torchvision pre-trained models in PyTorch - Model Pipeline Trace

Model Pipeline - torchvision pre-trained models

This pipeline uses a pre-trained model from torchvision to classify images. It starts with input images, processes them through the model, and outputs predicted labels with confidence scores.

Data Flow - 4 Stages

1Input Images

1000 images x 3 channels x 224 height x 224 width→Raw images loaded and resized to 224x224 pixels with 3 color channels (RGB)→1000 images x 3 x 224 x 224

An image of a cat resized to 224x224 pixels with RGB channels

↓

2Preprocessing

1000 images x 3 x 224 x 224→Normalize pixel values using mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225]→1000 images x 3 x 224 x 224

Normalized cat image pixels scaled to have zero mean and unit variance per channel

↓

3Feature Extraction (Pre-trained Model)

1000 images x 3 x 224 x 224→Pass images through ResNet-18 pre-trained on ImageNet to extract features and classify→1000 images x 1000 classes

Model outputs a vector of 1000 class scores for each image

↓

4Prediction

1000 images x 1000 classes→Apply softmax to convert class scores to probabilities→1000 images x 1000 classes (probabilities)

For a cat image, highest probability might be for class 'tabby cat' with 0.85 confidence

Training Trace - Epoch by Epoch

Loss
1.0 |***************
0.8 |************
0.6 |********
0.4 |*****
0.2 |***
0.0 +----------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.75	0.65	Initial training loss and accuracy using fine-tuning on a small dataset
2	0.50	0.78	Loss decreased and accuracy improved after second epoch
3	0.35	0.85	Model continues to learn, showing better predictions
4	0.28	0.89	Training converging with lower loss and higher accuracy
5	0.22	0.92	Final epoch shows good performance on training data

Prediction Trace - 5 Layers

Layer 1: Input Image

Layer 2: ResNet-18 Convolutional Layers

Layer 3: Fully Connected Layer

Layer 4: Softmax Activation

Layer 5: Prediction Output

Model Quiz - 3 Questions

What is the shape of the output after the pre-trained model processes the input images?

A 1000 images x 3 channels x 224 x 224

B 1000 images x 1000 classes

C 1000 images x 512 features

D 1000 images x 25088 features

Key Insight

Using torchvision pre-trained models allows quick and effective image classification by leveraging knowledge learned from large datasets. The model processes images through layers extracting features and outputs class probabilities, improving accuracy as training progresses.

Practice

1. What is the main advantage of using torchvision pre-trained models?

easy

A. They automatically improve your dataset quality.

B. They generate new images from text descriptions.

C. They reduce the size of your images.

D. They allow you to use powerful image models without training from scratch.

Solution

1. Step 1: Understand what pre-trained models do

   Pre-trained models are already trained on large datasets, so you don't need to train them from zero.

2. Step 2: Identify the main benefit

   This saves time and resources, letting you use powerful models quickly.

3. Final Answer:

   They allow you to use powerful image models without training from scratch. -> Option D

4. Quick Check:

   Pre-trained models = reuse trained weights [OK]

Hint: Pre-trained means ready to use without full training [OK]

Common Mistakes:

• Thinking pre-trained models improve data quality
• Confusing pre-trained models with image resizing
• Believing they generate images from text

2. Which of the following is the correct way to load a pre-trained ResNet18 model from torchvision?

easy

A. model = torchvision.models.resnet18(weights=torchvision.models.ResNet18_Weights.IMAGENET1K_V1)

B. model = torchvision.resnet18(pretrained=True)

C. model = torchvision.models.resnet18(pretrained=False)

D. model = torchvision.models.load_resnet18(pretrained=True)

Solution

1. Step 1: Recall the updated torchvision syntax

   Since torchvision 0.13+, pre-trained weights are loaded using the 'weights' argument with a weights enum, not 'pretrained=True'.

2. Step 2: Identify the correct syntax for ResNet18

   Use torchvision.models.resnet18(weights=torchvision.models.ResNet18_Weights.IMAGENET1K_V1).

3. Final Answer:

   model = torchvision.models.resnet18(weights=torchvision.models.ResNet18_Weights.IMAGENET1K_V1) -> Option A

4. Quick Check:

   Use weights=enum, not pretrained=True [OK]

Hint: Use weights= argument, not pretrained=True [OK]

Common Mistakes:

• Using pretrained=False which doesn't load pre-trained weights
• Calling torchvision.resnet18 directly
• Using a non-existent load_resnet18 function

3. What will be the output shape of the following code snippet using a pre-trained ResNet18 model on a batch of 8 RGB images of size 224x224?

import torch
import torchvision.models as models
model = models.resnet18(weights=models.ResNet18_Weights.IMAGENET1K_V1)
model.eval()
inputs = torch.randn(8, 3, 224, 224)
outputs = model(inputs)
print(outputs.shape)

medium

A. torch.Size([8, 3, 224, 224])

B. torch.Size([8, 1000])

C. torch.Size([8, 512])

D. torch.Size([1, 1000])

Solution

1. Step 1: Understand ResNet18 output size

   ResNet18 pre-trained on ImageNet outputs logits for 1000 classes, so output shape is (batch_size, 1000).

2. Step 2: Check input batch size and output shape

   Input batch size is 8, so output shape is (8, 1000).

3. Final Answer:

   torch.Size([8, 1000]) -> Option B

4. Quick Check:

   Batch size 8, 1000 classes output [OK]

Hint: Output shape = (batch_size, number_of_classes) [OK]

Common Mistakes:

• Confusing output with input image shape
• Expecting feature vector size instead of class logits
• Assuming batch size 1 output

4. You wrote this code to use a pre-trained model for prediction but get wrong results:

model = torchvision.models.resnet18(weights=torchvision.models.ResNet18_Weights.IMAGENET1K_V1)
inputs = torch.randn(1, 3, 224, 224)
outputs = model(inputs)

What is the likely mistake?

medium

A. Input tensor shape should be (3, 224, 224) without batch dimension.

B. You need to set weights=None to use pre-trained weights.

C. You forgot to call model.eval() before prediction.

D. You must convert inputs to numpy arrays before passing to model.

Solution

1. Step 1: Check model mode for prediction

   Pre-trained models must be set to evaluation mode with model.eval() to disable dropout and batch norm updates.

2. Step 2: Identify the missing step

   The code misses model.eval(), so outputs may be incorrect or inconsistent.

3. Final Answer:

   You forgot to call model.eval() before prediction. -> Option C

4. Quick Check:

   Set model.eval() before inference [OK]

Hint: Always call model.eval() before predicting [OK]

Common Mistakes:

• Not calling model.eval() before inference
• Wrong input tensor shape without batch
• Trying to convert tensors to numpy before model

5. You want to fine-tune a pre-trained ResNet18 model on your own 5-class dataset. Which of the following code snippets correctly replaces the final layer for this task?

hard

A. model.fc = torch.nn.Linear(in_features=512, out_features=5)

B. model.classifier = torch.nn.Linear(in_features=1000, out_features=5)

C. model.fc = torch.nn.Linear(in_features=2048, out_features=5)

D. model.output = torch.nn.Linear(in_features=512, out_features=1000)

Solution

1. Step 1: Identify the final layer of ResNet18

   ResNet18's final fully connected layer is model.fc with input features 512 and output 1000 classes.

2. Step 2: Replace final layer for 5 classes

   To fine-tune, replace model.fc with a new Linear layer with 512 inputs and 5 outputs.

3. Final Answer:

   model.fc = torch.nn.Linear(in_features=512, out_features=5) -> Option A

4. Quick Check:

   Replace model.fc with correct output size [OK]

Hint: Replace model.fc with Linear(512, number_of_classes) [OK]

Common Mistakes:

• Replacing wrong attribute like model.classifier
• Using wrong input feature size (2048 instead of 512)
• Not changing output features to dataset classes