tutorials/beginner_source/transfer_learning_tutorial.py at main · pytorch/tutorials · GitHub

History

394 lines (311 loc) · 13 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

# -*- coding: utf-8 -*-

"""

Transfer Learning for Computer Vision Tutorial

==============================================

**Author**: `Sasank Chilamkurthy <https://chsasank.github.io>`_

In this tutorial, you will learn how to train a convolutional neural network for

image classification using transfer learning. You can read more about the transfer

learning at `cs231n notes <https://cs231n.github.io/transfer-learning/>`__

Quoting these notes,

In practice, very few people train an entire Convolutional Network

from scratch (with random initialization), because it is relatively

rare to have a dataset of sufficient size. Instead, it is common to

pretrain a ConvNet on a very large dataset (e.g. ImageNet, which

contains 1.2 million images with 1000 categories), and then use the

ConvNet either as an initialization or a fixed feature extractor for

the task of interest.

These two major transfer learning scenarios look as follows:

- **Finetuning the ConvNet**: Instead of random initialization, we

initialize the network with a pretrained network, like the one that is

trained on imagenet 1000 dataset. Rest of the training looks as

usual.

- **ConvNet as fixed feature extractor**: Here, we will freeze the weights

for all of the network except that of the final fully connected

layer. This last fully connected layer is replaced with a new one

with random weights and only this layer is trained.

"""

# License: BSD

# Author: Sasank Chilamkurthy

import torch

import torch.nn as nn

import torch.optim as optim

from torch.optim import lr_scheduler

import torch.backends.cudnn as cudnn

import numpy as np

import torchvision

from torchvision import datasets, models, transforms

import matplotlib.pyplot as plt

import time

import os

from PIL import Image

from tempfile import TemporaryDirectory

cudnn.benchmark = True

plt.ion() # interactive mode

######################################################################

# Load Data

# ---------

# We will use torchvision and torch.utils.data packages for loading the

# data.

# The problem we're going to solve today is to train a model to classify

# **ants** and **bees**. We have about 120 training images each for ants and bees.

# There are 75 validation images for each class. Usually, this is a very

# small dataset to generalize upon, if trained from scratch. Since we

# are using transfer learning, we should be able to generalize reasonably

# well.

# This dataset is a very small subset of imagenet.

# .. Note ::

# Download the data from

# `here <https://download.pytorch.org/tutorial/hymenoptera_data.zip>`_

# and extract it to the current directory.

# Data augmentation and normalization for training

# Just normalization for validation

data_transforms = {

'train': transforms.Compose([

transforms.RandomResizedCrop(224),

transforms.RandomHorizontalFlip(),

transforms.ToTensor(),

transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])

]),

'val': transforms.Compose([

transforms.Resize(256),

transforms.CenterCrop(224),

transforms.ToTensor(),

transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])

]),

}

data_dir = 'data/hymenoptera_data'

image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),

data_transforms[x])

for x in ['train', 'val']}

dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,

shuffle=True, num_workers=4)

for x in ['train', 'val']}

dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}

class_names = image_datasets['train'].classes

# We want to be able to train our model on an `accelerator <https://pytorch.org/docs/stable/torch.html#accelerators>`__

# such as CUDA, MPS, MTIA, or XPU. If the current accelerator is available, we will use it. Otherwise, we use the CPU.

device = torch.accelerator.current_accelerator().type if torch.accelerator.is_available() else "cpu"

print(f"Using {device} device")

######################################################################

# Visualize a few images

# ^^^^^^^^^^^^^^^^^^^^^^

# Let's visualize a few training images so as to understand the data

# augmentations.

def imshow(inp, title=None):

"""Display image for Tensor."""

inp = inp.numpy().transpose((1, 2, 0))

mean = np.array([0.485, 0.456, 0.406])

std = np.array([0.229, 0.224, 0.225])

inp = std * inp + mean

inp = np.clip(inp, 0, 1)

plt.imshow(inp)

if title is not None:

plt.title(title)

plt.pause(0.001) # pause a bit so that plots are updated

# Get a batch of training data

inputs, classes = next(iter(dataloaders['train']))

# Make a grid from batch

out = torchvision.utils.make_grid(inputs)

imshow(out, title=[class_names[x] for x in classes])

######################################################################

# Training the model

# ------------------

# Now, let's write a general function to train a model. Here, we will

# illustrate:

# - Scheduling the learning rate

# - Saving the best model

# In the following, parameter ``scheduler`` is an LR scheduler object from

# ``torch.optim.lr_scheduler``.

def train_model(model, criterion, optimizer, scheduler, num_epochs=25):

since = time.time()

# Create a temporary directory to save training checkpoints

with TemporaryDirectory() as tempdir:

best_model_params_path = os.path.join(tempdir, 'best_model_params.pt')

torch.save(model.state_dict(), best_model_params_path)

best_acc = 0.0

for epoch in range(num_epochs):

print(f'Epoch {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.

for inputs, labels in 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'):

outputs = model(inputs)

_, preds = torch.max(outputs, 1)

loss = criterion(outputs, labels)

# 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)

if phase == 'train':

scheduler.step()

epoch_loss = running_loss / dataset_sizes[phase]

epoch_acc = running_corrects.double() / dataset_sizes[phase]

print(f'{phase} Loss: {epoch_loss:.4f} Acc: {epoch_acc:.4f}')

# deep copy the model

if phase == 'val' and epoch_acc > best_acc:

best_acc = epoch_acc

torch.save(model.state_dict(), best_model_params_path)

print()

time_elapsed = time.time() - since

print(f'Training complete in {time_elapsed // 60:.0f}m {time_elapsed % 60:.0f}s')

print(f'Best val Acc: {best_acc:4f}')

# load best model weights

model.load_state_dict(torch.load(best_model_params_path, weights_only=True))

return model

######################################################################

# Visualizing the model predictions

# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

# Generic function to display predictions for a few images

def visualize_model(model, num_images=6):

was_training = model.training

model.eval()

images_so_far = 0

fig = plt.figure()

with torch.no_grad():

for i, (inputs, labels) in enumerate(dataloaders['val']):

inputs = inputs.to(device)

labels = labels.to(device)

outputs = model(inputs)

_, preds = torch.max(outputs, 1)

for j in range(inputs.size()[0]):

images_so_far += 1

ax = plt.subplot(num_images//2, 2, images_so_far)

ax.axis('off')

ax.set_title(f'predicted: {class_names[preds[j]]}')

imshow(inputs.cpu().data[j])

if images_so_far == num_images:

model.train(mode=was_training)

return

model.train(mode=was_training)

######################################################################

# Finetuning the ConvNet

# ----------------------

# Load a pretrained model and reset final fully connected layer.

model_ft = models.resnet18(weights='IMAGENET1K_V1')

num_ftrs = model_ft.fc.in_features

# Here the size of each output sample is set to 2.

# Alternatively, it can be generalized to ``nn.Linear(num_ftrs, len(class_names))``.

model_ft.fc = nn.Linear(num_ftrs, 2)

model_ft = model_ft.to(device)

criterion = nn.CrossEntropyLoss()

# Observe that all parameters are being optimized

optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs

exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)

######################################################################

# Train and evaluate

# ^^^^^^^^^^^^^^^^^^

# It should take around 15-25 min on CPU. On GPU though, it takes less than a

# minute.

model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,

num_epochs=25)

######################################################################

visualize_model(model_ft)

######################################################################

# ConvNet as fixed feature extractor

# ----------------------------------

# Here, we need to freeze all the network except the final layer. We need

# to set ``requires_grad = False`` to freeze the parameters so that the

# gradients are not computed in ``backward()``.

# You can read more about this in the documentation

# `here <https://pytorch.org/docs/notes/autograd.html#excluding-subgraphs-from-backward>`__.

model_conv = torchvision.models.resnet18(weights='IMAGENET1K_V1')

for param in model_conv.parameters():

param.requires_grad = False

# Parameters of newly constructed modules have requires_grad=True by default

num_ftrs = model_conv.fc.in_features

model_conv.fc = nn.Linear(num_ftrs, 2)

model_conv = model_conv.to(device)

criterion = nn.CrossEntropyLoss()

# Observe that only parameters of final layer are being optimized as

# opposed to before.

optimizer_conv = optim.SGD(model_conv.fc.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs

exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)

######################################################################

# Train and evaluate

# ^^^^^^^^^^^^^^^^^^

# On CPU this will take about half the time compared to previous scenario.

# This is expected as gradients don't need to be computed for most of the

# network. However, forward does need to be computed.

model_conv = train_model(model_conv, criterion, optimizer_conv,

exp_lr_scheduler, num_epochs=25)

######################################################################

visualize_model(model_conv)

plt.ioff()

plt.show()

######################################################################

# Inference on custom images

# --------------------------

# Use the trained model to make predictions on custom images and visualize

# the predicted class labels along with the images.

def visualize_model_predictions(model,img_path):

was_training = model.training

model.eval()

img = Image.open(img_path)

img = data_transforms['val'](img)

img = img.unsqueeze(0)

img = img.to(device)

with torch.no_grad():

outputs = model(img)

_, preds = torch.max(outputs, 1)

ax = plt.subplot(2,2,1)

ax.axis('off')

ax.set_title(f'Predicted: {class_names[preds[0]]}')

imshow(img.cpu().data[0])

model.train(mode=was_training)

######################################################################

visualize_model_predictions(

model_conv,

img_path='data/hymenoptera_data/val/bees/72100438_73de9f17af.jpg'

)

plt.ioff()

plt.show()

######################################################################

# Further Learning

# -----------------

# If you would like to learn more about the applications of transfer learning,

# checkout our `Quantized Transfer Learning for Computer Vision Tutorial <https://pytorch.org/tutorials/intermediate/quantized_transfer_learning_tutorial.html>`_.

tutorials/beginner_source/transfer_learning_tutorial.py at main · pytorch/tutorials · GitHub

Uh oh!

Expand file tree

Breadcrumbs

transfer_learning_tutorial.py

Latest commit

History

Breadcrumbs

transfer_learning_tutorial.py

File metadata and controls