YOLOv5 v4.0 Release (#1837)
* Update C3 module * Update C3 module * Update C3 module * Update C3 module * update * update * update * update * update * update * update * update * update * updates * updates * updates * updates * updates * updates * updates * updates * updates * updates * update * update * update * update * updates * updates * updates * updates * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update datasets * update * update * update * update attempt_downlaod() * merge * merge * update * update * update * update * update * update * update * update * update * update * parameterize eps * comments * gs-multiple * update * max_nms implemented * Create one_cycle() function * update * update * update * update * update * update * update * update study.png * update study.png * Update datasets.py
This commit is contained in:
Glenn Jocher authored and GitHub committed
1 parent
0e341c5660
commit
69be8e738f
23 files changed
+489
-125
No files matched your search
+32
-9
@@ -30,7 +30,7 @@ class Conv(nn.Module):
|
||||
super(Conv, self).__init__()
|
||||
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
|
||||
self.bn = nn.BatchNorm2d(c2)
|
||||
self.act = nn.Hardswish() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
|
||||
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
|
||||
|
||||
def forward(self, x):
|
||||
return self.act(self.bn(self.conv(x)))
|
||||
@@ -105,9 +105,39 @@ class Focus(nn.Module):
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super(Focus, self).__init__()
|
||||
self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
|
||||
# self.contract = Contract(gain=2)
|
||||
|
||||
def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2)
|
||||
return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
|
||||
# return self.conv(self.contract(x))
|
||||
|
||||
|
||||
class Contract(nn.Module):
|
||||
# Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
|
||||
def __init__(self, gain=2):
|
||||
super().__init__()
|
||||
self.gain = gain
|
||||
|
||||
def forward(self, x):
|
||||
N, C, H, W = x.size() # assert (H / s == 0) and (W / s == 0), 'Indivisible gain'
|
||||
s = self.gain
|
||||
x = x.view(N, C, H // s, s, W // s, s) # x(1,64,40,2,40,2)
|
||||
x = x.permute(0, 3, 5, 1, 2, 4).contiguous() # x(1,2,2,64,40,40)
|
||||
return x.view(N, C * s * s, H // s, W // s) # x(1,256,40,40)
|
||||
|
||||
|
||||
class Expand(nn.Module):
|
||||
# Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
|
||||
def __init__(self, gain=2):
|
||||
super().__init__()
|
||||
self.gain = gain
|
||||
|
||||
def forward(self, x):
|
||||
N, C, H, W = x.size() # assert C / s ** 2 == 0, 'Indivisible gain'
|
||||
s = self.gain
|
||||
x = x.view(N, s, s, C // s ** 2, H, W) # x(1,2,2,16,80,80)
|
||||
x = x.permute(0, 3, 4, 1, 5, 2).contiguous() # x(1,16,80,2,80,2)
|
||||
return x.view(N, C // s ** 2, H * s, W * s) # x(1,16,160,160)
|
||||
|
||||
|
||||
class Concat(nn.Module):
|
||||
@@ -253,20 +283,13 @@ class Detections:
|
||||
return x
|
||||
|
||||
|
||||
class Flatten(nn.Module):
|
||||
# Use after nn.AdaptiveAvgPool2d(1) to remove last 2 dimensions
|
||||
@staticmethod
|
||||
def forward(x):
|
||||
return x.view(x.size(0), -1)
|
||||
|
||||
|
||||
class Classify(nn.Module):
|
||||
# Classification head, i.e. x(b,c1,20,20) to x(b,c2)
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super(Classify, self).__init__()
|
||||
self.aap = nn.AdaptiveAvgPool2d(1) # to x(b,c1,1,1)
|
||||
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g) # to x(b,c2,1,1)
|
||||
self.flat = Flatten()
|
||||
self.flat = nn.Flatten()
|
||||
|
||||
def forward(self, x):
|
||||
z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1) # cat if list
|
||||
|
||||
@@ -105,8 +105,8 @@ class Ensemble(nn.ModuleList):
|
||||
for module in self:
|
||||
y.append(module(x, augment)[0])
|
||||
# y = torch.stack(y).max(0)[0] # max ensemble
|
||||
# y = torch.cat(y, 1) # nms ensemble
|
||||
y = torch.stack(y).mean(0) # mean ensemble
|
||||
# y = torch.stack(y).mean(0) # mean ensemble
|
||||
y = torch.cat(y, 1) # nms ensemble
|
||||
return y, None # inference, train output
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,58 @@
|
||||
# Default YOLOv5 anchors for COCO data
|
||||
|
||||
|
||||
# P5 -------------------------------------------------------------------------------------------------------------------
|
||||
# P5-640:
|
||||
anchors_p5_640:
|
||||
- [ 10,13, 16,30, 33,23 ] # P3/8
|
||||
- [ 30,61, 62,45, 59,119 ] # P4/16
|
||||
- [ 116,90, 156,198, 373,326 ] # P5/32
|
||||
|
||||
|
||||
# P6 -------------------------------------------------------------------------------------------------------------------
|
||||
# P6-640: thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11, 21,19, 17,41, 43,32, 39,70, 86,64, 65,131, 134,130, 120,265, 282,180, 247,354, 512,387
|
||||
anchors_p6_640:
|
||||
- [ 9,11, 21,19, 17,41 ] # P3/8
|
||||
- [ 43,32, 39,70, 86,64 ] # P4/16
|
||||
- [ 65,131, 134,130, 120,265 ] # P5/32
|
||||
- [ 282,180, 247,354, 512,387 ] # P6/64
|
||||
|
||||
# P6-1280: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792
|
||||
anchors_p6_1280:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# P6-1920: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41, 67,59, 57,141, 144,103, 129,227, 270,205, 209,452, 455,396, 358,812, 653,922, 1109,570, 1387,1187
|
||||
anchors_p6_1920:
|
||||
- [ 28,41, 67,59, 57,141 ] # P3/8
|
||||
- [ 144,103, 129,227, 270,205 ] # P4/16
|
||||
- [ 209,452, 455,396, 358,812 ] # P5/32
|
||||
- [ 653,922, 1109,570, 1387,1187 ] # P6/64
|
||||
|
||||
|
||||
# P7 -------------------------------------------------------------------------------------------------------------------
|
||||
# P7-640: thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11, 13,30, 29,20, 30,46, 61,38, 39,92, 78,80, 146,66, 79,163, 149,150, 321,143, 157,303, 257,402, 359,290, 524,372
|
||||
anchors_p7_640:
|
||||
- [ 11,11, 13,30, 29,20 ] # P3/8
|
||||
- [ 30,46, 61,38, 39,92 ] # P4/16
|
||||
- [ 78,80, 146,66, 79,163 ] # P5/32
|
||||
- [ 149,150, 321,143, 157,303 ] # P6/64
|
||||
- [ 257,402, 359,290, 524,372 ] # P7/128
|
||||
|
||||
# P7-1280: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22, 54,36, 32,77, 70,83, 138,71, 75,173, 165,159, 148,334, 375,151, 334,317, 251,626, 499,474, 750,326, 534,814, 1079,818
|
||||
anchors_p7_1280:
|
||||
- [ 19,22, 54,36, 32,77 ] # P3/8
|
||||
- [ 70,83, 138,71, 75,173 ] # P4/16
|
||||
- [ 165,159, 148,334, 375,151 ] # P5/32
|
||||
- [ 334,317, 251,626, 499,474 ] # P6/64
|
||||
- [ 750,326, 534,814, 1079,818 ] # P7/128
|
||||
|
||||
# P7-1920: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34, 81,55, 47,115, 105,124, 207,107, 113,259, 247,238, 222,500, 563,227, 501,476, 376,939, 749,711, 1126,489, 801,1222, 1618,1227
|
||||
anchors_p7_1920:
|
||||
- [ 29,34, 81,55, 47,115 ] # P3/8
|
||||
- [ 105,124, 207,107, 113,259 ] # P4/16
|
||||
- [ 247,238, 222,500, 563,227 ] # P5/32
|
||||
- [ 501,476, 376,939, 749,711 ] # P6/64
|
||||
- [ 1126,489, 801,1222, 1618,1227 ] # P7/128
|
||||
@@ -0,0 +1,54 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
|
||||
[ -1, 3, C3, [ 128 ] ],
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
|
||||
[ -1, 9, C3, [ 256 ] ],
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
|
||||
[ -1, 9, C3, [ 512 ] ],
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 7-P5/32
|
||||
[ -1, 1, SPP, [ 1024, [ 5, 9, 13 ] ] ],
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[ [ -1, 1, Conv, [ 512, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 13
|
||||
|
||||
[ -1, 1, Conv, [ 256, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 17 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 128, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 2 ], 1, Concat, [ 1 ] ], # cat backbone P2
|
||||
[ -1, 1, C3, [ 128, False ] ], # 21 (P2/4-xsmall)
|
||||
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ],
|
||||
[ [ -1, 18 ], 1, Concat, [ 1 ] ], # cat head P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 24 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ],
|
||||
[ [ -1, 14 ], 1, Concat, [ 1 ] ], # cat head P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 27 (P4/16-medium)
|
||||
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ],
|
||||
[ [ -1, 10 ], 1, Concat, [ 1 ] ], # cat head P5
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 30 (P5/32-large)
|
||||
|
||||
[ [ 24, 27, 30 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5)
|
||||
]
|
||||
@@ -0,0 +1,56 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
|
||||
[ -1, 3, C3, [ 128 ] ],
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
|
||||
[ -1, 9, C3, [ 256 ] ],
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
|
||||
[ -1, 9, C3, [ 512 ] ],
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
|
||||
[ -1, 3, C3, [ 768 ] ],
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
|
||||
[ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[ [ -1, 1, Conv, [ 768, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 15
|
||||
|
||||
[ -1, 1, Conv, [ 512, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 19
|
||||
|
||||
[ -1, 1, Conv, [ 256, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 23 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ],
|
||||
[ [ -1, 20 ], 1, Concat, [ 1 ] ], # cat head P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 26 (P4/16-medium)
|
||||
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ],
|
||||
[ [ -1, 16 ], 1, Concat, [ 1 ] ], # cat head P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 29 (P5/32-large)
|
||||
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ],
|
||||
[ [ -1, 12 ], 1, Concat, [ 1 ] ], # cat head P6
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 32 (P5/64-xlarge)
|
||||
|
||||
[ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@@ -0,0 +1,67 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
|
||||
[ -1, 3, C3, [ 128 ] ],
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
|
||||
[ -1, 9, C3, [ 256 ] ],
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
|
||||
[ -1, 9, C3, [ 512 ] ],
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
|
||||
[ -1, 3, C3, [ 768 ] ],
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
|
||||
[ -1, 3, C3, [ 1024 ] ],
|
||||
[ -1, 1, Conv, [ 1280, 3, 2 ] ], # 11-P7/128
|
||||
[ -1, 1, SPP, [ 1280, [ 3, 5 ] ] ],
|
||||
[ -1, 3, C3, [ 1280, False ] ], # 13
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[ [ -1, 1, Conv, [ 1024, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 10 ], 1, Concat, [ 1 ] ], # cat backbone P6
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 17
|
||||
|
||||
[ -1, 1, Conv, [ 768, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 21
|
||||
|
||||
[ -1, 1, Conv, [ 512, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 25
|
||||
|
||||
[ -1, 1, Conv, [ 256, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 29 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ],
|
||||
[ [ -1, 26 ], 1, Concat, [ 1 ] ], # cat head P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 32 (P4/16-medium)
|
||||
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ],
|
||||
[ [ -1, 22 ], 1, Concat, [ 1 ] ], # cat head P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 35 (P5/32-large)
|
||||
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ],
|
||||
[ [ -1, 18 ], 1, Concat, [ 1 ] ], # cat head P6
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 38 (P6/64-xlarge)
|
||||
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ],
|
||||
[ [ -1, 14 ], 1, Concat, [ 1 ] ], # cat head P7
|
||||
[ -1, 3, C3, [ 1280, False ] ], # 41 (P7/128-xxlarge)
|
||||
|
||||
[ [ 29, 32, 35, 38, 41 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6, P7)
|
||||
]
|
||||
+9
-9
@@ -1,17 +1,13 @@
|
||||
import argparse
|
||||
import logging
|
||||
import math
|
||||
import sys
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
sys.path.append('./') # to run '$ python *.py' files in subdirectories
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
from models.common import Conv, Bottleneck, SPP, DWConv, Focus, BottleneckCSP, C3, Concat, NMS, autoShape
|
||||
from models.common import *
|
||||
from models.experimental import MixConv2d, CrossConv
|
||||
from utils.autoanchor import check_anchor_order
|
||||
from utils.general import make_divisible, check_file, set_logging
|
||||
@@ -89,7 +85,7 @@ class Model(nn.Module):
|
||||
# Build strides, anchors
|
||||
m = self.model[-1] # Detect()
|
||||
if isinstance(m, Detect):
|
||||
s = 128 # 2x min stride
|
||||
s = 256 # 2x min stride
|
||||
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
|
||||
m.anchors /= m.stride.view(-1, 1, 1)
|
||||
check_anchor_order(m)
|
||||
@@ -109,7 +105,7 @@ class Model(nn.Module):
|
||||
f = [None, 3, None] # flips (2-ud, 3-lr)
|
||||
y = [] # outputs
|
||||
for si, fi in zip(s, f):
|
||||
xi = scale_img(x.flip(fi) if fi else x, si)
|
||||
xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
|
||||
yi = self.forward_once(xi)[0] # forward
|
||||
# cv2.imwrite('img%g.jpg' % s, 255 * xi[0].numpy().transpose((1, 2, 0))[:, :, ::-1]) # save
|
||||
yi[..., :4] /= si # de-scale
|
||||
@@ -242,13 +238,17 @@ def parse_model(d, ch): # model_dict, input_channels(3)
|
||||
elif m is nn.BatchNorm2d:
|
||||
args = [ch[f]]
|
||||
elif m is Concat:
|
||||
c2 = sum([ch[-1 if x == -1 else x + 1] for x in f])
|
||||
c2 = sum([ch[x if x < 0 else x + 1] for x in f])
|
||||
elif m is Detect:
|
||||
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)
|
||||
elif m is Contract:
|
||||
c2 = ch[f if f < 0 else f + 1] * args[0] ** 2
|
||||
elif m is Expand:
|
||||
c2 = ch[f if f < 0 else f + 1] // args[0] ** 2
|
||||
else:
|
||||
c2 = ch[f]
|
||||
c2 = ch[f if f < 0 else f + 1]
|
||||
|
||||
m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args) # module
|
||||
t = str(m)[8:-2].replace('__main__.', '') # module type
|
||||
|
||||
+8
-8
@@ -14,14 +14,14 @@ backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, BottleneckCSP, [128]],
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, BottleneckCSP, [256]],
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, BottleneckCSP, [512]],
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 9
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
@@ -29,20 +29,20 @@ head:
|
||||
[[-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
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-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]], # 17 (P3/8-small)
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 20 (P4/16-medium)
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 23 (P5/32-large)
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
+8
-8
@@ -14,14 +14,14 @@ backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, BottleneckCSP, [128]],
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, BottleneckCSP, [256]],
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, BottleneckCSP, [512]],
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 9
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
@@ -29,20 +29,20 @@ head:
|
||||
[[-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
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-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]], # 17 (P3/8-small)
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 20 (P4/16-medium)
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 23 (P5/32-large)
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
+8
-8
@@ -14,14 +14,14 @@ backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, BottleneckCSP, [128]],
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, BottleneckCSP, [256]],
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, BottleneckCSP, [512]],
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 9
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
@@ -29,20 +29,20 @@ head:
|
||||
[[-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
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-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]], # 17 (P3/8-small)
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 20 (P4/16-medium)
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 23 (P5/32-large)
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
+8
-8
@@ -14,14 +14,14 @@ backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, BottleneckCSP, [128]],
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, BottleneckCSP, [256]],
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, BottleneckCSP, [512]],
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 9
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
@@ -29,20 +29,20 @@ head:
|
||||
[[-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
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-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]], # 17 (P3/8-small)
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 20 (P4/16-medium)
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 23 (P5/32-large)
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
Reference in new issue
Block a user