301 lines
14 KiB
Python
301 lines
14 KiB
Python
"""YOLOv5-specific modules
|
||
|
||
Usage:
|
||
$ python path/to/models/yolo.py --cfg yolov5s.yaml
|
||
"""
|
||
|
||
import argparse
|
||
import sys
|
||
from copy import deepcopy
|
||
from pathlib import Path
|
||
|
||
FILE = Path(__file__).absolute()
|
||
sys.path.append(FILE.parents[1].as_posix()) # add yolov5/ to path
|
||
|
||
from models.common import *
|
||
from models.experimental import *
|
||
from utils.autoanchor import check_anchor_order
|
||
from utils.general import make_divisible, check_file, set_logging
|
||
from utils.plots import feature_visualization
|
||
from utils.torch_utils import time_sync, fuse_conv_and_bn, model_info, scale_img, initialize_weights, \
|
||
select_device, copy_attr
|
||
|
||
try:
|
||
import thop # for FLOPs computation
|
||
except ImportError:
|
||
thop = None
|
||
|
||
LOGGER = logging.getLogger(__name__)
|
||
|
||
|
||
class Detect(nn.Module):#对特征图进行检测的类
|
||
stride = None # strides computed during build
|
||
onnx_dynamic = False # ONNX export parameter
|
||
|
||
def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer
|
||
#ch()相应于每个特征图上卷积核的通道数
|
||
super().__init__()
|
||
self.nc = nc # number of classes
|
||
self.no = nc + 5 # number of outputs per anchor 每个anchor输出值的个数20个类别+4个坐标信息+得分
|
||
self.nl = len(anchors) # number of detection layers 做检测的特征图，相应的层数是4？？
|
||
self.na = len(anchors[0]) // 2 # number of anchors
|
||
self.grid = [torch.zeros(1)] * self.nl # init grid
|
||
a = torch.tensor(anchors).float().view(self.nl, -1, 2) #对变量a进行赋值
|
||
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 输入通道是x，输出通道是self.no * self.na
|
||
#1x1卷积是将特征图通过此卷积运算得到我们预测后的值，包括预测框的坐标信息，目标性得分，分类概率。这里ch是得到通道的取值，分别为[192,192,384,768]??
|
||
self.inplace = inplace # use in-place ops (e.g. slice assignment)
|
||
|
||
def forward(self, x):
|
||
# x = x.copy() # for profiling
|
||
z = [] # inference output
|
||
for i in range(self.nl):#对nl进行迭代，即每个先验框进行迭代，
|
||
x[i] = self.m[i](x[i]) # conv 在detect层做卷积运算
|
||
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() #用permute调整前面的顺序，再用contiguout变成内存连续变量
|
||
|
||
if not self.training: # inference判断是否在做训练，不在做训练则是在做inference即推理
|
||
if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
|
||
self.grid[i] = self._make_grid(nx, ny).to(x[i].device) #调用make_grid函数调用网格
|
||
|
||
y = x[i].sigmoid() #调用sigmoid函数，求出预测框坐标信息，包括xy坐标信息以及wh坐标信息
|
||
if self.inplace:
|
||
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||
else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
|
||
xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].view(1, self.na, 1, 1, 2) # wh
|
||
y = torch.cat((xy, wh, y[..., 4:]), -1)
|
||
z.append(y.view(bs, -1, self.no))#预测框信息
|
||
|
||
return x if self.training else (torch.cat(z, 1), x) #如果是训练，则返回x即可。如果推理，返回预测框坐标，obj（目标性得分），cls（概率信息，这里是x）
|
||
|
||
@staticmethod
|
||
def _make_grid(nx=20, ny=20):#图像上划分网格，如果是640x640，则刚好32倍后是20x20
|
||
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
|
||
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
|
||
|
||
|
||
#网络模型类 如何解析项目文件来构建网络结构
|
||
class Model(nn.Module):
|
||
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 #通过路径，将文件名取出，字符串型
|
||
with open(cfg,'r',encoding='utf-8') as f:
|
||
self.yaml = yaml.safe_load(f) # model dict #yaml变成字典
|
||
|
||
# Define model
|
||
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
|
||
if anchors:
|
||
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 通过parse_model来解析构建model
|
||
self.names = [str(i) for i in range(self.yaml['nc'])] # default names
|
||
self.inplace = self.yaml.get('inplace', True)
|
||
# LOGGER.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
|
||
|
||
# Build strides, anchors
|
||
m = self.model[-1] # Detect()
|
||
if isinstance(m, Detect):
|
||
s = 256 # 2x min stride
|
||
m.inplace = self.inplace
|
||
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)
|
||
self.stride = m.stride
|
||
self._initialize_biases() # only run once
|
||
# LOGGER.info('Strides: %s' % m.stride.tolist())
|
||
|
||
# Init weights, biases
|
||
initialize_weights(self)
|
||
self.info()
|
||
LOGGER.info('')
|
||
|
||
def forward(self, x, augment=False, profile=False, visualize=False):
|
||
if augment:
|
||
return self.forward_augment(x) # augmented inference, None
|
||
return self.forward_once(x, profile, visualize) # single-scale inference, train
|
||
|
||
def forward_augment(self, x):
|
||
img_size = x.shape[-2:] # height, width
|
||
s = [1, 0.83, 0.67] # scales
|
||
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, gs=int(self.stride.max()))
|
||
yi = self.forward_once(xi)[0] # forward
|
||
# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save
|
||
yi = self._descale_pred(yi, fi, si, img_size)
|
||
y.append(yi)
|
||
return torch.cat(y, 1), None # augmented inference, train
|
||
|
||
def forward_once(self, x, profile=False, visualize=False):
|
||
y, dt = [], [] # outputs
|
||
for m in self.model:
|
||
if m.f != -1: # if not from previous layer
|
||
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
|
||
|
||
if profile:
|
||
o = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs
|
||
t = time_sync()
|
||
for _ in range(10):
|
||
_ = m(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}')
|
||
|
||
x = m(x) # run
|
||
y.append(x if m.i in self.save else None) # save output
|
||
|
||
if visualize:
|
||
feature_visualization(x, m.type, m.i, save_dir=visualize)
|
||
|
||
if profile:
|
||
LOGGER.info('%.1fms total' % sum(dt))
|
||
return x
|
||
|
||
def _descale_pred(self, p, flips, scale, img_size):
|
||
# de-scale predictions following augmented inference (inverse operation)
|
||
if self.inplace:
|
||
p[..., :4] /= scale # de-scale
|
||
if flips == 2:
|
||
p[..., 1] = img_size[0] - p[..., 1] # de-flip ud
|
||
elif flips == 3:
|
||
p[..., 0] = img_size[1] - p[..., 0] # de-flip lr
|
||
else:
|
||
x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scale
|
||
if flips == 2:
|
||
y = img_size[0] - y # de-flip ud
|
||
elif flips == 3:
|
||
x = img_size[1] - x # de-flip lr
|
||
p = torch.cat((x, y, wh, p[..., 4:]), -1)
|
||
return p
|
||
|
||
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
|
||
# https://arxiv.org/abs/1708.02002 section 3.3
|
||
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
|
||
m = self.model[-1] # Detect() module
|
||
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:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
||
|
||
def _print_biases(self):
|
||
m = self.model[-1] # Detect() module
|
||
for mi in m.m: # from
|
||
b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
|
||
LOGGER.info(
|
||
('%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():
|
||
# if type(m) is Bottleneck:
|
||
# LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
|
||
|
||
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
|
||
LOGGER.info('Fusing layers... ')
|
||
for m in self.model.modules():
|
||
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
|
||
m.forward = m.forward_fuse # update forward
|
||
self.info()
|
||
return self
|
||
|
||
def autoshape(self): # add AutoShape module
|
||
LOGGER.info('Adding AutoShape... ')
|
||
m = AutoShape(self) # wrap model
|
||
copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=()) # copy attributes
|
||
return m
|
||
|
||
def info(self, verbose=False, img_size=640): # print model information
|
||
model_info(self, verbose, img_size)
|
||
|
||
|
||
def parse_model(d, ch): # model_dict, input_channels(3)
|
||
LOGGER.info('\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) 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
|
||
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):
|
||
try:
|
||
args[j] = eval(a) if isinstance(a, str) else a # eval strings
|
||
except:
|
||
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]:
|
||
c1, c2 = ch[f], args[0]
|
||
if c2 != no: # if not output
|
||
c2 = make_divisible(c2 * gw, 8)
|
||
|
||
args = [c1, c2, *args[1:]]
|
||
if m in [BottleneckCSP, C3, C3TR]:
|
||
args.insert(2, n) # number of repeats
|
||
n = 1
|
||
elif m is nn.BatchNorm2d:
|
||
args = [ch[f]]
|
||
elif m is Concat:
|
||
c2 = sum([ch[x] for x in f])
|
||
elif m is Detect:
|
||
args.append([ch[x] 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] * args[0] ** 2
|
||
elif m is Expand:
|
||
c2 = ch[f] // args[0] ** 2
|
||
else:
|
||
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
|
||
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('%3s%18s%3s%10.0f %-40s%-30s' % (i, f, n_, np, t, args)) # 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:
|
||
ch = []
|
||
ch.append(c2)
|
||
return nn.Sequential(*layers), sorted(save)
|
||
|
||
|
||
if __name__ == '__main__':
|
||
parser = argparse.ArgumentParser()
|
||
parser.add_argument('--cfg', type=str, default='yolov5m_add_detect.yaml', help='model.yaml')
|
||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||
opt = parser.parse_args()
|
||
opt.cfg = check_file(opt.cfg) # check file
|
||
set_logging()
|
||
device = select_device(opt.device)
|
||
|
||
# Create model
|
||
model = Model(opt.cfg).to(device)
|
||
model.train()
|
||
|
||
# Profile
|
||
# img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 320, 320).to(device)
|
||
# y = model(img, profile=True)
|
||
|
||
# Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
|
||
# from torch.utils.tensorboard import SummaryWriter
|
||
# tb_writer = SummaryWriter('.')
|
||
# LOGGER.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/")
|
||
# tb_writer.add_graph(torch.jit.trace(model, img, strict=False), []) # add model graph
|