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.