Image dataset from folders in PyTorch - Model Pipeline Trace

Model Pipeline - Image dataset from folders

This pipeline loads images organized in folders by class, prepares them for training a model, trains a simple image classifier, and shows how predictions are made.

Data Flow - 5 Stages

1Load images from folders

1000 images organized in 5 folders→Read images and assign labels based on folder names→1000 samples x (3 color channels x 224 x 224 pixels)

Folder 'cats' contains 200 images labeled as class 0

↓

2Transform images

1000 samples x (3 x 224 x 224)→Resize, crop, convert to tensor, normalize pixel values→1000 samples x (3 x 224 x 224) tensor

Image tensor with pixel values normalized between -1 and 1

↓

3Train/test split

1000 samples→Split dataset into 800 training and 200 testing samples→Training: 800 samples, Testing: 200 samples

Training set has 160 images of class 0, Testing set has 40 images of class 0

↓

4Model training

800 samples x (3 x 224 x 224)→Train a CNN classifier on training data→Trained model weights

Model learns to classify images into 5 classes

↓

5Prediction

1 image tensor (3 x 224 x 224)→Model outputs class probabilities→1 x 5 vector of probabilities

[0.1, 0.7, 0.05, 0.1, 0.05] means class 1 predicted with 70% confidence

Training Trace - Epoch by Epoch

Loss
1.5 |****
1.1 |***
0.9 |**
0.7 |*
0.6 |

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.5	0.40	Model starts learning, accuracy is low
2	1.1	0.55	Loss decreases, accuracy improves
3	0.9	0.65	Model is learning useful features
4	0.7	0.75	Good progress, accuracy rising
5	0.6	0.80	Model converging well

Prediction Trace - 5 Layers

Layer 1: Input image tensor

Layer 2: Convolutional layers

Layer 3: Pooling layers

Layer 4: Fully connected layer

Layer 5: Softmax activation

Model Quiz - 3 Questions

What does the folder structure tell the model during loading?

A Which images belong to which class

B The image pixel values

C The image resolution

D The image file size

Key Insight

Organizing images in folders by class allows easy labeling. Transformations prepare images for the model. Training reduces loss and improves accuracy. Softmax outputs probabilities for class prediction.

Practice

1.

What does torchvision.datasets.ImageFolder do when loading images?

easy

A. Loads images and converts them to grayscale only

B. Loads images from a single folder without labels

C. Loads images and automatically splits them into training and testing sets

D. Loads images from folders where each folder name is used as a class label

Solution

1. Step 1: Understand ImageFolder functionality

   ImageFolder expects a root directory with subfolders. Each subfolder name is treated as a class label.

2. Step 2: Confirm label assignment

   Images inside each subfolder are assigned the label of that folder automatically.

3. Final Answer:

   Loads images from folders where each folder name is used as a class label -> Option D

4. Quick Check:

   ImageFolder uses folder names as labels [OK]

Hint: Remember: folder names become labels in ImageFolder [OK]

Common Mistakes:

• Thinking ImageFolder loads images without labels
• Assuming ImageFolder splits data automatically
• Believing ImageFolder converts images to grayscale by default

2.

Which of the following is the correct way to apply a transform that resizes images to 64x64 and converts them to tensors when using ImageFolder?

transform = transforms.Compose([
    ?
])
dataset = ImageFolder(root='data/train', transform=transform)

easy

A. transforms.Resize((64, 64)), transforms.ToTensor()

B. transforms.ToTensor(), transforms.Resize(64)

C. transforms.Resize(64), transforms.ToTensor()

D. transforms.ToPILImage(), transforms.Resize((64, 64))

Solution

1. Step 1: Identify correct transform order

   Resize must come before ToTensor because ToTensor expects a PIL image or ndarray.

2. Step 2: Check syntax correctness

   transforms.Resize takes a tuple for width and height. transforms.ToTensor converts PIL image to tensor.

3. Final Answer:

   transforms.Resize((64, 64)), transforms.ToTensor() -> Option A

4. Quick Check:

   Resize then ToTensor is correct order [OK]

Hint: Resize first, then convert to tensor [OK]

Common Mistakes:

• Applying ToTensor before Resize
• Using Resize with a single integer without tuple
• Using ToPILImage instead of ToTensor

3.

Given the following code, what will len(dataloader) print if the dataset has 100 images and batch_size=20?

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

transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.ToTensor()
])
dataset = ImageFolder(root='data/train', transform=transform)
dataloader = DataLoader(dataset, batch_size=20, shuffle=True)

print(len(dataloader))

medium

A. 5

B. 20

C. 100

D. 1

Solution

1. Step 1: Calculate number of batches

   Dataset size is 100 images, batch size is 20, so number of batches = 100 / 20 = 5.

2. Step 2: Confirm DataLoader length meaning

   len(dataloader) returns number of batches per epoch, which is 5 here.

3. Final Answer:

   5 -> Option A

4. Quick Check:

   100 images / 20 batch size = 5 batches [OK]

Hint: len(dataloader) = total images ÷ batch size [OK]

Common Mistakes:

• Confusing batch size with number of batches
• Assuming shuffle changes batch count
• Thinking len(dataloader) returns total images

4.

What is wrong with this code snippet for loading an image dataset?

from torchvision.datasets import ImageFolder
from torchvision import transforms

dataset = ImageFolder(root='data/train', transform=transforms.ToTensor())

medium

A. transforms.ToTensor() cannot be used alone without resizing or other transforms

B. transforms.ToTensor() expects a PIL image, but ImageFolder provides file paths

C. No error; this code works correctly

D. ImageFolder requires a list of image paths, not a root folder

Solution

1. Step 1: Check ImageFolder transform usage

   ImageFolder passes PIL images to the transform function, so transforms.ToTensor() works fine alone.

2. Step 2: Confirm no syntax or logic error

   Using only ToTensor is valid; resizing is optional but not required.

3. Final Answer:

   No error; this code works correctly -> Option C

4. Quick Check:

   ImageFolder passes PIL images, ToTensor alone is valid [OK]

Hint: ImageFolder sends PIL images, ToTensor alone is valid [OK]

Common Mistakes:

• Thinking ToTensor needs Resize always
• Believing ImageFolder needs image paths list
• Assuming ToTensor cannot handle PIL images

5.

You want to load images from folders and apply a transform that randomly flips images horizontally during training but not during validation. How can you set up ImageFolder and transforms for this?

hard

A. Use transforms.RandomHorizontalFlip() in both training and validation transforms

B. Use transforms.RandomHorizontalFlip() in training transform only, and a separate transform without flip for validation

C. Use transforms.RandomHorizontalFlip() only in validation transform

D. Use transforms.RandomHorizontalFlip() outside of transforms.Compose

Solution

1. Step 1: Understand data augmentation purpose

   RandomHorizontalFlip is a data augmentation used only during training to improve generalization.

2. Step 2: Apply transforms separately for train and validation

   Training transform includes RandomHorizontalFlip; validation transform excludes it to keep data consistent.

3. Final Answer:

   Use transforms.RandomHorizontalFlip() in training transform only, and a separate transform without flip for validation -> Option B

4. Quick Check:

   Augment training only, keep validation unchanged [OK]

Hint: Apply random flip only in training transforms [OK]

Common Mistakes:

• Applying random flip in validation data
• Not separating train and validation transforms
• Placing RandomHorizontalFlip outside Compose