中文版 pytorch
Topic | Replies | Views | Activity | |
---|---|---|---|---|
About the pytorch category
|
0 | 1036 | January 14, 2021 | |
锚框
|
62 | 15549 | January 21, 2025 | |
为什么在 d2l 的 torch 包中没有 train_ch3 这个函数?
|
2 | 108 | January 20, 2025 | |
自定义层
|
38 | 9816 | January 20, 2025 | |
[反馈][笔误] 书中发现的问题
|
1 | 414 | January 20, 2025 | |
多层感知机的从零实现
|
86 | 26094 | January 20, 2025 | |
随机梯度下降
|
5 | 1784 | January 19, 2025 | |
梯度下降
|
7 | 2642 | January 19, 2025 | |
语言模型和数据集
|
32 | 9803 | January 19, 2025 | |
文本预处理
|
42 | 8695 | January 19, 2025 | |
Softmax回归的从零实现
|
150 | 42875 | January 18, 2025 | |
序列模型
|
32 | 9920 | January 17, 2025 | |
注意力汇聚:Nadaraya-Watson 核回归
|
51 | 13951 | January 17, 2025 | |
卷积神经网络(LeNet)
|
97 | 32551 | January 16, 2025 | |
图像分类数据集
|
71 | 21155 | January 16, 2025 | |
自注意力和位置编码
|
16 | 5238 | January 16, 2025 | |
多头注意力
|
54 | 16454 | January 16, 2025 | |
稠密连接网络(DenseNet)
|
24 | 9930 | January 15, 2025 | |
注意力评分函数
|
28 | 6959 | January 14, 2025 | |
使用 GPU
|
41 | 14256 | January 13, 2025 | |
延后初始化
|
13 | 6787 | January 13, 2025 | |
层和块
|
43 | 13220 | January 13, 2025 | |
权重衰减
|
56 | 15280 | January 11, 2025 | |
Softmax回归的简洁实现
|
111 | 33393 | January 11, 2025 | |
残差网络(ResNet)
|
74 | 30513 | January 11, 2025 | |
多输入多输出通道
|
34 | 10993 | January 11, 2025 | |
批量规范化
|
45 | 10692 | January 10, 2025 | |
多层感知机的简洁实现
|
40 | 17060 | January 9, 2025 | |
自然语言推断:使用注意力
|
1 | 1057 | January 6, 2025 | |
安装D2L包失败
|
6 | 2505 | January 5, 2025 |