import torch
import torch.nn as nn
import torch.nn.functional as F
import copy
import torchvision
from torchvision import transforms
from torchvision.models.resnet import resnet50, resnet18
from torch.quantization.quantize_fx import prepare_fx, convert_fx
from torch.ao.quantization.fx.graph_module import ObservedGraphModule
from torch.quantization import (
get_default_qconfig,
)
from torch import optim
import os
import time
def train_model(model, train_loader, test_loader, device):
# The training configurations were not carefully selected.
learning_rate = 1e-2
num_epochs = 20
criterion = nn.CrossEntropyLoss()
model.to(device)
# It seems that SGD optimizer is better than Adam optimizer for ResNet18 training on CIFAR10.
optimizer = optim.SGD(
model.parameters(), lr=learning_rate, momentum=0.9, weight_decay=1e-5
)
# optimizer = optim.Adam(model.parameters(), lr=learning_rate, betas=(0.9, 0.999), eps=1e-08, weight_decay=0, amsgrad=False)
for epoch in range(num_epochs):
# Training
model.train()
running_loss = 0
running_corrects = 0
for inputs, labels in train_loader:
inputs = inputs.to(device)
labels = labels.to(device)
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# statistics
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
train_loss = running_loss / len(train_loader.dataset)
train_accuracy = running_corrects / len(train_loader.dataset)
# Evaluation
model.eval()
eval_loss, eval_accuracy = evaluate_model(
model=model, test_loader=test_loader, device=device, criterion=criterion
)
print(
"Epoch: {:02d} Train Loss: {:.3f} Train Acc: {:.3f} Eval Loss: {:.3f} Eval Acc: {:.3f}".format(
epoch, train_loss, train_accuracy, eval_loss, eval_accuracy
)
)
return model
def prepare_dataloader(num_workers=8, train_batch_size=128, eval_batch_size=256):
train_transform = transforms.Compose(
[
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
]
)
test_transform = transforms.Compose(
[
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
]
)
train_set = torchvision.datasets.CIFAR10(
root="data", train=True, download=True, transform=train_transform
)
# We will use test set for validation and test in this project.
# Do not use test set for validation in practice!
test_set = torchvision.datasets.CIFAR10(
root="data", train=False, download=True, transform=test_transform
)
train_sampler = torch.utils.data.RandomSampler(train_set)
test_sampler = torch.utils.data.SequentialSampler(test_set)
train_loader = torch.utils.data.DataLoader(
dataset=train_set,
batch_size=train_batch_size,
sampler=train_sampler,
num_workers=num_workers,
)
test_loader = torch.utils.data.DataLoader(
dataset=test_set,
batch_size=eval_batch_size,
sampler=test_sampler,
num_workers=num_workers,
)
return train_loader, test_loader
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
- 8.
- 9.
- 10.
- 11.
- 12.
- 13.
- 14.
- 15.
- 16.
- 17.
- 18.
- 19.
- 20.
- 21.
- 22.
- 23.
- 24.
- 25.
- 26.
- 27.
- 28.
- 29.
- 30.
- 31.
- 32.
- 33.
- 34.
- 35.
- 36.
- 37.
- 38.
- 39.
- 40.
- 41.
- 42.
- 43.
- 44.
- 45.
- 46.
- 47.
- 48.
- 49.
- 50.
- 51.
- 52.
- 53.
- 54.
- 55.
- 56.
- 57.
- 58.
- 59.
- 60.
- 61.
- 62.
- 63.
- 64.
- 65.
- 66.
- 67.
- 68.
- 69.
- 70.
- 71.
- 72.
- 73.
- 74.
- 75.
- 76.
- 77.
- 78.
- 79.
- 80.
- 81.
- 82.
- 83.
- 84.
- 85.
- 86.
- 87.
- 88.
- 89.
- 90.
- 91.
- 92.
- 93.
- 94.
- 95.
- 96.
- 97.
- 98.
- 99.
- 100.
- 101.
- 102.
- 103.
- 104.
- 105.
- 106.
- 107.