The steps for this recipe are as follows:
- Import the libraries:
import numpy as np
import torch
from torch import nn
from torch import optim
import torch.nn.functional as F
from torchvision import datasets, transforms, models
from torch.utils.data.sampler import SubsetRandomSampler
- Declare your variables:
datadir = './data/train'
valid_size = .3
epochs = 3
steps = 0
running_loss = 0
print_every = 10
train_losses = []
test_losses = []
- Make an accuracy printer:
def print_score(torch, testloader, inputs, device, model, criterion, labels):
test_loss = 0
accuracy = 0
model.eval()daimen
with torch.no_grad():
for inputs, labels in testloader:
inputs, labels = inputs.to(device), labels.to(device)
logps = model.forward(inputs)
batch_loss = criterion(logps, labels)
test_loss += batch_loss.item()
ps = torch.exp(logps)
top_p, top_class = ps.topk(1, dim=1)
equals = top_class == labels.view(*top_class.shape)
accuracy += torch...