使用 pytorch-lightning 在网络 CNN 模型中实现网络

如何解决使用 pytorch-lightning 在网络 CNN 模型中实现网络

我正在尝试实施 NiN 模型。基本上是尝试从 d2l 复制代码 这是我的代码。

import pandas as pd
import torch
from torch import nn
import torchmetrics
from torchvision import transforms
from torch.utils.data import DataLoader,random_split
import pytorch_lightning as pl
from torchvision.datasets import FashionMNIST
import wandb
from pytorch_lightning.loggers import WandbLogger
wandb.login()

## class definition
class Lightning_nin(pl.LightningModule):
  def __init__(self):
    super().__init__()
    self.accuracy = torchmetrics.Accuracy(top_k=1)
    self.model = nn.Sequential(
                self.nin_block(1,96,kernel_size=11,strides=4,padding=0),nn.MaxPool2d(3,stride=2),self.nin_block(96,256,kernel_size=5,strides=1,padding=2),self.nin_block(256,384,kernel_size=3,padding=1),nn.Dropout(0.5),# There are 10 label classes
                self.nin_block(384,10,nn.AdaptiveAvgPool2d((1,1)),# Transform the four-dimensional output into two-dimensional output with a
                # shape of (batch size,10)
                nn.Flatten())
    for layer in self.model:
      if type(layer) == nn.Linear or type(layer) == nn.Conv2d:
        nn.init.xavier_uniform_(layer.weight)  
  def nin_block(self,in_channels,out_channels,kernel_size,strides,padding):
      return nn.Sequential(
          nn.Conv2d(in_channels,padding),nn.ReLU(),nn.Conv2d(out_channels,kernel_size=1),nn.ReLU())
      
  def forward(self,x):
      x = self.model(x)
      return x
 
  def loss_fn(self,logits,y):
    loss = nn.CrossEntropyLoss()
    return loss(logits,y)
    
  def training_step(self,train_batch,batch_idx):
    X,y = train_batch
    logits = self.forward(X)
    loss = self.loss_fn(logits,y)
    self.log('train_loss',loss)
    m = nn.Softmax(dim=1)
    output = m(logits)
    self.log('train_acc',self.accuracy(output,y))
    return loss
  
  def validation_step(self,val_batch,y = val_batch
    logits = self.forward(X)
    loss = self.loss_fn(logits,y)
    self.log('test_loss',loss)
    m = nn.Softmax(dim=1)
    output = m(logits)
    self.log('test_acc',y))
  
  def configure_optimizers(self):
    optimizer = torch.optim.SGD(self.model.parameters(),lr= 0.1)
    return optimizer
  
class Light_DataModule(pl.LightningDataModule):
  def __init__(self,resize= None):
    super().__init__()
    if resize:
      self.resize = resize
 
  def setup(self,stage):
    # transforms for images
    trans = [transforms.ToTensor()]
    if self.resize:
      trans.insert(0,transforms.Resize(self.resize))
    trans = transforms.Compose(trans)
    # prepare transforms standard to MNIST
    self.mnist_train = FashionMNIST(root="../data",train=True,download=True,transform=trans)
    self.mnist_test = FashionMNIST(root="../data",train=False,transform=trans)
 
  def train_dataloader(self):
    return DataLoader(self.mnist_train,batch_size=128,shuffle=True,num_workers=4)
 
  def val_dataloader(self):
    return DataLoader(self.mnist_test,num_workers=4)

## Train model
data_module = Light_DataModule(resize=224)
wandb_logger = WandbLogger(project="d2l",name ='NIN')
model  = Lightning_nin()
trainer = pl.Trainer(logger=wandb_logger,max_epochs=4,gpus=1,progress_bar_refresh_rate =1)
trainer.fit(model,data_module)
wandb.finish()

运行代码后，我只得到了 0.1 的准确度。不知道我哪里出错了。我已经能够使用相同的模板实现其他 CNN（如 VGG）。不知道我哪里出错了。 10个epochs后准确率应该接近0.9。

解决方法

对于 224 的图像大小，kernel_size 和 strides 非常大。它将大大减少传递到后续层的信息。尝试减少它们。此外，VGG 是一个非常精心设计的架构。