How to calculate flops and params in deep learning

Just as a record , Big man, please skip .

When model After reading , Use ：

from thop import profile

dummy_input = torch.randn(1, 3, 224, 224)
flops, params = profile(model, (dummy_input,))
print('flops: ', flops, 'params: ', params)
print('flops: %.2f M, params: %.2f M' % (flops / 1000000.0, params / 1000000.0))

that will do .

Such as resnet-101 Of ：

Reference resources

Portal