Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
from __future__ import print_function
from __future__ import division
import torch
import torch.nn as nn
import torch.optim as optim
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
from torch.autograd import Variable
import matplotlib.pyplot as plt
import time
import os
import copy
import torchvision.models as models
from tqdm import tqdm
inception = models.inception_v3(pretrained=True)
for param in inception.parameters():
param.requires_grad = False
inception.AuxLogits.fc = nn.Linear(768, 10)
inception.fc = nn.Linear(2048, 10)
# data augmentation
data_transforms = {
"train": transforms.Compose(
[
transforms.Resize(312),
transforms.CenterCrop(299),
transforms.ToTensor(),
transforms.Lambda(lambda x: x.repeat(3, 1, 1)),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
]
),
"val": transforms.Compose(
[
transforms.Resize(312),
transforms.CenterCrop(299),
transforms.ToTensor(),
transforms.Lambda(lambda x: x.repeat(3, 1, 1)),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
]
),
}
data_dir = "./mnist"
num_classes = 10
batch_size = 16
train_loader = torch.utils.data.DataLoader(
torchvision.datasets.MNIST(
data_dir, train=True, download=True, transform=data_transforms["train"]
),
batch_size=batch_size,
shuffle=True,
)
test_loader = torch.utils.data.DataLoader(
torchvision.datasets.MNIST(
data_dir, train=False, download=True, transform=data_transforms["val"]
),
batch_size=batch_size,
shuffle=True,
)
dataloaders = {"train": train_loader, "val": test_loader}
dataset_sizes = {x: len(dataloaders[x].dataset) for x in ["train", "val"]}
class_names = train_loader.dataset.classes
# train the model
# takes the model, dataloaders, criterion, optimizer, device(GPU or CPU) and number of epochs respectively as parameters
# returns model, array of validation accuracy, validation loss, train accuracy, train loss respectively
def train_model(
model, dataloaders, criterion, optimizer, device, num_epochs=25, is_inception=False
):
since = time.time()
val_acc_history = []
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(num_epochs):
print("Epoch {}/{}".format(epoch, num_epochs - 1))
print("-" * 10)
# Each epoch has a training and validation phase
for phase in ["train", "val"]:
if phase == "train":
model.train() # Set model to training mode
else:
model.eval() # Set model to evaluate mode
running_loss = 0.0
running_corrects = 0
# Iterate over data.
print("expecting data")
for inputs, labels in tqdm(dataloaders[phase]):
inputs = inputs.to(device)
labels = labels.to(device)
# zero the parameter gradients
optimizer.zero_grad()
# forward
# track history if only in train
with torch.set_grad_enabled(phase == "train"):
# Get model outputs and calculate loss
# Special case for inception because in training it has an auxiliary output. In train
# mode we calculate the loss by summing the final output and the auxiliary output
# but in testing we only consider the final output.
if is_inception and phase == "train":
# From https://discuss.pytorch.org/t/how-to-optimize-inception-model-with-auxiliary-classifiers/7958
outputs, aux_outputs = model(inputs)
loss1 = criterion(outputs, labels)
loss2 = criterion(aux_outputs, labels)
loss = loss1 + 0.4 * loss2
else:
outputs = model(inputs)
loss = criterion(outputs, labels)
_, preds = torch.max(outputs, 1)
# backward + optimize only if in training phase
if phase == "train":
loss.backward()
optimizer.step()
# statistics
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
epoch_loss = running_loss / len(dataloaders[phase].dataset)
epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)
print("{} Loss: {:.4f} Acc: {:.4f}".format(phase, epoch_loss, epoch_acc))
# deep copy the model
if phase == "val" and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
if phase == "val":
val_acc_history.append(epoch_acc)
print()
time_elapsed = time.time() - since
print(
"Training complete in {:.0f}m {:.0f}s".format(
time_elapsed // 60, time_elapsed % 60
)
)
print("Best val Acc: {:4f}".format(best_acc))
# load best model weights
model.load_state_dict(best_model_wts)
return model, val_acc_history
# specify loss function
criterion = nn.CrossEntropyLoss()
# specify optimizer
optimizer = torch.optim.Adam(inception.parameters(), lr=0.1)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
inception = inception.to(device) # send the model to the gpu
model_name = "inception"
model, val_acc = train_model(
inception,
dataloaders,
criterion,
optimizer,
device,
num_epochs=30,
is_inception=(model_name == "inception"),
) # train model
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment