
# construct an optimizer
params = [p for p in net.parameters() if p.requires_grad]
optimizer = optim.Adam(params, lr=0.0001)
epochs = 1
#epochs = 3
best_acc = 0.0
# save_path = './resNet34.pth'
save_path = 'D:/software/PyCharm/resnet34-pre.pth'
train_steps = len(train_loader)
for epoch in range(epochs):
# train
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader, file=sys.stdout)
for step, data in enumerate(train_bar):
images, labels = data
optimizer.zero_grad()
logits = net(images.to(device))
loss = loss_function(logits, labels.to(device))
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch + 1,
epochs,
loss)
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
val_bar = tqdm(validate_loader, file=sys.stdout)
for val_data in val_bar:
val_images, val_labels = val_data
outputs = net(val_images.to(device))
# loss = loss_function(outputs, test_labels)
predict_y = torch.max(outputs, dim=1)[1]
acc += torch.eq(predict_y, val_labels.to(device)).sum().item()
val_bar.desc = "valid epoch[{}/{}]".format(epoch + 1,
epochs)
val_accurate = acc / val_num
print('[epoch %d] train_loss: %.3f val_accuracy: %.3f' %
(epoch + 1, running_loss / train_steps, val_accurate))
if val_accurate > best_acc:
best_acc = val_accurate
torch.save(net.state_dict(), save_path)
print('Finished Training')
if __name__ == '__main__':
main()
#import torch
#print(torch.__version__)
实验结果
using cuda:0 device.
Using 4 dataloader workers every process
using 3306 images for training, 364 images for validation.
train epoch[1/1] loss:1.320: 100%|██████████| 827/827 [00:43<00:00, 18.90it/s]
valid epoch[1/1]: 100%|██████████| 91/91 [00:04<00:00, 20.90it/s]
[epoch 1] train_loss: 0.720 val_accuracy: 0.849
Finished Training
predict.py: 单张图像预测脚本
import os
import json
import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
from model import resnet34
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
data_transform = transforms.Compose(
[transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
# load image
img_path = "D:/software/PyCharm/data_set/flower_data/train/tulips/112428665_d8f3632f36_n.jpg"
assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
img = Image.open(img_path)
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
# read class_indict
json_path = 'D:/software/PyCharm/PycharmProjects/pythonproject/class_indices.json'
assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path)
json_file = open(json_path, "r")
class_indict = json.load(json_file)
# create model
model = resnet34(num_classes=5).to(device)
# load model weights
weights_path = "D:/software/PyCharm/resnet34-pre.pth"
assert os.path.exists(weights_path), "file: '{}' dose not exist.".format(weights_path)
model.load_state_dict(torch.load(weights_path, map_location=device))
# prediction
model.eval()
with torch.no_grad():
# predict class
output = torch.squeeze(model(img.to(device))).cpu()
predict = torch.softmax(output, dim=0)
predict_cla = torch.argmax(predict).numpy()
print_res = "class: {} prob: {:.3}".format(class_indict[str(predict_cla)],
predict[predict_cla].numpy())
plt.title(print_res)
for i in range(len(predict)):
print("class: {:10} prob: {:.3}".format(class_indict[str(i)],
predict[i].numpy()))
plt.show()
if __name__ == '__main__':
main()
实验结果
class: daisy prob: 2.29e-11
class: dandelion prob: 4.75e-06
class: roses prob: 6.1e-07
class: sunflowers prob: 6.95e-07
class: tulips prob: 1.0
batch_predict.py: 批量图像预测脚本
import os
import json
import torch
from PIL import Image
from torchvision import transforms
from model import resnet34
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
data_transform = transforms.Compose(
[transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
# load image
# 指向需要遍历预测的图像文件夹
imgs_root = "/data/imgs"
assert os.path.exists(imgs_root), f"file: '{imgs_root}' dose not exist."
# 读取指定文件夹下所有jpg图像路径
img_path_list = [os.path.join(imgs_root, i) for i in os.listdir(imgs_root) if i.endswith(".jpg")]
# read class_indict
json_path = './class_indices.json'
assert os.path.exists(json_path), f"file: '{json_path}' dose not exist."
json_file = open(json_path, "r")
class_indict = json.load(json_file)
# create model
model = resnet34(num_classes=5).to(device)
# load model weights
weights_path = "./resNet34.pth"
assert os.path.exists(weights_path), f"file: '{weights_path}' dose not exist."
model.load_state_dict(torch.load(weights_path, map_location=device))
# prediction
model.eval()
batch_size = 8 # 每次预测时将多少张图片打包成一个batch
with torch.no_grad():
for ids in range(0, len(img_path_list) // batch_size):
img_list = []
for img_path in img_path_list[ids * batch_size: (ids + 1) * batch_size]:
assert os.path.exists(img_path), f"file: '{img_path}' dose not exist."
img = Image.open(img_path)
img = data_transform(img)
img_list.append(img)
# batch img
# 将img_list列表中的所有图像打包成一个batch
batch_img = torch.stack(img_list, dim=0)
# predict class
output = model(batch_img.to(device)).cpu()
predict = torch.softmax(output, dim=1)
probs, classes = torch.max(predict, dim=1)
for idx, (pro, cla) in enumerate(zip(probs, classes)):
print("image: {} class: {} prob: {:.3}".format(img_path_list[ids * batch_size + idx],
class_indict[str(cla.numpy())],
pro.numpy()))
if __name__ == '__main__':
main()
认真是一种态度更是一种责任