1. Intro

  • ML和DL的本质essence是获取数据，构建算法(如神经网络)来发现
    其中的模式pattern，并使用发现的模式来预测未来predict future；

PytorchWorkflow 
import torch

# nn contain all pytorch building block for neural network
from torch import nn
import matplotlib.pyplot as plt

# check PyTorch version
torchVersion = torch.__version__

what_were_covering = {1: "data (prepare and load)",
    2: "build model",
    3: "fitting the model to data (training)",
    4: "making predictions and evaluating a model (inference)",
    5: "saving and loading a model",
    6: "putting it all together"
}

torchVersion,what_were_covering

2. Getting Data Ready

  • getting data ready turn into tensor；

3. Building Model

  • 构建模型：来学习数据中的模式，还将选择损失函数、优化器并建立训练循环；

  • to learn pattern in data，also choose loss function，
    optimizer and build training loop；

4. Fitting Model

  • 将模型与数据拟合(训练)，有数据和模型后，让模型(尝试)在(训练)数据中找到模式；

  • fitting model to data (training)，get data and model，
    let model(try to) find pattern in (training) data；

5. Prediction Evaluating

  • 预测和评估模型(推理)，模型在数据中发现的模式，将其发现与实际(测试)数据比较；

  • making prediction and evaluating model (inference)，model found
    pattern in data，compare its finding to actual (testing) data；

6. Saving Loading Model

  • 保存和加载模型，可能想在其它地方使用模型或稍后再使用；

  • saving and loading model，
    use model elsewhere or come back to it later；

7. Putting Together

  • putting it all together，combine it；