2020-01-31-pytorch一般流程

import torch
import torch.optim as optim
import torch.nn as nn
from torchviz import make_dot

device = 'cuda' if torch.cuda.is_available() else 'cpu'

# Our data was in Numpy arrays, but we need to transform them into PyTorch's Tensors
# and then we send them to the chosen device
x_train_tensor = torch.from_numpy(x_train).float().to(device)
y_train_tensor = torch.from_numpy(y_train).float().to(device)

# Here we can see the difference - notice that .type() is more useful
# since it also tells us WHERe the tensor is (device)
print(type(x_train), type(x_train_tensor), x_train_tensor.type())

def make_train_step(model, loss_fn, optimizer):
    # Builds function that performs a step in the train loop
    def train_step(x, y):
        # Sets model to TRAIN mode
        model.train()
        # Makes predictions
        yhat = model(x)
        # Computes loss
        loss = loss_fn(y, yhat)
        # Computes gradients
        loss.backward()
        # Updates parameters and zeroes gradients
        optimizer.step()
        optimizer.zero_grad()
        # Returns the loss
        return loss.item()
    
    # Returns the function that will be called inside the train loop
    return train_step

from torch.utils.data.dataset import random_split
from torch.utils.data import DataLoader

x_tensor = torch.from_numpy(x).float()
y_tensor = torch.from_numpy(y).float()

dataset = TensorDataset(x_tensor, y_tensor)

train_dataset, val_dataset = random_split(dataset, [80, 20])

train_loader = DataLoader(dataset=train_dataset, batch_size=16)
val_loader = DataLoader(dataset=val_dataset, batch_size=20)

losses = []
val_losses = []
train_step = make_train_step(model, loss_fn, optimizer)

for epoch in range(n_epochs):
    for x_batch, y_batch in train_loader:
        x_batch = x_batch.to(device)
        y_batch = y_batch.to(device)

        loss = train_step(x_batch, y_batch)
        losses.append(loss)
        
    with torch.no_grad():
        for x_val, y_val in val_loader:
            x_val = x_val.to(device)
            y_val = y_val.to(device)
            
            model.eval()

            yhat = model(x_val)
            val_loss = loss_fn(y_val, yhat)
            val_losses.append(val_loss.item())

print(model.state_dict())