Why pre-trained models save time in Computer Vision

Introduction

Pre-trained models save time because they have already learned useful features from large datasets. This means you don't have to start learning from scratch, making your work faster and easier.

When you want to quickly build an image recognition app without collecting lots of data.

When you have limited computing power and want to avoid long training times.

When you want to improve your model's accuracy by using knowledge learned from big datasets.

When you need a good starting point for your own custom model.

When you want to experiment with different tasks without training a new model each time.

Syntax

Computer Vision

from torchvision import models

model = models.resnet18(weights='IMAGENET1K_V1')

This example loads a pre-trained ResNet18 model from PyTorch's torchvision library.

Setting weights='IMAGENET1K_V1' loads the model weights learned on a large dataset.

Examples

Loads the VGG16 model pre-trained on ImageNet dataset using TensorFlow Keras.

Computer Vision

from tensorflow.keras.applications import VGG16

model = VGG16(weights='imagenet')

Loads the AlexNet model with pre-trained weights from PyTorch.

Computer Vision

import torchvision.models as models

model = models.alexnet(weights='IMAGENET1K_V1')

Sample Model

This code loads a pre-trained ResNet18 model and uses it to predict the class of a dog image. It shows how pre-trained models can quickly give accurate predictions without training.

Computer Vision

import torch
from torchvision import models, transforms
from PIL import Image
import requests

# Load pre-trained ResNet18 model
model = models.resnet18(weights=models.ResNet18_Weights.IMAGENET1K_V1)
model.eval()

# Image preprocessing
preprocess = transforms.Compose([
    transforms.Resize(256),
    transforms.CenterCrop(224),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406],
                         std=[0.229, 0.224, 0.225])
])

# Download an example image
url = 'https://upload.wikimedia.org/wikipedia/commons/9/9a/Pug_600.jpg'
image = Image.open(requests.get(url, stream=True).raw)

# Preprocess the image
input_tensor = preprocess(image)
input_batch = input_tensor.unsqueeze(0)  # create a mini-batch

# Run the model
with torch.no_grad():
    output = model(input_batch)

# Load labels
labels_url = 'https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt'
labels = requests.get(labels_url).text.splitlines()

# Get top prediction
probabilities = torch.nn.functional.softmax(output[0], dim=0)
confidence, predicted_idx = torch.max(probabilities, 0)

print(f'Predicted label: {labels[predicted_idx]}')
print(f'Confidence: {confidence.item():.4f}')

Important Notes

Pre-trained models are trained on large datasets like ImageNet with millions of images.

You can fine-tune pre-trained models on your own smaller dataset to improve results.

Summary

Pre-trained models save time by reusing learned features from big datasets.

They help you get good results quickly without long training.

You can use them as a starting point for your own projects.

Practice

1. Why do pre-trained models save time in computer vision projects?

easy

A. They require more data to train from scratch

B. They eliminate the need for any data preprocessing

C. They always produce perfect results without any training

D. They reuse features learned from large datasets, reducing training time

Solution

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

   Pre-trained models have already learned useful features from large datasets, so you don't start from zero.

2. Step 2: Connect this to time saved

   Since the model already knows many features, you spend less time training it on your own data.

3. Final Answer:

   They reuse features learned from large datasets, reducing training time -> Option D

4. Quick Check:

   Pre-trained models reuse features = B [OK]

Hint: Pre-trained means already learned features reused [OK]

Common Mistakes:

• Thinking pre-trained models need more data
• Believing they need no training at all
• Assuming they remove all preprocessing

2. Which of the following is the correct way to load a pre-trained model in Python using PyTorch?

easy

A. model = torchvision.models.resnet50(pretrained=True)

B. model = torchvision.models.resnet50(pretrained=False)

C. model = torchvision.load_model('resnet50')

D. model = torch.load('resnet50_pretrained')

Solution

1. Step 1: Recall PyTorch syntax for loading pre-trained models

   In PyTorch, you use torchvision.models with pretrained=True to load a pre-trained model.

2. Step 2: Check options for correctness

   model = torchvision.models.resnet50(pretrained=True) uses the correct function and argument. model = torchvision.models.resnet50(pretrained=False) loads without pre-training. Options C and D are incorrect function calls.

3. Final Answer:

   model = torchvision.models.resnet50(pretrained=True) -> Option A

4. Quick Check:

   PyTorch pre-trained load = A [OK]

Hint: Use pretrained=True to load pre-trained models in PyTorch [OK]

Common Mistakes:

• Using pretrained=False by mistake
• Calling non-existent functions like torchvision.load_model
• Trying to load model weights incorrectly

3. Consider this Python code using TensorFlow to load a pre-trained MobileNetV2 model and predict on an input image:

import tensorflow as tf
model = tf.keras.applications.MobileNetV2(weights='imagenet')
import numpy as np
input_data = np.random.rand(1, 224, 224, 3).astype('float32')
predictions = model.predict(input_data)
print(predictions.shape)

What will be the printed output shape?

medium

A. (224, 224, 3)

B. (1, 1000)

C. (1, 224, 224, 3)

D. (1000,)

Solution

1. Step 1: Understand MobileNetV2 output shape

   MobileNetV2 pre-trained on ImageNet outputs predictions for 1000 classes, so output shape is (batch_size, 1000).

2. Step 2: Check input batch size and output

   Input batch size is 1, so output shape is (1, 1000).

3. Final Answer:

   (1, 1000) -> Option B

4. Quick Check:

   Output shape = (batch, 1000 classes) = A [OK]

Hint: Output shape matches batch size and number of classes [OK]

Common Mistakes:

• Confusing input shape with output shape
• Ignoring batch dimension
• Expecting output shape to match input image size

4. You tried to fine-tune a pre-trained model but got an error: AttributeError: 'Sequential' object has no attribute 'fc'. What is the likely cause?

medium

A. You used a model architecture without an 'fc' layer and tried to access it

B. You forgot to load pre-trained weights

C. You passed wrong input shape to the model

D. You used the wrong optimizer

Solution

1. Step 1: Understand the error message

   The error says the model has no attribute 'fc', which usually means the model architecture does not have a fully connected layer named 'fc'.

2. Step 2: Connect error to cause

   Trying to access or modify 'fc' layer on a Sequential model that doesn't have it causes this error.

3. Final Answer:

   You used a model architecture without an 'fc' layer and tried to access it -> Option A

4. Quick Check:

   Missing 'fc' layer attribute = D [OK]

Hint: Check if model has the layer before accessing it [OK]

Common Mistakes:

• Assuming all models have 'fc' layer
• Ignoring error details
• Blaming optimizer or input shape wrongly

5. You want to use a pre-trained model to classify images of cats and dogs but your dataset has only 500 images. Which approach saves the most time while achieving good accuracy?

hard

A. Use a pre-trained model without any fine-tuning and directly predict

B. Train a new model from scratch with random weights on your 500 images

C. Use a pre-trained model and fine-tune only the last layer on your dataset

D. Manually label more images before training any model

Solution

1. Step 1: Consider dataset size and training time

   With only 500 images, training from scratch is slow and likely inaccurate.

2. Step 2: Use pre-trained model fine-tuning

   Fine-tuning only the last layer uses learned features and adapts to your task quickly and efficiently.

3. Final Answer:

   Use a pre-trained model and fine-tune only the last layer on your dataset -> Option C

4. Quick Check:

   Fine-tune last layer for small data = C [OK]

Hint: Fine-tune last layer for small datasets [OK]

Common Mistakes:

• Training from scratch with little data
• Skipping fine-tuning and expecting perfect results
• Spending time labeling more data unnecessarily