Skip to content
Datamewby Intura
Start free
Computer Vision with Deep Learning

Image Classification with CNNs

Building a CNN in PyTorch, transfer learning from pretrained models, and evaluating a classifier honestly.

Level
Intermediate
Lessons
3
Total time
56 min
Simulations
3
Included in Computer Vision with Deep Learning · $9
Tools you'll use
  • Python
  • PyTorch
  • OpenCV
Skills
  • CNNs in PyTorch
  • Transfer learning
  • ResNet

What you will be able to do

  • Train an image classifier from a small dataset
  • Read a multi-class confusion matrix

Before you start

A suggestion, never a lock — you can start here.

  • image-fundamentals
Modules that help first

Syllabus

3 lessons · 56 min

Every lesson's title and summary is public. The lessons themselves open once you own the track.

Every lesson in Computer Vision with Deep Learning

  1. Building a CNN in PyTorch

    22 min

    Conv2d, pooling and a classification head — from scratch to trained.

    Included with the track Simulation

  2. Transfer Learning with Pretrained Backbones

    18 min

    Freezing, fine-tuning, and different learning rates per layer.

    Included with the track Simulation

  3. Evaluating Image Classifiers

    16 min

    Confusion matrices, imbalanced classes, and looking at the mistakes.

    Included with the track Simulation
Lifetime access
$9
Buy the track
More in Computer Vision with Deep Learning
Module · Beginner

Image Fundamentals

Images as numbers, convolution as a sliding weighted sum, and why a CNN learns its own filters.

  • 3 lessons
  • 48 min
  • 4 simulations
Included in Computer Vision with Deep Learning· $9
Module · Intermediate

Object Detection

Bounding boxes, IoU, one-stage detectors like YOLO, and how to read mAP.

  • 3 lessons
  • 53 min
  • 3 simulations
Included in Computer Vision with Deep Learning· $9
Module · Intermediate

Image Segmentation

Classification per pixel: semantic and instance segmentation, U-Net, and general segmentation models.

  • 3 lessons
  • 46 min
  • 2 simulations
Included in Computer Vision with Deep Learning· $9
Module · Intermediate

Vision Transformers and Multimodal Models

ViT, CLIP and vision-language models — when images and text share one embedding space.

  • 3 lessons
  • 52 min
  • 2 simulations
Included in Computer Vision with Deep Learning· $9