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.