PyTorch
文章平均质量分 91
研究生入学前对PyTorch的学习记录
Mendax_chen
弱鸡学习中
展开
-
PyTorch官方Tutorials Quickstart
PyTorch官方Tutorials跟着PyTorch官方Tutorials码的,便于理解自己稍有改动代码并添加注释,IDE用的jupyter notebook链接:Quickstart这篇建议直接看原链接 上面有扩展链接 我这里直接复制过来没有加上超链接QUICKSTARTThis section runs through the API for common tasks in machine learning. Refer to the links in each section to div原创 2021-07-22 14:39:29 · 179 阅读 · 0 评论 -
PyTorch官方Tutorials SAVE AND LOAD THE MODEL
PyTorch官方Tutorials跟着PyTorch官方Tutorials码的,便于理解自己稍有改动代码并添加注释,IDE用的jupyter notebook链接: SAVE AND LOAD THE MODEL保存与加载模型通过保存,加载,预测模型来保存模型状态import torchimport torch.onnx as onnximport torchvision.models as models保存与加载模型权重pytorch模型在内部状态字典保存习得的参数,这个字典叫做原创 2021-07-21 10:20:30 · 152 阅读 · 0 评论 -
PyTorch官方Tutorials Optimization
PyTorch官方Tutorials跟着PyTorch官方Tutorials码的,便于理解自己稍有改动代码并添加注释,IDE用的jupyter notebook链接: Optimization优化模型参数有了模型和数据以后就可以训练了 通过利用数据优化参数来验证和测试模型训练模型是一个迭代的过程 在每一次迭代(epoch)中 模型对输出进行一次猜测 计算猜测的错(loss) 收集和参数相关的错误的导数(见上一节) 并使用梯度下降对这些参数进行优化进一步了解这个过程 观看视频backpropga原创 2021-07-02 17:25:32 · 133 阅读 · 0 评论 -
PyTorch官方Tutorials Autograd
PyTorch官方Tutorials跟着PyTorch官方Tutorials码的,便于理解自己稍有改动代码并添加注释,IDE用的jupyter notebook链接: AutogradAUTOMATIC DIFFERENTIATION WITH TORCH.AUTOGRAD用torch.autograd自动微分When training neural networks, the most frequently used algorithm is back propagation. In thi原创 2021-06-30 20:15:26 · 216 阅读 · 0 评论 -
PyTorch官方Tutorials Tenosrs
PyTorch官方Tutorials跟着PyTorch官方Tutorials码的,便于理解自己稍有改动代码并添加注释,IDE用的jupyter notebook链接: tutorials-TensorsTENSORSTensors are a specialized data structure that are very similar to arrays and matrices.In PyTorch, we use tensors to encode the inputs and outpu原创 2021-06-28 20:48:43 · 148 阅读 · 0 评论 -
PyTorch官方Tutorials Build Model
PyTorch官方Tutorials跟着PyTorch官方Tutorials码的,便于理解自己稍有改动代码并添加注释,IDE用的jupyter notebook链接:Build ModelBUILD THE NEURAL NETWORKNeural networks comprise of layers/modules that perform operations on data. The torch.nn namespace provides all the building blocks yo原创 2021-06-27 21:06:35 · 318 阅读 · 0 评论 -
PyTorch官方Tutorials Transforms
PyTorch官方Tutorials跟着PyTorch官方Tutorials码的,便于理解自己稍有改动代码并添加注释,IDE用的jupyter notebook链接:Tutorials-TransformsTRANSFORMSData does not always come in its final processed form that is required for training machine learning algorithms. We use transforms to perfo原创 2021-06-24 16:17:04 · 133 阅读 · 0 评论 -
PyTorch官方Tutorials Datasets & DataLoders
PyTorch官方Tutorials跟着PyTorch官方Tutorials码的,便于理解自己稍有改动代码并添加注释,IDE用的jupyter notebook链接: tutorials-Datasets & DataLodersDATASETS & DATALOADERSCode for processing data samples can get messy and hard to maintain; we ideally want our dataset code to be原创 2021-05-07 15:15:47 · 205 阅读 · 1 评论 -
win10 Anaconda3+PyTorch环境配置
文章目录pytorch环境配置pytorch环境配置1.anaconda prompt进入base环境2.输入下列四条指令更换清华源1 conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/2 conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/3 conda con原创 2021-04-24 15:52:32 · 327 阅读 · 1 评论