![](https://img-blog.csdnimg.cn/20201014180756919.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
刘大大pytorch
KaHoWong
五邑大学 人工智能研究生
展开
-
pytorch深度学习-RNN
pytorch深度学习-RNNRNNCell 循环Predicted string: ooooo, Epoch [1/15] loss=7.8655 Predicted string: ooooo, Epoch [2/15] loss=6.4431 Predicted string: olool, Epoch [3/15] loss=5.4130 Predicted string: olool, Epoch [4/15] loss=4.8994 Predicted string: olool,原创 2020-09-18 08:59:15 · 155 阅读 · 0 评论 -
pytorch深度学习-CNN Ressidual Net
pytorch深度学习-CNN Ressidual Net [1, 300] loss: 0.730 [1, 600] loss: 0.221 [1, 900] loss: 0.148Accuracy on test set: 96 % [2, 300] loss: 0.124 [2, 600] loss: 0.103 [2, 900] loss: 0.093Accuracy on test set: 97 % [3, 300] loss: 0.084 [3, 6原创 2020-09-15 16:12:23 · 420 阅读 · 0 评论 -
pytorch深度学习-CNN google Net
pytorch深度学习-CNN google Net原创 2020-09-15 15:46:26 · 143 阅读 · 0 评论 -
pytorch 入门学习CNN卷积神经网络
pytorch 入门学习CNN卷积神经网络运行结果 [1, 300] loss: 1.008 [1, 600] loss: 0.289 [1, 900] loss: 0.203Accuracy on test set: 95 % [2, 300] loss: 0.163 [2, 600] loss: 0.135 [2, 900] loss: 0.123Accuracy on test set: 96 % [3, 300] loss: 0.109 [3, 600]原创 2020-09-12 22:29:57 · 178 阅读 · 0 评论 -
pytorch 入门学习多分类问题
pytorch 入门学习多分类问题运行结果 [1, 300] loss: 2.287 [1, 600] loss: 2.137 [1, 900] loss: 1.192Accuracy on test set: 78 % [2, 300] loss: 0.560 [2, 600] loss: 0.422 [2, 900] loss: 0.361Accuracy on test set: 90 % [3, 300] loss: 0.307 [3, 600] loss:原创 2020-09-12 15:34:43 · 237 阅读 · 0 评论 -
pytorch 入门学习加载数据集
pytorch 入门学习加载数据集import torchimport numpy as npimport torchvisionimport numpy as npfrom torch.utils.data import Datasetfrom torch.utils.data import DataLoaderimport torch.nn.functional as Fimport matplotlib.pyplot as pltclass DiabetesDa原创 2020-09-04 17:01:11 · 496 阅读 · 0 评论 -
pytorch 入门学习处理多维特征输入
pytorch 入门学习处理多维特征输入处理多维特征输入import torchimport numpy as npimport torchvisionimport numpy as npimport torch.nn.functional as Fimport matplotlib.pyplot as pltclass Model(torch.nn.Module): def __init__(self): super(Model, self).__in原创 2020-08-26 20:32:18 · 352 阅读 · 0 评论 -
pytorch 入门学习使用逻辑斯蒂做二分类
pytorch 入门学习使用逻辑斯蒂做二分类使用pytorch实现逻辑斯蒂做二分类import torchimport torchvisionimport numpy as npimport torch.nn.functional as Fimport matplotlib.pyplot as pltx_data = torch.Tensor([[1.0],[2.0],[3.0]])y_data = torch.Tensor([[0],[0],[1]])class Logist原创 2020-08-26 14:44:53 · 205 阅读 · 0 评论 -
pytorch 入门学习反向传播
pytorch 入门学习反向传播使用pytorch实现线性回归import numpy as npimport matplotlib.pyplot as pltimport torch#part1 prepare datasetx_data = torch.Tensor([[1.0],[2.0],[3.0]])y_data = torch.Tensor([[2.0],[4.0],[6.0]])#part2 design model using classclass LinearMod原创 2020-08-25 21:59:27 · 222 阅读 · 0 评论 -
pytorch 入门学习反向传播
pytorch 入门学习反向传播反向传播import numpy as npimport matplotlib.pyplot as pltimport torchdef forward(x): return x * wdef loss(x,y): y_pred = forward(x) return (y_pred - y) **2x_data = [1.0, 2.0, 3.0]y_data = [2.0 ,4.0, 6.0]w = torch.Tens原创 2020-08-25 14:13:33 · 187 阅读 · 0 评论 -
pytorch 入门学习 MSE
《PyTorch深度学习实践》完结合集-线性模型import numpy as npimport matplotlib.pyplot as pltx_data = [1.0,2.0,3.0]y_data = [2.0,4.0,6.0]def forward(x): return x*wdef loss(x,y): y_pred = forward(x) return (y_pred - y) * (y_pred - y)w_list = []mse_lis原创 2020-08-24 16:37:05 · 539 阅读 · 0 评论