构建CNN模型时出现“顺序对象没有属性权重”错误

问题描述 投票:0回答:1
from google.colab import drive
drive.mount('/gdrive', force_remount=True)

import os
import numpy as np
import torch
import torch.nn as nn
from sklearn.metrics import accuracy_score
from torch.utils.data import (DataLoader, RandomSampler, TensorDataset)
from keras.datasets import mnist

class MNIST_CNN(nn.Module):
  def __init__(self, config):
    super(MNIST_CNN, self).__init__()

    self.conv1 = nn.Sequential(
        nn.Conv2d(1, 32, kernel_size=3, stride=1, padding=1),
        nn.ReLU(),
        nn.MaxPool2d(kernel_size=2, stride=2)
    )

    self.conv2 = nn.Sequential(
        nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
        nn.ReLU(),
        nn.MaxPool2d(kernel_size=2, stride=2)
    )

    self.fnn = nn.Sequential(
        nn.Linear(7*7*64, 10, bias=True)
    )

    nn.init.xavier_uniform_(self.fnn.weight)

  def forward(self,input_features):
    output = self.conv1(input_features)
    output = self.conv2(output)
    output = output.view(output.size(0), -1)
    hyothesis = self.fnn(output)
    return hyothesis

def load_dataset():
  (train_X, train_Y), (test_X, test_Y) = mnist.load_data()

  train_X = train_X.reshape(-1, 1, 28, 28)
  test_X = test_X.reshape(-1, 1, 28, 28)

  train_X = torch.tensor(train_X, dtype=torch.float)
  train_Y = torch.tensor(train_Y, dtype=torch.long)
  test_X = torch.tensor(test_X, dtype=torch.float)
  test_Y = torch.tensor(test_Y, dtype=torch.long)

  return (train_X, train_Y), (test_X, test_Y)

def tensor2list(input_tensor):
  return input_tensor.cpu().detach().numpy().tolist()

def do_test(model, test_dataloader):
  model.eval()

  predicts, golds = [], []

  with torch.no_grad():
    for step, batch in enumerate(test_dataloader):
      batch = tuple(t.cuda() for t in batch)
      input_features, labels = batch

      hypothesis = model(input_features)
      print("size of hypothesis", hypothesis.size())
      logits = torch.argmax(hypothesis, -1)

      x = tensor2list(logits)
      y = tensor2list(labels)

      predicts.extend(x)
      golds.extend(y)

  print("PRED=", predicts)
  print("GOLD=", golds)
  print("Accuracy={0:f}\n".format(accuracy_score(golds, predicts)))

def test(config):
  model = MNIST_CNN(config).cuda()

  model.load_state_dict(torch.load(os.path.join(config["output_dir"], config["model_name"])))

  (_, _), (features, labels) = load_dataset()

  test_features = TensorDataset(features, labels)
  test_dataloader = DataLoader(test_features, shuffle=True, batch_size=config["batch_size"])

  do_test(model, test_dataloader)

def train(config):
  model = MNIST_CNN(config).cuda()

  (input_features, labels), (_, _) = load_dataset()

  train_features = TensorDataset(input_features, labels)
  train_dataloader = DataLoader(train_features, shuffle=True, batch_size=config["batch_size"])

  loss_func = nn.CrossEntropyLoss()
  optimizer = torch.optim.Adam(model.parameters(), lr=config["learn_rate"])

  for epoch in range(config["epochs"]):
    model.train()

    costs = []

    for step, batch in enumerate(train_dataloader):
      batch = tuple(t.cuda() for t in batch)
      input_features, labels = batch

      optimizer.zero_grad()

      hypothesis = model(input_features)
      cost = loss_func(hypothesis, labels)

      cost.backward()
      optimizer.step()

      costs.append(cost.data.item())
    
    print("Average Loss={0:f}".format(np.mean(costs)))
    torch.save(model.state_dict(), os.path.join(config["output_dir"], "epoch_{0:d}.pt"))
    do_test(model, train_dataloader)

if(__name__=="__main__"):
    root_dir = "/gdrive/My Drive/24-2/MachineLearning"
    output_dir = os.path.join(root_dir, "output")
    if not os.path.exists(output_dir):
        os.makedirs(output_dir)

    config = {"mode": "test",
              "model_name":"epoch_{0:d}.pt".format(10),
              "output_dir":output_dir,
              "learn_rate":0.001,
              "batch_size":32,
              "epoch":10,
              }

    if(config["mode"] == "train"):
        train(config)
    else:
        test(config)

从这段代码中,我得到了 AttributeError: 'Sequential' object has no attribute 'weight'。 我尝试了 nn.init.xavier_uniform_(self.fnn[0].weight),但它低于错误。

运行时错误:加载 MNIST_CNN 的 state_dict 时出错: state_dict 中缺少键:“conv1.0.weight”、“conv1.0.bias”、“conv2.0.weight”、“conv2.0.bias”、“fnn.0.weight”、“fnn .0.偏差”。 state_dict 中出现意外的键:“线性1.权重”、“线性1.偏差”、“线性2.权重”、“线性2.偏差”。

我该如何解决?请帮助我。

python runtime-error attributeerror torch
1个回答
0
投票

一个简单的解决方案是从 self.fnn 中删除 nn.Sequential() 包装器

self.fnn = nn.Linear(7*7*64, 10, bias=True)

nn.init.xavier_uniform_(self.fnn.weight)
© www.soinside.com 2019 - 2024. All rights reserved.