1. Did you verify the dataset structure by checking for agricultural and non-agricultural folders?

✅ Yes
❌ No

Explanation:
Verifying the directory structure ensures the dataset is organized correctly for both the custom class and ImageFolder.

---

2. Did you implement the CustomBinaryClassDataset class with __init__, __len__, and __getitem__?

✅ Yes
❌ No

Explanation:
These three methods are essential for PyTorch to load samples, compute dataset length, and retrieve items.

---

3. Did you create the custom_transform using transforms.Compose?

✅ Yes
❌ No

Explanation:
transforms.Compose allows chaining multiple preprocessing steps into one transform pipeline.

---

4. Did you add Resize((64, 64)) to your transform pipeline?

✅ Yes
❌ No

Explanation:
Resizing ensures all images have uniform dimensions for batch processing and model input.

---

5. Did you add ToTensor() to your transform pipeline?

✅ Yes
❌ No

Explanation:
ToTensor() converts images into PyTorch tensors and normalizes pixel values to [0,1].

---

6. Did you add Normalize(mean=[0.5]*3, std=[0.5]*3)?

✅ Yes
❌ No

Explanation:
Normalization brings pixel values into [-1, 1], which helps stable training in neural networks.

---

7. Did you instantiate CustomBinaryClassDataset with base directory and transform?

✅ Yes
❌ No

Explanation:
Creating the dataset object finalizes your custom pipeline for loading images.

---

8. Did you create an ImageFolder dataset using datasets.ImageFolder?

✅ Yes
❌ No

Explanation:
ImageFolder is a simple and reliable baseline dataset loader for structured images.

---

9. Did you create DataLoader objects for both datasets with batch_size, shuffle=True, and num_workers=2?

✅ Yes
❌ No

Explanation:
DataLoaders handle batching, parallel loading, and shuffling, improving training performance.

---

10. Did you extract sample batches using iter() and next() from both DataLoaders?

✅ Yes
❌ No

Explanation:
Extracting batches checks if the dataset and DataLoader work correctly before model training.

---

11. Did you complete the tasks and download the Jupyter notebook?

✅ Yes
❌ No

Explanation:
Downloading ensures you can upload your notebook for final course evaluation.

---

🧾 Summary Table

---