AlexNet b
Fit diagram
Read at 100%
Clear selection
Download SVG
Download PNG
Click a block to read its description, or select it with Tab and Enter.
AlexNet b
Classification, 224 × 224 input, 1,000 classes. Tensor sizes exclude batch.
LibreYOLO
AlexNet b
Classification, 224 × 224 input, 1,000 classes. Tensor sizes exclude batch.
Features 1
Input
3 × 224 × 224
Conv2d 11×11 / 4
64 × 55 × 55; p=2, g=1
ReLU
64 × 55 × 55
MaxPool2d
64 × 27 × 27
Conv2d 5×5 / 1
192 × 27 × 27; p=2, g=1
ReLU
192 × 27 × 27
MaxPool2d
192 × 13 × 13
Features 2
Conv2d 3×3 / 1
384 × 13 × 13; p=1, g=1
ReLU
384 × 13 × 13
Conv2d 3×3 / 1
256 × 13 × 13; p=1, g=1
ReLU
256 × 13 × 13
Conv2d 3×3 / 1
256 × 13 × 13; p=1, g=1
ReLU
256 × 13 × 13
MaxPool2d
256 × 6 × 6
Classifier
AdaptiveAvgPool2d
256 × 6 × 6
Flatten
9,216
Dropout (eval identity)
p=0.5; 9216
Linear
9216 to 4096
ReLU
4096
Dropout (eval identity)
p=0.5; 4096
Linear
4096 to 4096
ReLU
4096
Linear
4096 to 1000
Native single-tower graph: no local response normalization or grouped convolution.
Convolutions and Linear layers include bias. MaxPool kernels are 3×3 with stride 2.
Output: 1,000 logits. Dropout is inactive in the displayed eval graph.
Source: libreyolo/models/alexnet/nn.py. Revision a4d0ecc9e17f.
libreyolo.com