Ankle/yolov5_ZWgra
1
0 Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

v2.0 Release (#491)

Browse Source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Glenn Jocher authored and GitHub committed 2020-07-23 15:34:23 -07:00
1 parent 5e970d45c4
commit 9da56b62dd
9 files changed
+77 -86
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

models/yolo.py
+12 -8
View File
@@ -5,7 +5,7 @@ from models.experimental import *
class Detect(nn.Module):
def __init__(self, nc=80, anchors=()): # detection layer
def __init__(self, nc=80, anchors=(), ch=()): # detection layer
super(Detect, self).__init__()
self.stride = None # strides computed during build
self.nc = nc # number of classes
@@ -16,6 +16,7 @@ class Detect(nn.Module):
a = torch.tensor(anchors).float().view(self.nl, -1, 2)
self.register_buffer('anchors', a) # shape(nl,na,2)
self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2)
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
self.export = False # onnx export
def forward(self, x):
@@ -23,6 +24,7 @@ class Detect(nn.Module):
z = [] # inference output
self.training |= self.export
for i in range(self.nl):
x[i] = self.m[i](x[i]) # conv
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
@@ -124,8 +126,7 @@ class Model(nn.Module):
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
m = self.model[-1] # Detect() module
for f, s in zip(m.f, m.stride): #  from
mi = self.model[f % m.i]
for mi, s in zip(m.m, m.stride): #  from
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
b[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
b[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum()) # cls
@@ -133,9 +134,9 @@ class Model(nn.Module):
def _print_biases(self):
m = self.model[-1] # Detect() module
for f in sorted([x % m.i for x in m.f]): #  from
b = self.model[f].bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
print(('%g Conv2d.bias:' + '%10.3g' * 6) % (f, *b[:5].mean(1).tolist(), b[5:].mean()))
for mi in m.m: #  from
b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
print(('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
# def _print_weights(self):
# for m in self.model.modules():
@@ -159,7 +160,7 @@ class Model(nn.Module):
def parse_model(d, ch): # model_dict, input_channels(3)
print('\n%3s%18s%3s%10s %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
na = (len(anchors[0]) // 2) # number of anchors
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
@@ -181,6 +182,7 @@ def parse_model(d, ch): # model_dict, input_channels(3)
# e = math.log(c2 / ch[1]) / math.log(2)
# c2 = int(ch[1] * ex ** e)
# if m != Focus:
c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
# Experimental
@@ -201,7 +203,9 @@ def parse_model(d, ch): # model_dict, input_channels(3)
elif m is Concat:
c2 = sum([ch[-1 if x == -1 else x + 1] for x in f])
elif m is Detect:
f = f or list(reversed([(-1 if j == i else j - 1) for j, x in enumerate(ch) if x == no]))
args.append([ch[x + 1] for x in f])
if isinstance(args[1], int): # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
else:
c2 = ch[f]
models/yolov5l.yaml
+11 -15
View File
@@ -5,9 +5,9 @@ width_multiple: 1.0 # layer channel multiple
# anchors
anchors:
- [116,90, 156,198, 373,326] # P5/32
- [30,61, 62,45, 59,119] # P4/16
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
@@ -19,15 +19,14 @@ backbone:
[-1, 9, BottleneckCSP, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, BottleneckCSP, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, BottleneckCSP, [1024, False]], # 9
]
# YOLOv5 head
head:
[[-1, 3, BottleneckCSP, [1024, False]], # 9
[-1, 1, Conv, [512, 1, 1]],
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, BottleneckCSP, [512, False]], # 13
@@ -35,18 +34,15 @@ head:
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, BottleneckCSP, [256, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 18 (P3/8-small)
[-1, 3, BottleneckCSP, [256, False]], # 17
[-2, 1, Conv, [256, 3, 2]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, BottleneckCSP, [512, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 22 (P4/16-medium)
[-1, 3, BottleneckCSP, [512, False]], # 20
[-2, 1, Conv, [512, 3, 2]],
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, BottleneckCSP, [1024, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 26 (P5/32-large)
[-1, 3, BottleneckCSP, [1024, False]], # 23
[[], 1, Detect, [nc, anchors]], # Detect(P5, P4, P3)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
models/yolov5m.yaml
+11 -15
View File
@@ -5,9 +5,9 @@ width_multiple: 0.75 # layer channel multiple
# anchors
anchors:
- [116,90, 156,198, 373,326] # P5/32
- [30,61, 62,45, 59,119] # P4/16
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
@@ -19,15 +19,14 @@ backbone:
[-1, 9, BottleneckCSP, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, BottleneckCSP, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, BottleneckCSP, [1024, False]], # 9
]
# YOLOv5 head
head:
[[-1, 3, BottleneckCSP, [1024, False]], # 9
[-1, 1, Conv, [512, 1, 1]],
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, BottleneckCSP, [512, False]], # 13
@@ -35,18 +34,15 @@ head:
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, BottleneckCSP, [256, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 18 (P3/8-small)
[-1, 3, BottleneckCSP, [256, False]], # 17
[-2, 1, Conv, [256, 3, 2]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, BottleneckCSP, [512, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 22 (P4/16-medium)
[-1, 3, BottleneckCSP, [512, False]], # 20
[-2, 1, Conv, [512, 3, 2]],
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, BottleneckCSP, [1024, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 26 (P5/32-large)
[-1, 3, BottleneckCSP, [1024, False]], # 23
[[], 1, Detect, [nc, anchors]], # Detect(P5, P4, P3)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
models/yolov5s.yaml
+11 -15
View File
@@ -5,9 +5,9 @@ width_multiple: 0.50 # layer channel multiple
# anchors
anchors:
- [116,90, 156,198, 373,326] # P5/32
- [30,61, 62,45, 59,119] # P4/16
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
@@ -19,15 +19,14 @@ backbone:
[-1, 9, BottleneckCSP, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, BottleneckCSP, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, BottleneckCSP, [1024, False]], # 9
]
# YOLOv5 head
head:
[[-1, 3, BottleneckCSP, [1024, False]], # 9
[-1, 1, Conv, [512, 1, 1]],
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, BottleneckCSP, [512, False]], # 13
@@ -35,18 +34,15 @@ head:
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, BottleneckCSP, [256, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 18 (P3/8-small)
[-1, 3, BottleneckCSP, [256, False]], # 17
[-2, 1, Conv, [256, 3, 2]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, BottleneckCSP, [512, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 22 (P4/16-medium)
[-1, 3, BottleneckCSP, [512, False]], # 20
[-2, 1, Conv, [512, 3, 2]],
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, BottleneckCSP, [1024, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 26 (P5/32-large)
[-1, 3, BottleneckCSP, [1024, False]], # 23
[[], 1, Detect, [nc, anchors]], # Detect(P5, P4, P3)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
models/yolov5x.yaml
+11 -15
View File
@@ -5,9 +5,9 @@ width_multiple: 1.25 # layer channel multiple
# anchors
anchors:
- [116,90, 156,198, 373,326] # P5/32
- [30,61, 62,45, 59,119] # P4/16
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
@@ -19,15 +19,14 @@ backbone:
[-1, 9, BottleneckCSP, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, BottleneckCSP, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, BottleneckCSP, [1024, False]], # 9
]
# YOLOv5 head
head:
[[-1, 3, BottleneckCSP, [1024, False]], # 9
[-1, 1, Conv, [512, 1, 1]],
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, BottleneckCSP, [512, False]], # 13
@@ -35,18 +34,15 @@ head:
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, BottleneckCSP, [256, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 18 (P3/8-small)
[-1, 3, BottleneckCSP, [256, False]], # 17
[-2, 1, Conv, [256, 3, 2]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, BottleneckCSP, [512, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 22 (P4/16-medium)
[-1, 3, BottleneckCSP, [512, False]], # 20
[-2, 1, Conv, [512, 3, 2]],
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, BottleneckCSP, [1024, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 26 (P5/32-large)
[-1, 3, BottleneckCSP, [1024, False]], # 23
[[], 1, Detect, [nc, anchors]], # Detect(P5, P4, P3)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]