search

vibalab / CNNExplorer

0 stars 0 forks source link

Understanding Conv Blocks #5

Closed sungwookson closed 6 months ago

sungwookson commented 7 months ago

I have issue understanding current conv blocks

sungwookson commented 7 months ago

AlexNet

image image

Above are information regarding AlexNet. On svelte app, there are 3 conv blocks while actual alexnet has 5 blocks

Is it?

  1. Conv Block 1
    • (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
    • (1): ReLU(inplace=True)
    • (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
  2. Conv Block 2
    • (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    • (4): ReLU(inplace=True)
    • (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
  3. Conv Block 3
    • (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    • (7): ReLU(inplace=True)
    • (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    • (9): ReLU(inplace=True)
    • (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    • (11): ReLU(inplace=True)
    • (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
Negota commented 7 months ago

I divided convolution block based on the point where the pooling layer ends.