1

python train.py --model MODEL_NAME --batch_size BATCH_SIZE --lr LEARNING_RATE --num_epochs NUM_EPOCHS

1

python train.py --model tinyvgg --batch_size 32 --lr 0.001 --num_epochs 10

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22

going_modular/
├── going_modular/
│   ├── data_setup.py
│   ├── engine.py
│   ├── model_builder.py
│   ├── train.py
│   └── utils.py
├── models/
│   ├── 05_going_modular_cell_mode_tinyvgg_model.pth
│   └── 05_going_modular_script_mode_tinyvgg_model.pth
└── data/
    └── pizza_steak_sushi/
        ├── train/
        │   ├── pizza/
        │   │   ├── image01.jpeg
        │   │   └── ...
        │   ├── steak/
        │   └── sushi/
        └── test/
            ├── pizza/
            ├── steak/
            └── sushi/

1
2
3
4
5
6

import os
import torch
import data_setup, engine, model_builder, utils

from torchvision import transforms

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

import os
import requests
import zipfile
from pathlib import Path


data_path = Path("data/")
image_path = data_path / "pizza_steak_sushi"


if image_path.is_dir():
    print(f"{image_path} directory exists.")
else:
    print(f"Did not find {image_path} directory, creating one...")
    image_path.mkdir(parents=True, exist_ok=True)


with open(data_path / "pizza_steak_sushi.zip", "wb") as f:
    request = requests.get("https://github.com/mrdbourke/pytorch-deep-learning/raw/main/data/pizza_steak_sushi.zip")
    print("Downloading pizza, steak, sushi data...")
    f.write(request.content)


with zipfile.ZipFile(data_path / "pizza_steak_sushi.zip", "r") as zip_ref:
    print("Unzipping pizza, steak, sushi data...") 
    zip_ref.extractall(image_path)


os.remove(data_path / "pizza_steak_sushi.zip")

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17

data/
└── pizza_steak_sushi/
    ├── train/
    │   ├── pizza/
    │   │   ├── train_image01.jpeg
    │   │   ├── test_image02.jpeg
    │   │   └── ...
    │   ├── steak/
    │   │   └── ...
    │   └── sushi/
    │       └── ...
    └── test/
        ├── pizza/
        │   ├── test_image01.jpeg
        │   └── test_image02.jpeg
        ├── steak/
        └── sushi/

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

%%writefile going_modular/data_setup.py
"""
Contains functionality for creating PyTorch DataLoaders for 
image classification data.
"""
import os

from torchvision import datasets, transforms
from torch.utils.data import DataLoader

NUM_WORKERS = os.cpu_count()

def create_dataloaders(
    train_dir: str, 
    test_dir: str, 
    transform: transforms.Compose, 
    batch_size: int, 
    num_workers: int=NUM_WORKERS
):
  """Creates training and testing DataLoaders.

  Takes in a training directory and testing directory path and turns
  them into PyTorch Datasets and then into PyTorch DataLoaders.

  Args:
    train_dir: Path to training directory.
    test_dir: Path to testing directory.
    transform: torchvision transforms to perform on training and testing data.
    batch_size: Number of samples per batch in each of the DataLoaders.
    num_workers: An integer for number of workers per DataLoader.

  Returns:
    A tuple of (train_dataloader, test_dataloader, class_names).
    Where class_names is a list of the target classes.
    Example usage:
      train_dataloader, test_dataloader, class_names = \
        = create_dataloaders(train_dir=path/to/train_dir,
                             test_dir=path/to/test_dir,
                             transform=some_transform,
                             batch_size=32,
                             num_workers=4)
  """
  
  train_data = datasets.ImageFolder(train_dir, transform=transform)
  test_data = datasets.ImageFolder(test_dir, transform=transform)

  
  class_names = train_data.classes

  
  train_dataloader = DataLoader(
      train_data,
      batch_size=batch_size,
      shuffle=True,
      num_workers=num_workers,
      pin_memory=True,
  )
  test_dataloader = DataLoader(
      test_data,
      batch_size=batch_size,
      shuffle=False, 
      num_workers=num_workers,
      pin_memory=True,
  )

  return train_dataloader, test_dataloader, class_names

1
2
3
4
5

from going_modular import data_setup


train_dataloader, test_dataloader, class_names = data_setup.create_dataloaders(...)

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

%%writefile going_modular/model_builder.py
"""
Contains PyTorch model code to instantiate a TinyVGG model.
"""
import torch
from torch import nn 

class TinyVGG(nn.Module):
  """Creates the TinyVGG architecture.

  Replicates the TinyVGG architecture from the CNN explainer website in PyTorch.
  See the original architecture here: https://poloclub.github.io/cnn-explainer/

  Args:
    input_shape: An integer indicating number of input channels.
    hidden_units: An integer indicating number of hidden units between layers.
    output_shape: An integer indicating number of output units.
  """
  def __init__(self, input_shape: int, hidden_units: int, output_shape: int) -> None:
      super().__init__()
      self.conv_block_1 = nn.Sequential(
          nn.Conv2d(in_channels=input_shape, 
                    out_channels=hidden_units, 
                    kernel_size=3, 
                    stride=1, 
                    padding=0),  
          nn.ReLU(),
          nn.Conv2d(in_channels=hidden_units, 
                    out_channels=hidden_units,
                    kernel_size=3,
                    stride=1,
                    padding=0),
          nn.ReLU(),
          nn.MaxPool2d(kernel_size=2,
                        stride=2)
      )
      self.conv_block_2 = nn.Sequential(
          nn.Conv2d(hidden_units, hidden_units, kernel_size=3, padding=0),
          nn.ReLU(),
          nn.Conv2d(hidden_units, hidden_units, kernel_size=3, padding=0),
          nn.ReLU(),
          nn.MaxPool2d(2)
      )
      self.classifier = nn.Sequential(
          nn.Flatten(),
          
          
          nn.Linear(in_features=hidden_units*13*13,
                    out_features=output_shape)
      )

  def forward(self, x: torch.Tensor):
      x = self.conv_block_1(x)
      x = self.conv_block_2(x)
      x = self.classifier(x)
      return x
      

1
2
3
4
5
6
7
8
9
10

import torch

from going_modular import model_builder
device = "cuda" if torch.cuda.is_available() else "cpu"


torch.manual_seed(42)
model = model_builder.TinyVGG(input_shape=3,
                              hidden_units=10, 
                              output_shape=len(class_names)).to(device)

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
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

%%writefile going_modular/engine.py
"""
Contains functions for training and testing a PyTorch model.
"""
import torch

from tqdm.auto import tqdm
from typing import Dict, List, Tuple

def train_step(model: torch.nn.Module, 
               dataloader: torch.utils.data.DataLoader, 
               loss_fn: torch.nn.Module, 
               optimizer: torch.optim.Optimizer,
               device: torch.device) -> Tuple[float, float]:
  """Trains a PyTorch model for a single epoch.

  Turns a target PyTorch model to training mode and then
  runs through all of the required training steps (forward
  pass, loss calculation, optimizer step).

  Args:
    model: A PyTorch model to be trained.
    dataloader: A DataLoader instance for the model to be trained on.
    loss_fn: A PyTorch loss function to minimize.
    optimizer: A PyTorch optimizer to help minimize the loss function.
    device: A target device to compute on (e.g. "cuda" or "cpu").

  Returns:
    A tuple of training loss and training accuracy metrics.
    In the form (train_loss, train_accuracy). For example:

    (0.1112, 0.8743)
  """
  
  model.train()

  
  train_loss, train_acc = 0, 0

  
  for batch, (X, y) in enumerate(dataloader):
      
      X, y = X.to(device), y.to(device)

      
      y_pred = model(X)

      
      loss = loss_fn(y_pred, y)
      train_loss += loss.item() 

      
      optimizer.zero_grad()

      
      loss.backward()

      
      optimizer.step()

      
      y_pred_class = torch.argmax(torch.softmax(y_pred, dim=1), dim=1)
      train_acc += (y_pred_class == y).sum().item()/len(y_pred)

  
  train_loss = train_loss / len(dataloader)
  train_acc = train_acc / len(dataloader)
  return train_loss, train_acc

def test_step(model: torch.nn.Module, 
              dataloader: torch.utils.data.DataLoader, 
              loss_fn: torch.nn.Module,
              device: torch.device) -> Tuple[float, float]:
  """Tests a PyTorch model for a single epoch.

  Turns a target PyTorch model to "eval" mode and then performs
  a forward pass on a testing dataset.

  Args:
    model: A PyTorch model to be tested.
    dataloader: A DataLoader instance for the model to be tested on.
    loss_fn: A PyTorch loss function to calculate loss on the test data.
    device: A target device to compute on (e.g. "cuda" or "cpu").

  Returns:
    A tuple of testing loss and testing accuracy metrics.
    In the form (test_loss, test_accuracy). For example:

    (0.0223, 0.8985)
  """
  
  model.eval() 

  
  test_loss, test_acc = 0, 0

  
  with torch.inference_mode():
      
      for batch, (X, y) in enumerate(dataloader):
          
          X, y = X.to(device), y.to(device)

          
          test_pred_logits = model(X)

          
          loss = loss_fn(test_pred_logits, y)
          test_loss += loss.item()

          
          test_pred_labels = test_pred_logits.argmax(dim=1)
          test_acc += ((test_pred_labels == y).sum().item()/len(test_pred_labels))

  
  test_loss = test_loss / len(dataloader)
  test_acc = test_acc / len(dataloader)
  return test_loss, test_acc

def train(model: torch.nn.Module, 
          train_dataloader: torch.utils.data.DataLoader, 
          test_dataloader: torch.utils.data.DataLoader, 
          optimizer: torch.optim.Optimizer,
          loss_fn: torch.nn.Module,
          epochs: int,
          device: torch.device) -> Dict[str, List]:
  """Trains and tests a PyTorch model.

  Passes a target PyTorch models through train_step() and test_step()
  functions for a number of epochs, training and testing the model
  in the same epoch loop.

  Calculates, prints and stores evaluation metrics throughout.

  Args:
    model: A PyTorch model to be trained and tested.
    train_dataloader: A DataLoader instance for the model to be trained on.
    test_dataloader: A DataLoader instance for the model to be tested on.
    optimizer: A PyTorch optimizer to help minimize the loss function.
    loss_fn: A PyTorch loss function to calculate loss on both datasets.
    epochs: An integer indicating how many epochs to train for.
    device: A target device to compute on (e.g. "cuda" or "cpu").

  Returns:
    A dictionary of training and testing loss as well as training and
    testing accuracy metrics. Each metric has a value in a list for 
    each epoch.
    In the form: {train_loss: [...],
                  train_acc: [...],
                  test_loss: [...],
                  test_acc: [...]} 
    For example if training for epochs=2: 
                 {train_loss: [2.0616, 1.0537],
                  train_acc: [0.3945, 0.3945],
                  test_loss: [1.2641, 1.5706],
                  test_acc: [0.3400, 0.2973]} 
  """
  
  results = {"train_loss": [],
      "train_acc": [],
      "test_loss": [],
      "test_acc": []
  }

  
  for epoch in tqdm(range(epochs)):
      train_loss, train_acc = train_step(model=model,
                                          dataloader=train_dataloader,
                                          loss_fn=loss_fn,
                                          optimizer=optimizer,
                                          device=device)
      test_loss, test_acc = test_step(model=model,
          dataloader=test_dataloader,
          loss_fn=loss_fn,
          device=device)

      
      print(
          f"Epoch: {epoch+1} | "
          f"train_loss: {train_loss:.4f} | "
          f"train_acc: {train_acc:.4f} | "
          f"test_loss: {test_loss:.4f} | "
          f"test_acc: {test_acc:.4f}"
      )

      
      results["train_loss"].append(train_loss)
      results["train_acc"].append(train_acc)
      results["test_loss"].append(test_loss)
      results["test_acc"].append(test_acc)

  
  return results

1
2
3
4
5

from going_modular import engine


engine.train(...)

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

%%writefile going_modular/utils.py
"""
Contains various utility functions for PyTorch model training and saving.
"""
import torch
from pathlib import Path

def save_model(model: torch.nn.Module,
               target_dir: str,
               model_name: str):
  """Saves a PyTorch model to a target directory.

  Args:
    model: A target PyTorch model to save.
    target_dir: A directory for saving the model to.
    model_name: A filename for the saved model. Should include
      either ".pth" or ".pt" as the file extension.

  Example usage:
    save_model(model=model_0,
               target_dir="models",
               model_name="05_going_modular_tingvgg_model.pth")
  """
  
  target_dir_path = Path(target_dir)
  target_dir_path.mkdir(parents=True,
                        exist_ok=True)

  
  assert model_name.endswith(".pth") or model_name.endswith(".pt"), "model_name should end with '.pt' or '.pth'"
  model_save_path = target_dir_path / model_name

  
  print(f"[INFO] Saving model to: {model_save_path}")
  torch.save(obj=model.state_dict(),
             f=model_save_path)

1
2
3
4
5
6
7

from going_modular import utils


save_model(model=...
           target_dir=...,
           model_name=...)

1

python train.py

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

%%writefile going_modular/train.py
"""
Trains a PyTorch image classification model using device-agnostic code.
"""

import os
import torch
import data_setup, engine, model_builder, utils

from torchvision import transforms


NUM_EPOCHS = 5
BATCH_SIZE = 32
HIDDEN_UNITS = 10
LEARNING_RATE = 0.001


train_dir = "data/pizza_steak_sushi/train"
test_dir = "data/pizza_steak_sushi/test"


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


data_transform = transforms.Compose([
  transforms.Resize((64, 64)),
  transforms.ToTensor()
])


train_dataloader, test_dataloader, class_names = data_setup.create_dataloaders(
    train_dir=train_dir,
    test_dir=test_dir,
    transform=data_transform,
    batch_size=BATCH_SIZE
)


model = model_builder.TinyVGG(
    input_shape=3,
    hidden_units=HIDDEN_UNITS,
    output_shape=len(class_names)
).to(device)


loss_fn = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(),
                             lr=LEARNING_RATE)


engine.train(model=model,
             train_dataloader=train_dataloader,
             test_dataloader=test_dataloader,
             loss_fn=loss_fn,
             optimizer=optimizer,
             epochs=NUM_EPOCHS,
             device=device)


utils.save_model(model=model,
                 target_dir="models",
                 model_name="05_going_modular_script_mode_tinyvgg_model.pth")

1

python train.py

1

python train.py --model MODEL_NAME --batch_size BATCH_SIZE --lr LEARNING_RATE --num_epochs NUM_EPOCHS