Ankle/yolov5_birdproject
1
0 Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Update Actions with Lychee and GitHub Token (#12592)

Browse Source 
* Add Ultralytics Actions

* Auto-format by Ultralytics actions

* Update format.yml

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

---------

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Paula DerrengerUltralyticsAssistantGlenn Jocher
 authored and GitHub committed 2024-01-08 01:29:14 +01:00
1 parent f56355d321
commit ad97dc6a6d
47 files changed
+4217 -3462
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

models/yolo.py
+102 -48
View File
@@ -1,6 +1,6 @@
# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
"""
YOLO-specific modules
YOLO-specific modules.
Usage:
$ python models/yolo.py --cfg yolov5s.yaml
@@ -22,18 +22,46 @@ FILE = Path(__file__).resolve()
ROOT = FILE.parents[1] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
if platform.system() != 'Windows':
if platform.system() != "Windows":
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from models.common import (C3, C3SPP, C3TR, SPP, SPPF, Bottleneck, BottleneckCSP, C3Ghost, C3x, Classify, Concat,
Contract, Conv, CrossConv, DetectMultiBackend, DWConv, DWConvTranspose2d, Expand, Focus,
GhostBottleneck, GhostConv, Proto)
from models.common import (
C3,
C3SPP,
C3TR,
SPP,
SPPF,
Bottleneck,
BottleneckCSP,
C3Ghost,
C3x,
Classify,
Concat,
Contract,
Conv,
CrossConv,
DetectMultiBackend,
DWConv,
DWConvTranspose2d,
Expand,
Focus,
GhostBottleneck,
GhostConv,
Proto,
)
from models.experimental import MixConv2d
from utils.autoanchor import check_anchor_order
from utils.general import LOGGER, check_version, check_yaml, colorstr, make_divisible, print_args
from utils.plots import feature_visualization
from utils.torch_utils import (fuse_conv_and_bn, initialize_weights, model_info, profile, scale_img, select_device,
time_sync)
from utils.torch_utils import (
fuse_conv_and_bn,
initialize_weights,
model_info,
profile,
scale_img,
select_device,
time_sync,
)
try:
import thop # for FLOPs computation
@@ -55,7 +83,7 @@ class Detect(nn.Module):
self.na = len(anchors[0]) // 2 # number of anchors
self.grid = [torch.empty(0) for _ in range(self.nl)] # init grid
self.anchor_grid = [torch.empty(0) for _ in range(self.nl)] # init anchor grid
self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)
self.register_buffer("anchors", torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
self.inplace = inplace # use inplace ops (e.g. slice assignment)
@@ -82,14 +110,14 @@ class Detect(nn.Module):
y = torch.cat((xy, wh, conf), 4)
z.append(y.view(bs, self.na * nx * ny, self.no))
return x if self.training else (torch.cat(z, 1), ) if self.export else (torch.cat(z, 1), x)
return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x)
def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')):
def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, "1.10.0")):
d = self.anchors[i].device
t = self.anchors[i].dtype
shape = 1, self.na, ny, nx, 2 # grid shape
y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)
yv, xv = torch.meshgrid(y, x, indexing='ij') if torch_1_10 else torch.meshgrid(y, x) # torch>=0.7 compatibility
yv, xv = torch.meshgrid(y, x, indexing="ij") if torch_1_10 else torch.meshgrid(y, x) # torch>=0.7 compatibility
grid = torch.stack((xv, yv), 2).expand(shape) - 0.5 # add grid offset, i.e. y = 2.0 * x - 0.5
anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
return grid, anchor_grid
@@ -132,23 +160,23 @@ class BaseModel(nn.Module):
def _profile_one_layer(self, m, x, dt):
c = m == self.model[-1] # is final layer, copy input as inplace fix
o = thop.profile(m, inputs=(x.copy() if c else x, ), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs
o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1e9 * 2 if thop else 0 # FLOPs
t = time_sync()
for _ in range(10):
m(x.copy() if c else x)
dt.append((time_sync() - t) * 100)
if m == self.model[0]:
LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} module")
LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}')
LOGGER.info(f"{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}")
if c:
LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total")
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
LOGGER.info('Fusing layers... ')
LOGGER.info("Fusing layers... ")
for m in self.model.modules():
if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
if isinstance(m, (Conv, DWConv)) and hasattr(m, "bn"):
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
delattr(m, 'bn') # remove batchnorm
delattr(m, "bn") # remove batchnorm
m.forward = m.forward_fuse # update forward
self.info()
return self
@@ -170,27 +198,28 @@ class BaseModel(nn.Module):
class DetectionModel(BaseModel):
# YOLOv5 detection model
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
def __init__(self, cfg="yolov5s.yaml", ch=3, nc=None, anchors=None): # model, input channels, number of classes
super().__init__()
if isinstance(cfg, dict):
self.yaml = cfg # model dict
else: # is *.yaml
import yaml # for torch hub
self.yaml_file = Path(cfg).name
with open(cfg, encoding='ascii', errors='ignore') as f:
with open(cfg, encoding="ascii", errors="ignore") as f:
self.yaml = yaml.safe_load(f) # model dict
# Define model
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
if nc and nc != self.yaml['nc']:
ch = self.yaml["ch"] = self.yaml.get("ch", ch) # input channels
if nc and nc != self.yaml["nc"]:
LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
self.yaml['nc'] = nc # override yaml value
self.yaml["nc"] = nc # override yaml value
if anchors:
LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
self.yaml['anchors'] = round(anchors) # override yaml value
LOGGER.info(f"Overriding model.yaml anchors with anchors={anchors}")
self.yaml["anchors"] = round(anchors) # override yaml value
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
self.names = [str(i) for i in range(self.yaml['nc'])] # default names
self.inplace = self.yaml.get('inplace', True)
self.names = [str(i) for i in range(self.yaml["nc"])] # default names
self.inplace = self.yaml.get("inplace", True)
# Build strides, anchors
m = self.model[-1] # Detect()
@@ -207,7 +236,7 @@ class DetectionModel(BaseModel):
# Init weights, biases
initialize_weights(self)
self.info()
LOGGER.info('')
LOGGER.info("")
def forward(self, x, augment=False, profile=False, visualize=False):
if augment:
@@ -248,9 +277,9 @@ class DetectionModel(BaseModel):
def _clip_augmented(self, y):
# Clip YOLOv5 augmented inference tails
nl = self.model[-1].nl # number of detection layers (P3-P5)
g = sum(4 ** x for x in range(nl)) # grid points
g = sum(4**x for x in range(nl)) # grid points
e = 1 # exclude layer count
i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e)) # indices
i = (y[0].shape[1] // g) * sum(4**x for x in range(e)) # indices
y[0] = y[0][:, :-i] # large
i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e)) # indices
y[-1] = y[-1][:, i:] # small
@@ -263,7 +292,9 @@ class DetectionModel(BaseModel):
for mi, s in zip(m.m, m.stride): # from
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
b.data[:, 5:5 + m.nc] += math.log(0.6 / (m.nc - 0.99999)) if cf is None else torch.log(cf / cf.sum()) # cls
b.data[:, 5 : 5 + m.nc] += (
math.log(0.6 / (m.nc - 0.99999)) if cf is None else torch.log(cf / cf.sum())
) # cls
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
@@ -272,7 +303,7 @@ Model = DetectionModel # retain YOLOv5 'Model' class for backwards compatibilit
class SegmentationModel(DetectionModel):
# YOLOv5 segmentation model
def __init__(self, cfg='yolov5s-seg.yaml', ch=3, nc=None, anchors=None):
def __init__(self, cfg="yolov5s-seg.yaml", ch=3, nc=None, anchors=None):
super().__init__(cfg, ch, nc, anchors)
@@ -288,9 +319,9 @@ class ClassificationModel(BaseModel):
model = model.model # unwrap DetectMultiBackend
model.model = model.model[:cutoff] # backbone
m = model.model[-1] # last layer
ch = m.conv.in_channels if hasattr(m, 'conv') else m.cv1.conv.in_channels # ch into module
ch = m.conv.in_channels if hasattr(m, "conv") else m.cv1.conv.in_channels # ch into module
c = Classify(ch, nc) # Classify()
c.i, c.f, c.type = m.i, m.f, 'models.common.Classify' # index, from, type
c.i, c.f, c.type = m.i, m.f, "models.common.Classify" # index, from, type
model.model[-1] = c # replace
self.model = model.model
self.stride = model.stride
@@ -305,8 +336,14 @@ class ClassificationModel(BaseModel):
def parse_model(d, ch): # model_dict, input_channels(3)
# Parse a YOLOv5 model.yaml dictionary
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
anchors, nc, gd, gw, act, ch_mul = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get(
'activation'), d.get('channel_multiple')
anchors, nc, gd, gw, act, ch_mul = (
d["anchors"],
d["nc"],
d["depth_multiple"],
d["width_multiple"],
d.get("activation"),
d.get("channel_multiple"),
)
if act:
Conv.default_act = eval(act) # redefine default activation, i.e. Conv.default_act = nn.SiLU()
LOGGER.info(f"{colorstr('activation:')} {act}") # print
@@ -316,7 +353,7 @@ def parse_model(d, ch): # model_dict, input_channels(3)
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
for i, (f, n, m, args) in enumerate(d["backbone"] + d["head"]): # from, number, module, args
m = eval(m) if isinstance(m, str) else m # eval strings
for j, a in enumerate(args):
with contextlib.suppress(NameError):
@@ -324,8 +361,25 @@ def parse_model(d, ch): # model_dict, input_channels(3)
n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain
if m in {
Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
Conv,
GhostConv,
Bottleneck,
GhostBottleneck,
SPP,
SPPF,
DWConv,
MixConv2d,
Focus,
CrossConv,
BottleneckCSP,
C3,
C3TR,
C3SPP,
C3Ghost,
nn.ConvTranspose2d,
DWConvTranspose2d,
C3x,
}:
c1, c2 = ch[f], args[0]
if c2 != no: # if not output
c2 = make_divisible(c2 * gw, ch_mul)
@@ -353,10 +407,10 @@ def parse_model(d, ch): # model_dict, input_channels(3)
c2 = ch[f]
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
t = str(m)[8:-2].replace("__main__.", "") # module type
np = sum(x.numel() for x in m_.parameters()) # number params
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f} {t:<40}{str(args):<30}') # print
LOGGER.info(f"{i:>3}{str(f):>18}{n_:>3}{np:10.0f} {t:<40}{str(args):<30}") # print
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
layers.append(m_)
if i == 0:
@@ -365,14 +419,14 @@ def parse_model(d, ch): # model_dict, input_channels(3)
return nn.Sequential(*layers), sorted(save)
if __name__ == '__main__':
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
parser.add_argument('--batch-size', type=int, default=1, help='total batch size for all GPUs')
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')
parser.add_argument('--line-profile', action='store_true', help='profile model speed layer by layer')
parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
parser.add_argument("--cfg", type=str, default="yolov5s.yaml", help="model.yaml")
parser.add_argument("--batch-size", type=int, default=1, help="total batch size for all GPUs")
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")
parser.add_argument("--line-profile", action="store_true", help="profile model speed layer by layer")
parser.add_argument("--test", action="store_true", help="test all yolo*.yaml")
opt = parser.parse_args()
opt.cfg = check_yaml(opt.cfg) # check YAML
print_args(vars(opt))
@@ -390,11 +444,11 @@ if __name__ == '__main__':
results = profile(input=im, ops=[model], n=3)
elif opt.test: # test all models
for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
for cfg in Path(ROOT / "models").rglob("yolo*.yaml"):
try:
_ = Model(cfg)
except Exception as e:
print(f'Error in {cfg}: {e}')
print(f"Error in {cfg}: {e}")
else: # report fused model summary
model.fuse()