import torch
from torch import nn
from torch.autograd import Variable
import torchvision.datasets as datasets
import torchvision.transforms as transforms
import numpy as np
import matplotlib.pyplot as plt
# 超参数
EPOCH = 1
BATCH_SIZE = 64
TIME_STEP = 28 # rnn time step / image height
INPUT_SIZE = 28 # rnn input size / image width
LR = 0.01
DOWNLOWD_MNIST = True # 如果没有下载好MNIST数据,设置为True
# 下载数据
# 训练数据
train_data = datasets.MNIST(root='./mnist', train=True, transform=transforms.ToTensor(), download=DOWNLOWD_MNIST)
train_loader = torch.utils.data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
#print(train_data.train_data.shape) 60000*28*28
# 测试数据
test_data = datasets.MNIST(root='./mnist', train=False)
#print(test_data.test_data.shape)大小10000*28*28
test_x = Variable(test_data.test_data, volatile=True).type(torch.FloatTensor)[:2000] / 255. # size 2000*28*28
test_y = test_data.test_labels.numpy()[:2000]
class RNN(nn.Module):
def __init__(self):
PYTORCH下RNN对MINIST数据集图片的识别
最新推荐文章于 2022-01-15 14:49:40 发布