Custom detection dataset in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a custom detection dataset in PyTorch?

A custom detection dataset is a user-defined dataset class that loads images and their bounding box annotations for object detection tasks, allowing PyTorch models to train on data not included in standard datasets.

beginner

Which PyTorch class do you typically extend to create a custom detection dataset?

You extend the torch.utils.data.Dataset class to create a custom detection dataset, implementing __len__ and __getitem__ methods.

intermediate

What should the __getitem__ method return in a custom detection dataset for object detection?

It should return a tuple: (image_tensor, target), where target is a dictionary containing keys like 'boxes' (bounding boxes), 'labels' (class labels), and optionally 'masks' or 'area'.

beginner

Why do bounding boxes in detection datasets use tensors of shape [N, 4]?

Because each bounding box is represented by 4 numbers (xmin, ymin, xmax, ymax), and N is the number of objects in the image, so the tensor shape is [N, 4].

intermediate

How can you apply transformations to images and targets in a custom detection dataset?

You can pass a transform function to the dataset class and apply it inside __getitem__ to both the image and the target dictionary, ensuring consistent augmentation.

What method must be implemented when creating a custom PyTorch dataset?

A __getitem__

B __init__

C __call__

D __len__

Both __getitem__ and __len__ must be implemented to define how to get an item and the dataset size.

In object detection datasets, what does the 'labels' key in the target dictionary represent?

A Coordinates of bounding boxes

B Class IDs of objects

C Image pixel values

D Image file paths

'labels' contains the class IDs for each object in the image.

Which of these is NOT typically part of the target dictionary in detection datasets?

A boxes

B labels

C masks

D image size

'image size' is usually not included in the target dictionary.

What shape does the bounding boxes tensor usually have?

A [N, 4]

B [4, N]

C [N, N]

D [4]

Bounding boxes tensor shape is [N, 4], where N is number of boxes.

Why is it important to apply the same transform to both image and target?

A To keep image and annotations aligned

B To speed up training

C To reduce dataset size

D To change class labels

Applying the same transform keeps bounding boxes aligned with the image.

Describe how to create a custom detection dataset class in PyTorch.

Think about what data the model needs and how to provide it.

Explain the structure and contents of the target dictionary in a detection dataset.

Focus on what information describes each object.

Practice

1. What is the main purpose of creating a Custom detection dataset in PyTorch?

easy

A. To perform image classification without labels

B. To convert images to grayscale only

C. To generate random images for testing

D. To load images and their bounding boxes with labels for training detection models

Solution

1. Step 1: Understand dataset role in detection

   A detection dataset provides images along with bounding boxes and labels for each object to train detection models.

2. Step 2: Identify correct purpose

   Classification without labels, random image generation, and grayscale conversion do not provide bounding boxes or labels needed for detection tasks.

3. Final Answer:

   To load images and their bounding boxes with labels for training detection models -> Option D

4. Quick Check:

   Detection dataset = images + bounding boxes + labels [OK]

Hint: Detection datasets always include bounding boxes and labels [OK]

Common Mistakes:

• Thinking detection datasets only have images
• Confusing detection with classification datasets
• Ignoring bounding boxes in dataset

2. Which of the following is the correct way to define the __getitem__ method in a custom detection dataset class?

easy

A. def __getitem__(self): return image, label

B. def __getitem__(self, idx): return image, label

C. def __getitem__(self, idx): return image, bounding_boxes, labels

D. def getitem(self, idx): return image, bounding_boxes

Solution

1. Step 1: Recall __getitem__ signature

   The method must accept an index parameter and return image, bounding boxes, and labels for detection.

2. Step 2: Check options for correct syntax and return values

   def __getitem__(self, idx): return image, bounding_boxes, labels correctly uses def __getitem__(self, idx): and returns image, bounding boxes, and labels. Others miss parameters or return incomplete data.

3. Final Answer:

   def __getitem__(self, idx): return image, bounding_boxes, labels -> Option C

4. Quick Check:

   __getitem__ needs idx and returns image + boxes + labels [OK]

Hint: __getitem__ always takes index and returns image with boxes and labels [OK]

Common Mistakes:

• Omitting the idx parameter
• Returning only image and label without boxes
• Using wrong method name without underscores

3. Given this snippet from a custom detection dataset, what will be the output type of dataset[0]?

class CustomDataset(torch.utils.data.Dataset):
    def __getitem__(self, idx):
        image = self.images[idx]
        boxes = self.boxes[idx]
        labels = self.labels[idx]
        target = {"boxes": boxes, "labels": labels}
        return image, target

medium

A. A tuple containing an image tensor and a dictionary with boxes and labels

B. A list containing image, boxes, and labels separately

C. Only the image tensor

D. A dictionary with keys 'image' and 'target'

Solution

1. Step 1: Analyze return statement

   The method returns image, target where target is a dictionary with keys 'boxes' and 'labels'.

2. Step 2: Determine output type

   Returning two items separated by comma means a tuple is returned: (image, target dictionary).

3. Final Answer:

   A tuple containing an image tensor and a dictionary with boxes and labels -> Option A

4. Quick Check:

   Return image, target dict = tuple [OK]

Hint: Comma-separated returns form a tuple in Python [OK]

Common Mistakes:

• Thinking return is a list instead of tuple
• Assuming only image is returned
• Confusing dictionary keys with return structure

4. You wrote this __getitem__ method but get an error when loading data:

def __getitem__(self, idx):
    image = self.images[idx]
    boxes = self.boxes[idx]
    labels = self.labels[idx]
    target = {"boxes": boxes, "labels": labels}
    return image, target

What is the most likely cause of the error?

medium

A. Missing return statement

B. boxes and labels are not converted to tensors

C. image is not normalized

D. Incorrect method name without underscores

Solution

1. Step 1: Check common dataset errors

   Detection models expect bounding boxes and labels as tensors, not raw lists or arrays.

2. Step 2: Identify missing tensor conversion

   If boxes and labels are not converted to tensors, PyTorch will raise errors during training or data loading.

3. Final Answer:

   boxes and labels are not converted to tensors -> Option B

4. Quick Check:

   Boxes and labels must be tensors [OK]

Hint: Always convert boxes and labels to tensors before returning [OK]

Common Mistakes:

• Forgetting to convert boxes and labels to torch tensors
• Assuming image normalization fixes tensor errors
• Using wrong method name causing attribute errors

5. You want to add a transform that flips images horizontally and adjusts bounding boxes accordingly in your custom detection dataset. Which approach is best?

hard

A. Apply the horizontal flip transform to both image and bounding boxes inside __getitem__

B. Flip bounding boxes but not the image

C. Apply the transform only after training the model

D. Apply the horizontal flip transform only to the image inside __getitem__, leave boxes unchanged

Solution

1. Step 1: Understand transform requirements

   When flipping images, bounding boxes must be adjusted to match the new image layout.

2. Step 2: Apply transform to both image and boxes

   Applying the transform only to the image or only to boxes causes mismatch and incorrect training data.

3. Final Answer:

   Apply the horizontal flip transform to both image and bounding boxes inside __getitem__ -> Option A

4. Quick Check:

   Flip image and boxes together for correct data [OK]

Hint: Transform image and boxes together to keep alignment [OK]

Common Mistakes:

• Flipping only image or only boxes
• Applying transforms after training
• Ignoring bounding box coordinate updates