Need to support AdaptiveAvgPool2d for ResNet

[sakaia]

When I run on TensorWatch on Google Colab, Following messages are appeared.

[MAdd]: AdaptiveAvgPool2d is not supported!
[Flops]: AdaptiveAvgPool2d is not supported!
[Memory]: AdaptiveAvgPool2d is not supported!

Test Code is follows

!pip install tensorwatch

import tensorwatch as tw
import torchvision.models

resnet_model = torchvision.models.resnet50()
tw.model_stats(resnet_model, [1, 3, 224, 224])

[sytelus]

This is currently expected because TensorWatch uses another library called torchstat underneath which does not support AdaptiveAvgPool2d layers for computing Flops and Memory. We are looking in to enhancing torchstat but for now you will get flops which are bit less than actual values when model uses above layer.