PyTorبرنامج تعليمي حول نقل التعلم مع أمثلة

from __future__ import print_function, division
import os
import time
import torch
import torchvision
from torchvision import datasets, models, transforms
import torch.optim as optim
import numpy as np
import matplotlib.pyplot as plt

data_dir = "alien_pred"
input_shape = 224
mean = [0.5, 0.5, 0.5]
std = [0.5, 0.5, 0.5]

#data transformation
data_transforms = {
   'train': transforms.Compose([
       transforms.CenterCrop(input_shape),
       transforms.ToTensor(),
       transforms.Normalize(mean, std)
   ]),
   'validation': transforms.Compose([
       transforms.CenterCrop(input_shape),
       transforms.ToTensor(),
       transforms.Normalize(mean, std)
   ]),
}

image_datasets = {
   x: datasets.ImageFolder(
       os.path.join(data_dir, x),
       transform=data_transforms[x]
   )
   for x in ['train', 'validation']
}

dataloaders = {
   x: torch.utils.data.DataLoader(
       image_datasets[x], batch_size=32,
       shuffle=True, num_workers=4
   )
   for x in ['train', 'validation']
}

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

print(dataset_sizes)
class_names = image_datasets['train'].classes

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

images, labels = next(iter(dataloaders['train']))

rows = 4
columns = 4
fig=plt.figure()
for i in range(16):
   fig.add_subplot(rows, columns, i+1)
   plt.title(class_names[labels[i]])
   img = images[i].numpy().transpose((1, 2, 0))
   img = std * img + mean
   plt.imshow(img)
plt.show()

## Load the model based on VGG19
vgg_based = torchvision.models.vgg19(pretrained=True)

## freeze the layers
for param in vgg_based.parameters():
   param.requires_grad = False

# Modify the last layer
number_features = vgg_based.classifier[6].in_features
features = list(vgg_based.classifier.children())[:-1] # Remove last layer
features.extend([torch.nn.Linear(number_features, len(class_names))])
vgg_based.classifier = torch.nn.Sequential(*features)

vgg_based = vgg_based.to(device)

print(vgg_based)

criterion = torch.nn.CrossEntropyLoss()
optimizer_ft = optim.SGD(vgg_based.parameters(), lr=0.001, momentum=0.9)

VGG(
  (features): Sequential(
	(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(1): ReLU(inplace)
	(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(3): ReLU(inplace)
	(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
	(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(6): ReLU(inplace)
	(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(8): ReLU(inplace)
	(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
	(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(11): ReLU(inplace)
	(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(13): ReLU(inplace)
	(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(15): ReLU(inplace)
	(16): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(17): ReLU(inplace)
	(18): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
	(19): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(20): ReLU(inplace)
	(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(22): ReLU(inplace)
	(23): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(24): ReLU(inplace)
	(25): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(26): ReLU(inplace)
	(27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
	(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(29): ReLU(inplace)
	(30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(31): ReLU(inplace)
	(32): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(33): ReLU(inplace)
	(34): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
	(35): ReLU(inplace)
	(36): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (classifier): Sequential(
	(0): Linear(in_features=25088, out_features=4096, bias=True)
	(1): ReLU(inplace)
	(2): Dropout(p=0.5)
	(3): Linear(in_features=4096, out_features=4096, bias=True)
	(4): ReLU(inplace)
	(5): Dropout(p=0.5)
	(6): Linear(in_features=4096, out_features=2, bias=True)
  )
)

def train_model(model, criterion, optimizer, num_epochs=25):
   since = time.time()

   for epoch in range(num_epochs):
       print('Epoch {}/{}'.format(epoch, num_epochs - 1))
       print('-' * 10)

       #set model to trainable
       # model.train()

       train_loss = 0

       # Iterate over data.
       for i, data in enumerate(dataloaders['train']):
           inputs , labels = data
           inputs = inputs.to(device)
           labels = labels.to(device)

           optimizer.zero_grad()
          
           with torch.set_grad_enabled(True):
               outputs  = model(inputs)
               loss = criterion(outputs, labels)

           loss.backward()
           optimizer.step()

           train_loss += loss.item() * inputs.size(0)

           print('{} Loss: {:.4f}'.format(
               'train', train_loss / dataset_sizes['train']))
          
   time_elapsed = time.time() - since
   print('Training complete in {:.0f}m {:.0f}s'.format(
       time_elapsed // 60, time_elapsed % 60))

   return model

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['validation']):
           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('predicted: {} truth: {}'.format(class_names[preds[j]], class_names[labels[j]]))
               img = inputs.cpu().data[j].numpy().transpose((1, 2, 0))
               img = std * img + mean
               ax.imshow(img)

               if images_so_far == num_images:
                   model.train(mode=was_training)
                   return
       model.train(mode=was_training)

vgg_based = train_model(vgg_based, criterion, optimizer_ft, num_epochs=25)

visualize_model(vgg_based)

plt.show()

Epoch 23/24
----------
train Loss: 0.0044
train Loss: 0.0078
train Loss: 0.0141
train Loss: 0.0221
train Loss: 0.0306
train Loss: 0.0336
train Loss: 0.0442
train Loss: 0.0482
train Loss: 0.0557
train Loss: 0.0643
train Loss: 0.0763
train Loss: 0.0779
train Loss: 0.0843
train Loss: 0.0910
train Loss: 0.0990
train Loss: 0.1063
train Loss: 0.1133
train Loss: 0.1220
train Loss: 0.1344
train Loss: 0.1382
train Loss: 0.1429
train Loss: 0.1500
Epoch 24/24
----------
train Loss: 0.0076
train Loss: 0.0115
train Loss: 0.0185
train Loss: 0.0277
train Loss: 0.0345
train Loss: 0.0420
train Loss: 0.0450
train Loss: 0.0490
train Loss: 0.0644
train Loss: 0.0755
train Loss: 0.0813
train Loss: 0.0868
train Loss: 0.0916
train Loss: 0.0980
train Loss: 0.1008
train Loss: 0.1101
train Loss: 0.1176
train Loss: 0.1282
train Loss: 0.1323
train Loss: 0.1397
train Loss: 0.1436
train Loss: 0.1467
Training complete in 2m 47s