rock数据集ResNet34实现「建议收藏」

# -*-coding:utf-8-*-
import torch.nn as nn
import torch
class BasicBlock(nn.Module):
expansion = 1
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
class Bottleneck(nn.Module):
expansion = 4
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,
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
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)
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))
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=1000, include_top=True):
# 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)

# -*-coding:utf-8-*-
import os
import json
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import transforms, datasets
from tqdm import tqdm
from Resnet_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
image_path = os.path.join(data_root,"data_mining","data_set")  # flower data set path
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)
rock_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in rock_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 = 5
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
model_weight_path = "./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=device))
# 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, 7)
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 = 10
best_acc = 0.0
save_path = './resNet34.pth'
train_steps = len(train_loader)
for epoch in range(epochs):
# train
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader)
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)
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()

C:\ProgramData\Anaconda3\envs\pytorch\python.exe C:/Users/pythonProject/data_mining/ResNet/Resnet_train.py
using cpu device.
Using 5 dataloader workers every process
using 12600 images for training, 1400 images for validation.
train epoch[1/10] loss:0.972100%|██████████| 2520/2520 [1:30:58<00:00,  2.14s/it]
valid epoch[1/10]100%|██████████| 280/280 [02:21<00:00,  2.03it/s]
[epoch 1] train_loss: 0.904  val_accuracy: 0.874
train epoch[2/10] loss:0.833100%|██████████| 2520/2520 [1:33:16<00:00,  2.17s/it]
valid epoch[2/10]100%|██████████| 280/280 [02:22<00:00,  2.06it/s]
0%|          | 0/2520 [00:00<?, ?it/s][epoch 2] train_loss: 0.665  val_accuracy: 0.791
train epoch[3/10] loss:0.884100%|██████████| 2520/2520 [1:30:23<00:00,  2.12s/it]
valid epoch[3/10]100%|██████████| 280/280 [02:20<00:00,  2.07it/s]
[epoch 3] train_loss: 0.588  val_accuracy: 0.938
train epoch[4/10] loss:0.507100%|██████████| 2520/2520 [1:31:15<00:00,  2.15s/it]
valid epoch[4/10]100%|██████████| 280/280 [02:18<00:00,  2.19it/s]
[epoch 4] train_loss: 0.509  val_accuracy: 0.939
train epoch[5/10] loss:0.344100%|██████████| 2520/2520 [1:30:26<00:00,  2.15s/it]
valid epoch[5/10]100%|██████████| 280/280 [02:21<00:00,  2.03it/s]
[epoch 5] train_loss: 0.462  val_accuracy: 0.945
train epoch[6/10] loss:0.258100%|██████████| 2520/2520 [1:30:19<00:00,  2.15s/it]
valid epoch[6/10]100%|██████████| 280/280 [02:19<00:00,  2.12it/s]
[epoch 6] train_loss: 0.416  val_accuracy: 0.874
train epoch[7/10] loss:0.097100%|██████████| 2520/2520 [1:30:09<00:00,  2.11s/it]
valid epoch[7/10]100%|██████████| 280/280 [02:17<00:00,  2.14it/s]
0%|          | 0/2520 [00:00<?, ?it/s][epoch 7] train_loss: 0.382  val_accuracy: 0.933
train epoch[8/10] loss:0.156100%|██████████| 2520/2520 [1:30:48<00:00,  2.17s/it]
valid epoch[8/10]100%|██████████| 280/280 [02:22<00:00,  2.03it/s]
0%|          | 0/2520 [00:00<?, ?it/s][epoch 8] train_loss: 0.337  val_accuracy: 0.938
train epoch[9/10] loss:0.284100%|██████████| 2520/2520 [1:31:23<00:00,  2.27s/it]
valid epoch[9/10]100%|██████████| 280/280 [02:23<00:00,  2.09it/s]
[epoch 9] train_loss: 0.319  val_accuracy: 0.961
train epoch[10/10] loss:0.248100%|██████████| 2520/2520 [1:35:54<00:00,  2.26s/it]
valid epoch[10/10]100%|██████████| 280/280 [02:32<00:00,  1.92it/s]
[epoch 10] train_loss: 0.299  val_accuracy: 0.974
Finished Training