Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add SPPF() layer #4420

Merged
merged 3 commits into from
Aug 15, 2021
Merged

Add SPPF() layer #4420

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
91580c2
Add `SPPF()` layer
glenn-jocher Aug 15, 2021
6494bb6
Cleanup
glenn-jocher Aug 15, 2021
8c89f4f
Add credit
glenn-jocher Aug 15, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 19 additions & 1 deletion models/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,7 +161,7 @@ def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):


class SPP(nn.Module):
# Spatial pyramid pooling layer used in YOLOv3-SPP
# Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
def __init__(self, c1, c2, k=(5, 9, 13)):
super().__init__()
c_ = c1 // 2 # hidden channels
Expand All @@ -176,6 +176,24 @@ def forward(self, x):
return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))


class SPPF(nn.Module):
# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13))
super().__init__()
c_ = c1 // 2 # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_ * 4, c2, 1, 1)
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)

def forward(self, x):
x = self.cv1(x)
with warnings.catch_warnings():
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
y1 = self.m(x)
y2 = self.m(y1)
return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))


class Focus(nn.Module):
# Focus wh information into c-space
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
Expand Down
10 changes: 6 additions & 4 deletions models/yolo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,8 +237,8 @@ def parse_model(d, ch): # model_dict, input_channels(3)
pass

n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP,
C3, C3TR, C3SPP, C3Ghost]:
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
c1, c2 = ch[f], args[0]
if c2 != no: # if not output
c2 = make_divisible(c2 * gw, 8)
Expand Down Expand Up @@ -279,6 +279,7 @@ def parse_model(d, ch): # model_dict, input_channels(3)
parser = argparse.ArgumentParser()
parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--profile', action='store_true', help='profile model speed')
opt = parser.parse_args()
opt.cfg = check_file(opt.cfg) # check file
set_logging()
Expand All @@ -289,8 +290,9 @@ def parse_model(d, ch): # model_dict, input_channels(3)
model.train()

# Profile
# img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 320, 320).to(device)
# y = model(img, profile=True)
if opt.profile:
img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
y = model(img, profile=True)

# Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
# from torch.utils.tensorboard import SummaryWriter
Expand Down