Hi
I had a look at the Focus layer and it seems to me like it is equivalent to a simple 2d-convolutional layer without the need for the space-to-depth operation. For example, a Focus layer with kernel size 3 can be expressed as a Conv layer with kernel size 6 and stride 2 . I wrote some code to verify this:
import torch
from models.common import Focus, Conv
from utils.torch_utils import profile
focus = Focus(3, 64, k=3).eval()
conv = Conv(3, 64, k=6, s=2, p=2).eval()
# Express focus layer as conv layer
conv.bn = focus.conv.bn
conv.conv.weight.data[:, :, ::2, ::2] = focus.conv.conv.weight.data[:, :3]
conv.conv.weight.data[:, :, 1::2, ::2] = focus.conv.conv.weight.data[:, 3:6]
conv.conv.weight.data[:, :, ::2, 1::2] = focus.conv.conv.weight.data[:, 6:9]
conv.conv.weight.data[:, :, 1::2, 1::2] = focus.conv.conv.weight.data[:, 9:12]
# Compare
x = torch.randn(16, 3, 640, 640)
with torch.no_grad():
# Results are not perfectly identical, errors up to about 1e-7 occur (probably numerical)
assert torch.allclose(focus(x), conv(x), atol=1e-6)
# Profile
results = profile(input=torch.randn(16, 3, 640, 640), ops=[focus, conv, focus, conv], n=10, device=0)And the output as follows:
YOLOv5 🚀 v5.0-434-g0dc725e torch 1.9.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536.1875MB)
Params GFLOPs GPU_mem (GB) forward (ms) backward (ms) input output
7040 23.07 2.682 4.055 13.78 (16, 3, 640, 640) (16, 64, 320, 320)
7040 23.07 2.368 3.474 9.989 (16, 3, 640, 640) (16, 64, 320, 320)
7040 23.07 2.343 3.556 11.57 (16, 3, 640, 640) (16, 64, 320, 320)
7040 23.07 2.368 3.456 9.961 (16, 3, 640, 640) (16, 64, 320, 320)I did have to slightly tweak the tolerance in torch.allcose for the assertion to succeed, but looking at the errors they seem to be purely numerical.
So am I missing something or could the Focus layer simply be replaced by a Conv layer which would lead to a slight increase in speed?
Hi
I had a look at the Focus layer and it seems to me like it is equivalent to a simple 2d-convolutional layer without the need for the space-to-depth operation. For example, a
Focuslayer with kernel size 3 can be expressed as aConvlayer with kernel size 6 and stride 2 . I wrote some code to verify this:And the output as follows:
I did have to slightly tweak the tolerance in
torch.allcosefor the assertion to succeed, but looking at the errors they seem to be purely numerical.So am I missing something or could the
Focuslayer simply be replaced by aConvlayer which would lead to a slight increase in speed?