Why torchvision pre-trained models in PyTorch? - Purpose & Use Cases

The Big Idea

What if you could skip months of training and still get a powerful image recognition model ready to use?

The Scenario

Imagine you want to build a computer program that can recognize objects in photos, like cats, dogs, or cars. Doing this from scratch means you have to teach the program by showing it millions of pictures and telling it what each one is.

The Problem

Training a model from zero takes a lot of time, powerful computers, and tons of data. It's easy to make mistakes, and the program might not learn well if you don't have enough examples or the right setup.

The Solution

Using torchvision pre-trained models means you start with a program that already knows how to recognize many objects because it was trained on huge image collections. You just fine-tune it for your specific task, saving time and effort.

Before vs After

✗ Before

model = MyCustomModel()
train(model, millions_of_images)

✓ After

import torchvision
model = torchvision.models.resnet50(pretrained=True)
finetune(model, your_images)

What It Enables

You can quickly build smart image recognition tools without needing massive data or long training times.

Real Life Example

A small startup uses a pre-trained model to create an app that identifies plant species from photos, launching their product much faster than if they trained a model from scratch.

Key Takeaways

Training models from scratch is slow and costly.

Pre-trained models come ready with learned knowledge.

Fine-tuning pre-trained models speeds up building smart apps.

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