Problems
Loading...
Step 4 of 6
VGG Configuration
Easy

Return the canonical convolution and pooling configuration for VGG11, VGG13, VGG16, or VGG19. Each integer is a convolution output-channel count and each string M is a 2 by 2 max-pooling layer. Accept the variant name case-insensitively. Return the configuration as a new Python list containing integers and M strings.

Loading visualization...

Examples

Input: variant = "vgg11"

Output: [64,"M",128,"M",256,256,"M",512,512,"M",512,512,"M"]

Explanation: VGG11 contains eight convolution entries grouped by five pooling entries.

Input: variant = "VGG16"

Output: [64,64,"M",128,128,"M",256,256,256,"M",512,512,512,"M",512,512,512,"M"]

Input: variant = "vgg19"

Output: [64,64,"M",128,128,"M",256,256,256,256,"M",512,512,512,512,"M",512,512,512,512,"M"]

Hint 1

Normalize the variant with str.lower().

Hint 2

Store the four canonical configurations in a dictionary.

Requirements

  • Use ordinary Python lists and strings.
  • Support VGG11, VGG13, VGG16, and VGG19.
  • Treat variant names case-insensitively.
  • Return a new Python list in canonical layer order.

Constraints

  • variant names one of the four supported VGG architectures, ignoring case.
Prev4 / 6Next