LiuYuanchi
/
FCN-test
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

修改train.py

This commit is contained in:
LiuYuanchi 2024-04-01 21:39:34 +08:00
parent f42c31ef6c
commit b80ddcbdb1
3 changed files with 104 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -7,3 +7,5 @@ __pycache__
assets
bag_data
bag_data_msk
logs
checkpoints

25
datas/data.md Normal file
View File

@ -0,0 +1,25 @@
# 原始数据
```
train(model_name='FCN8s', epo_num=50, show_vgg_params=False, loss_func='bce', optimizer='sgd', lr=0.02, momentum=0.7)
```
log1.txt
1.png
epoch train loss = 0.016117, epoch test loss = 0.290732, Time 00:00:27
# 学习率对于FCN网络影响
```
train(model_name='FCN8s', epo_num=11, show_vgg_params=False, loss_func='bce', optimizer='sgd', lr=0.01, momentum=0.7)
train(model_name='FCN8s', epo_num=11, show_vgg_params=False, loss_func='bce', optimizer='sgd', lr=0.02, momentum=0.7)
train(model_name='FCN8s', epo_num=11, show_vgg_params=False, loss_func='bce', optimizer='sgd', lr=0.03, momentum=0.7)
```
log2.txt
1.png
epoch train loss = 0.066093, epoch test loss = 0.134848, Time 00:00:23
epoch train loss = 0.048717, epoch test loss = 0.110684, Time 00:00:23
epoch train loss = 0.047222, epoch test loss = 0.102705, Time 00:00:23

130
train.py
View File

@ -1,99 +1,101 @@
from datetime import datetime
import matplotlib.pyplot as plt
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import visdom
from BagData import test_dataloader, train_dataloader
from FCN import FCN8s, FCN16s, FCN32s, FCNs, VGGNet
def train(model_name='FCN8s', epo_num=50, show_vgg_params=False, loss_func='bce', optimizer='sgd', lr=1e-2, momentum=0.7):
vis = visdom.Visdom()
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
def train(epo_num=50, show_vgg_params=False):
# 选择不同的VGGNet和FCN模型
vgg_model_options = {'VGG16': VGGNet(requires_grad=True, show_params=show_vgg_params),
'VGG19': VGGNet(model='vgg19', requires_grad=True, show_params=show_vgg_params)}
fcn_model_options = {'FCN8s': FCN8s(pretrained_net=vgg_model_options['VGG16'], n_class=2),
'FCN16s': FCN16s(pretrained_net=vgg_model_options['VGG16'], n_class=2),
'FCN32s': FCN32s(pretrained_net=vgg_model_options['VGG16'], n_class=2)}
vis = visdom.Visdom() # 可视化工具
# 根据输入选择模型
if model_name in fcn_model_options:
fcn_model = fcn_model_options[model_name]
else:
raise ValueError(f"Invalid model name: {model_name}")
fcn_model = fcn_model.to(device)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # 使用gpu或cpu，若安装cuda默认使用gpu
"""调用FCN.py中不同的vgg网络（自选一个）,进行定量实验分析"""
vgg_model = VGGNet(requires_grad=True, show_params=show_vgg_params) # backbone网络，用于特征提取
"""调用FCN.py中不同的FCN网络（自选一个）,进行定量实验分析"""
fcn_model = FCNs(pretrained_net=vgg_model, n_class=2) # Architecture结构，用于分割
fcn_model = fcn_model.to(device) # 将模型加载至指定gpu
"""更改损失函数为交叉熵nn.CELoss(), 进行定量实验分析"""
criterion = nn.BCELoss().to(device)
"""更改模型优化器，如：adam等（自选一个），并调整学习率lr和momentum参数,进行定量实验分析"""
optimizer = optim.SGD(fcn_model.parameters(), lr=1e-2, momentum=0.7)
# 选择不同的损失函数
if loss_func == 'bce':
criterion = nn.BCELoss().to(device)
elif loss_func == 'ce':
criterion = nn.CrossEntropyLoss().to(device)
all_train_iter_loss = [] # 训练loss存储list
all_test_iter_loss = [] # 测试loss存储list
# 选择不同的优化器和学习率、动量
if optimizer == 'sgd':
opt = optim.SGD(fcn_model.parameters(), lr=lr, momentum=momentum)
elif optimizer == 'adam':
opt = optim.Adam(fcn_model.parameters(), lr=lr)
# start timing
prev_time = datetime.now() # 训练起始时间记录
for epo in range(epo_num): # epo_num数据集训练次数
all_train_iter_loss = []
all_test_iter_loss = []
train_loss = 0 #初始化loss
fcn_model.train() # 打开训练模式
for index, (bag, bag_msk) in enumerate(train_dataloader): # 加载数据，bag为数据样本，bag_msk为对应的二进制标签
# bag.shape is torch.Size([4, 3, 160, 160])
# bag_msk.shape is torch.Size([4, 2, 160, 160])
prev_time = datetime.now()
for epo in range(epo_num):
train_loss = 0
fcn_model.train()
for index, (bag, bag_msk) in enumerate(train_dataloader):
bag = bag.to(device)
bag_msk = bag_msk.to(device)
bag = bag.to(device) #数据加载至device上
bag_msk = bag_msk.to(device) #标签加载至device上
optimizer.zero_grad() #优化器梯度清空
output = fcn_model(bag) # 模型forward
output = torch.sigmoid(output) # output.shape is torch.Size([4, 2, 160, 160])
loss = criterion(output, bag_msk) # 计算模型预测与标签之间的损失
loss.backward() # 反向传播
opt.zero_grad()
output = fcn_model(bag)
output = torch.sigmoid(output)
loss = criterion(output, bag_msk)
loss.backward()
iter_loss = loss.item()
all_train_iter_loss.append(iter_loss) #loss添加至存储的list里
train_loss += iter_loss #训练集loss累加
optimizer.step() # 模型参数优化更新
all_train_iter_loss.append(iter_loss)
train_loss += iter_loss
opt.step()
output_np = output.cpu().detach().numpy().copy() # output_np.shape = (4, 2, 160, 160)
output_np = output.cpu().detach().numpy().copy()
output_np = np.argmin(output_np, axis=1)
bag_msk_np = bag_msk.cpu().detach().numpy().copy() # bag_msk_np.shape = (4, 2, 160, 160)
bag_msk_np = bag_msk.cpu().detach().numpy().copy()
bag_msk_np = np.argmin(bag_msk_np, axis=1)
if np.mod(index, 15) == 0:
print('epoch {}, {}/{},train loss is {}'.format(epo, index, len(train_dataloader), iter_loss))
# vis.close()
"""结果可视化"""
# print('epoch {}, {}/{},train loss is {}'.format(epo, index, len(train_dataloader), iter_loss))
vis.images(output_np[:, None, :, :], win='train_pred', opts=dict(title='train prediction'))
vis.images(bag_msk_np[:, None, :, :], win='train_label', opts=dict(title='label'))
vis.line(all_train_iter_loss, win='train_iter_loss',opts=dict(title='train iter loss'))
vis.line(all_train_iter_loss, win='train_iter_loss', opts=dict(title='train iter loss'))
test_loss = 0
fcn_model.eval() # 模型打开测试模式
with torch.no_grad(): # 测试阶段取消梯度
fcn_model.eval()
with torch.no_grad():
for index, (bag, bag_msk) in enumerate(test_dataloader):
bag = bag.to(device)
bag_msk = bag_msk.to(device)
optimizer.zero_grad()
opt.zero_grad()
output = fcn_model(bag)
output = torch.sigmoid(output) # output.shape is torch.Size([4, 2, 160, 160])
output = torch.sigmoid(output)
loss = criterion(output, bag_msk)
iter_loss = loss.item()
all_test_iter_loss.append(iter_loss)
test_loss += iter_loss
output_np = output.cpu().detach().numpy().copy() # output_np.shape = (4, 2, 160, 160)
output_np = output.cpu().detach().numpy().copy()
output_np = np.argmin(output_np, axis=1)
bag_msk_np = bag_msk.cpu().detach().numpy().copy() # bag_msk_np.shape = (4, 2, 160, 160)
bag_msk_np = bag_msk.cpu().detach().numpy().copy()
bag_msk_np = np.argmin(bag_msk_np, axis=1)
if np.mod(index, 15) == 0:
print(r'Testing... Open http://localhost:8097/ to see test result.')
# vis.close()
# print(r'Testing... Open http://localhost:8097/ to see test result.')
vis.images(output_np[:, None, :, :], win='test_pred', opts=dict(title='test prediction'))
vis.images(bag_msk_np[:, None, :, :], win='test_label', opts=dict(title='label'))
vis.line(all_test_iter_loss, win='test_iter_loss', opts=dict(title='test iter loss'))
"""显示模型运行时间"""
cur_time = datetime.now()
h, remainder = divmod((cur_time - prev_time).seconds, 3600)
m, s = divmod(remainder, 60)
@ -101,14 +103,26 @@ def train(epo_num=50, show_vgg_params=False):
prev_time = cur_time
print('epoch train loss = %f, epoch test loss = %f, %s'
%(train_loss/len(train_dataloader), test_loss/len(test_dataloader), time_str))
"""每5个epoch保存一次模型到checkpoints路径"""
if np.mod(epo, 5) == 0:
torch.save(fcn_model, 'checkpoints/fcn_model_{}.pt'.format(epo))
print('saveing checkpoints/fcn_model_{}.pt'.format(epo))
% (train_loss / len(train_dataloader), test_loss / len(test_dataloader), time_str))
# 每10个训练轮次保存一次检查点
if np.mod(epo, 10) == 0:
checkpoint_name = f'checkpoints/fcn_model_{model_name}_ep{epo}_lr{lr}_mom{momentum}.pt'
torch.save(fcn_model, checkpoint_name)
print(f'Saving checkpoint: {checkpoint_name}')
if __name__ == "__main__":
# 调用训练函数,并修改不同的参数
train(epo_num=100, show_vgg_params=False) #调用训练函数开始训练，训练epoch数为100
## 1
#train(model_name='FCN8s', epo_num=11, show_vgg_params=False, loss_func='bce', optimizer='sgd', lr=0.02, momentum=0.7)
## 2
# train(model_name='FCN8s', epo_num=11, show_vgg_params=False, loss_func='bce', optimizer='sgd', lr=0.01, momentum=0.7)
# train(model_name='FCN8s', epo_num=11, show_vgg_params=False, loss_func='bce', optimizer='sgd', lr=0.02, momentum=0.7)
# train(model_name='FCN8s', epo_num=11, show_vgg_params=False, loss_func='bce', optimizer='sgd', lr=0.03, momentum=0.7)
train(model_name='FCN8s', epo_num=11, show_vgg_params=False, loss_func='bce', optimizer='sgd', lr=0.05, momentum=0.7)
#train(model_name='FCN16s', epo_num=11, show_vgg_params=False, loss_func='ce', optimizer='adam', lr=1e-3)
#train(model_name='FCN32s', epo_num=100, show_vgg_params=False, loss_func='bce', optimizer='sgd', lr=0.01, momentum=0.5)