All information regarding the third homework assignment can be found here: UROB HW3 – Fruit Image Analysis Repository

This homework focuses on training a Convolutional Neural Network (CNN) to:

• 🏷️ Classify images of fruits into 30 categories
• 🎨 Segment fruits using pixel-level masks
• 🔍 Learn meaningful image embeddings

The goal is to design, train, and evaluate a model capable of performing all three tasks efficiently.

• Implement your CNN model in `model.py` as class `MyModel`
• The `forward()` method must return:
  1. Class logits `[batch_size, 30]`
  2. Segmentation mask `[batch_size, 1, 64, 64]`
  3. Image embeddings `[batch_size, embedding_dim]`
• Implement `get_embedding()` returning embeddings only
• Complete the training loop in `train.py`
• Tune hyperparameters in `confs/config.yml`

Basic Evaluation (10 points)

Tournament Evaluation (up to +5 bonus points) Models are ranked by performance across all tasks. Lower total rank = better score. Ties are broken by earlier submission.

* 🥇 1st place → +5 pts * 🥈 2nd → +4 pts * 🥉 3rd → +3 pts * 🏅 Top 10 → +2 pts * 🎖️ Top 20 → +1 pt

Maximum total = 15 points

Submit a ZIP file containing:

• `model.py` – your model
• `train.py` – your training script
• `weights.pth` – trained model weights

Pretrained Models Policy ❌ No pretrained models or transfer learning allowed. ✅ Train from scratch using only the provided dataset.

Plagiarism Policy ✅ You may discuss ideas with classmates. ❌ Direct code copying = 0 points.

Good luck! 🍀 For questions, contact: hlavsja3@fel.cvut.cz