CNN architecture review in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding Convolutional Layer Output Size

Given an input image of size 64x64 with 3 color channels, a convolutional layer uses 16 filters of size 3x3, stride 1, and padding 1. What will be the output shape of this convolutional layer?

A (62, 62, 16)

B (66, 66, 16)

C (64, 64, 16)

D (64, 64, 3)

💡 Hint

Remember that padding of 1 keeps the spatial dimensions the same when stride is 1.

Padding of 1 adds one pixel border around the input, so the output spatial size remains 64x64. The number of filters determines the depth, which is 16.

❓ Predict Output

intermediate

Output Shape After Max Pooling

What is the output shape after applying a 2x2 max pooling layer with stride 2 on an input tensor of shape (32, 32, 10)?

A (16, 16, 10)

B (15, 15, 10)

C (31, 31, 10)

D (32, 32, 10)

💡 Hint

Max pooling reduces spatial dimensions by the stride when filter size equals stride.

With 2x2 filter and stride 2, the height and width are halved. Depth remains the same.

❓ Hyperparameter

advanced

Choosing Kernel Size for Edge Detection

You want to design a CNN layer to detect edges in images. Which kernel size is most appropriate for this task?

A 3x3 kernel

B 1x1 kernel

C 7x7 kernel

D 15x15 kernel

💡 Hint

Edge detection usually requires small kernels to capture local gradients.

3x3 kernels are commonly used for edge detection because they capture local changes effectively without too much computation.

❓ Metrics

advanced

Interpreting CNN Training Accuracy

A CNN model training on image classification shows training accuracy of 98% but validation accuracy of 75%. What is the most likely explanation?

A The model is underfitting the training data

B The model is overfitting the training data

C The validation data is corrupted

D The training data is too small

💡 Hint

High training accuracy but low validation accuracy usually means the model memorizes training data.

Overfitting happens when the model learns training data too well but fails to generalize to new data.

🔧 Debug

expert

Identifying Error in CNN Layer Definition

Consider this PyTorch CNN layer definition:

nn.Conv2d(in_channels=3, out_channels=32, kernel_size=3, stride=2, padding=2)

What is the output size for an input image of size 64x64? Is there an error in the output size calculation?

A Output size is 64x64; stride 2 has no effect

B Output size is 32x32; padding is correct for stride 2

C Output size is 31x31; padding is too small causing output to shrink

D Output size is 33x33; padding is too large causing output to be bigger than expected

💡 Hint

Use the formula: ((Input - Kernel + 2*Padding) / Stride) + 1

Output size = floor((64 - 3 + 2*2) / 2) + 1 = floor((64 - 3 + 4)/2) + 1 = floor(65/2) + 1 = 32 + 1 = 33. Padding of 2 is large for kernel 3 and stride 2, causing output to be larger than half input size.