一、安装配置环境

1、准备工作

代码地址

GitHub - bubbliiiing/classification-pytorch: 这是各个主干网络分类模型的源码，可以用于训练自己的分类模型。

# 创建环境
conda create -n ptorch1_2_0 python=3.6
# 然后启动
conda install pytorch==1.2.0 torchvision==0.4.0 cudatoolkit=10.0 -c pytorch
pip install scipy==1.2.1 numpy==1.17.0 matplotlib==3.1.2 opencv_python==4.1.2.30 tqdm==4.60.0 Pillow==8.2.0 h5py==2.10.0

下载好后 他的那个数据集 按他那个配置，然后在项目根目录下运行

python txt_annotation.py 

生成对应的 txt 文件

2、遇到的问题

1、

ImportError: TensorBoard logging requires TensorBoard with Python summary writer installed. This should be available in 1.14 or above.

解决

pip install tensorboard

2、

ModuleNotFoundError: No module named 'past'

解决办法

pip install future

3、

ImportError: libSM.so.6: cannot open shared object file: No such file or directory
# 和
ImportError: libXrender.so.1: cannot open shared object file: No such file or directory

解决

apt-get install libsm6
apt-get install libxrender1

二、debug 记录 

1、train_lines  

 val_lines

 2、 show_config

----------------------------------------------------------------------
|                     keys |                                   values|
----------------------------------------------------------------------
|              num_classes |                                        2|
|                 backbone |                              mobilenetv2|
|               model_path |                                         |
|              input_shape |                               [224, 224]|
|               Init_Epoch |                                        0|
|             Freeze_Epoch |                                       50|
|           UnFreeze_Epoch |                                      200|
|        Freeze_batch_size |                                       32|
|      Unfreeze_batch_size |                                       32|
|             Freeze_Train |                                     True|
|                  Init_lr |                                     0.01|
|                   Min_lr |                                   0.0001|
|           optimizer_type |                                      sgd|
|                 momentum |                                      0.9|
|            lr_decay_type |                                      cos|
|              save_period |                                       10|
|                 save_dir |                                     logs|
|              num_workers |                                        4|
|                num_train |                                    20000|
|                  num_val |                                     5000|
----------------------------------------------------------------------

3、 optimizer

4、打印日志

Start Train
Epoch 1/200:   0%|                        | 0/625 [00:00<?, ?it/s<class 'dict'>]

utils_fit.py --- 19

    if local_rank == 0:print('Start Train')pbar = tqdm(total=epoch_step,desc=f'Epoch {epoch + 1}/{Epoch}',postfix=dict,mininterval=0.3)

5、

gen

 batch

 

三、其它

1、打印模型 model， 这个应该是 backbone

MobileNetV2((features): Sequential((0): ConvBNReLU((0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)(2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(2): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(3): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(144, 144, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=144, bias=False)(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(4): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(144, 144, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=144, bias=False)(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(144, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(5): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(6): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(7): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(192, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=192, bias=False)(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(8): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(9): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(10): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(11): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(12): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(13): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(14): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(576, 576, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=576, bias=False)(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(576, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(15): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(16): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(17): InvertedResidual((conv): Sequential((0): ConvBNReLU((0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(1): ConvBNReLU((0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True))(2): Conv2d(960, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)(3): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(18): ConvBNReLU((0): Conv2d(320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU6(inplace=True)))(classifier): Sequential((0): Dropout(p=0.2, inplace=False)(1): Linear(in_features=1280, out_features=2, bias=True))
)

2、数据集导入与建立

train.py --- 384  397

train_dataset   = DataGenerator(train_lines, input_shape, True)
val_dataset     = DataGenerator(val_lines, input_shape, False)gen             = DataLoader(train_dataset, shuffle=shuffle, batch_size=batch_size, num_workers=num_workers, pin_memory=True, drop_last=True, collate_fn=detection_collate, sampler=train_sampler)
gen_val         = DataLoader(val_dataset, shuffle=shuffle, batch_size=batch_size, num_workers=num_workers, pin_memory=True,drop_last=True, collate_fn=detection_collate, sampler=val_sampler)

3、 开始训练模型

train.py --- 404

for epoch in range(Init_Epoch, UnFreeze_Epoch):

训练过程在  train.py --- 452

fit_one_epoch(model_train, model, loss_history, optimizer, epoch, epoch_step, epoch_step_val, gen, gen_val, UnFreeze_Epoch, Cuda, fp16, scaler, save_period, save_dir, local_rank)

 

4、调整学习率

train.py --- 450

set_optimizer_lr(optimizer, lr_scheduler_func, epoch)

5、前向传播的入口

utils_fit.py --- 40

outputs     = model_train(images)