DeformConv2d not supported in FLOPs counting?

[kenmbkr]

I tested flop counting for DeformConv2d and I am getting 0 for flops. The code to reproduce is as follows. Please kindly advise how to get the correct FLOPs.

import torch
from fvcore.nn import FlopCountAnalysis, flop_count_table
from torchvision.ops import DeformConv2d

kernel_size = 3
conv = DeformConv2d(64, 64, kernel_size=kernel_size, padding=1)
x = torch.randn(1, 64, 64, 64)
offset = torch.randn(1, 2 * kernel_size * kernel_size, 64, 64)

flops = FlopCountAnalysis(conv, (x, offset))
print(flop_count_table(flops, max_depth=1))

| module   | #parameters or shape   | #flops   |
|:---------|:-----------------------|:---------|
| model    | 36.928K                | 0        |
|  weight  |  (64, 64, 3, 3)        |          |
|  bias    |  (64,)                 |          |

[ppwwyyxx]

print(flops.unsupported_ops()) will show that deform_conv was encountered once in the model but unsupported (because its formula was not included).

[kenmbkr]

print(flops.unsupported_ops()) will show that deform_conv was encountered once in the model but unsupported (because its formula was not included).

@ppwwyyxx Thank you for the confirmation. Are there any plans to support it in the future?