search

tianzhi0549 / FCOS

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
https://arxiv.org/abs/1904.01355
Other
3.26k stars 630 forks source link

Can’t calculate the Params and FLOPs of Backbone #382

Open Pooky-Z opened 2 years ago

Pooky-Z commented 2 years ago

used thop,torchstat and ptflops to caculate the Flops of the model, but all of the results shows there is 0 params and 0 flops in ResNet and FPN. Why did this happen and how can I calucalte the Flops of model correctly. Thank you!

The example of output of the pyflops: Warning: module Conv2d is treated as a zero-op. Warning: module FrozenBatchNorm2d is treated as a zero-op. Warning: module StemWithFixedBatchNorm is treated as a zero-op. Warning: module BottleneckWithFixedBatchNorm is treated as a zero-op. Warning: module ResNet is treated as a zero-op. Warning: module GeneralizedRCNN is treated as a zero-op. GeneralizedRCNN( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (backbone): ResNet( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (stem): StemWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (layer1): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (downsample): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (1): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (2): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) ) (layer2): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (downsample): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (1): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (2): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (3): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) ) (layer3): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (downsample): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (1): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (2): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (3): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (4): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (5): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) ) (layer4): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (downsample): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (1): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (2): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) ) ) ) 0.0 Mac