Skip to content

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

1 watching

Forks

Latest commit

 

History

4 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MyCNN

A convolutional image classifier written from scratch in PyTorch.
100×100 grayscale images in, scores over 20 classes out.

Python PyTorch torchvision Parameters

Animation: a 100 by 100 grayscale image passes through four convolution blocks (50×50×64, 25×25×128, 12×12×256, 6×6×512), global average pooling and two linear layers, ending in scores over 20 classes. Augmentations shown: flip, rotation, blur, noise.

The layer shapes are the real ones from architecture.py; the input image and the scores are illustrative.


Architecture

Stage Layers Output
Input grayscale image 1 × 100 × 100
Block 1 Conv 3×3 (64) → ReLU → MaxPool 2 → BatchNorm 64 × 50 × 50
Block 2 Conv 3×3 (128) → ReLU → MaxPool 2 → BatchNorm → Dropout 0.4 128 × 25 × 25
Block 3 Conv 3×3 (256) → ReLU → MaxPool 2 → BatchNorm 256 × 12 × 12
Block 4 Conv 3×3 (512) → ReLU → MaxPool 2 → BatchNorm 512 × 6 × 6
Head Global average pool → Linear 512 → ReLU → Dropout 0.5 → Linear 20 20 scores

1,824,660 trainable parameters. Global average pooling keeps the head small: most parameters sit in the last conv block (1.18M), not in the classifier.

Data pipeline

dataset.py reads a folder of .jpg images plus one .csv (semicolon-separated, header row, filename;classname) and returns (image, class_id, class_name, path).

  • Grayscale done properly: RGB is converted to linear light, weighted with the Rec. 709 luminance coefficients (0.2126, 0.7152, 0.0722), then gamma-encoded back, rather than averaging the channels.
  • Fixed size without distortion: images are centre-cropped or edge-padded to 100 × 100, never stretched.
  • Normalised to [0, 1].

Augmentation

utils.DataTransforms defines four training pipelines, so the model sees each image under different distortions:

Pipeline What it varies
1 horizontal flip, rotation ±30°, random crop with padding
2 vertical flip, affine (rotate, translate, scale, shear), colour jitter
3 rotation ±45°, Gaussian blur, random resized crop
4 random grayscale, affine, additive Gaussian noise (σ 0.5)

Use it

import torch
from torch.utils.data import DataLoader
from architecture import MyCNN
from dataset import ImagesDataset
from utils import evaluate_model

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
data = ImagesDataset("path/to/images", width=100, height=100)
loader = DataLoader(data, batch_size=64)

model = MyCNN().to(device)
loss, accuracy = evaluate_model(model, loader, torch.nn.CrossEntropyLoss(), device)
print(f"loss {loss:.3f} · accuracy {accuracy:.1f}%")

Files

File Contents
architecture.py MyCNN
dataset.py ImagesDataset, grayscale conversion, crop/pad to size
utils.py evaluate_model, noise helpers, the four augmentation pipelines

The animation at the top is drawn frame by frame in code (canvas → headless Chromium → ffmpeg): source.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages