|
|
import argparse
|
|
|
|
|
|
import yaml
|
|
|
|
|
|
from models.common import *
|
|
|
|
|
|
|
|
|
class Detect(nn.Module):
|
|
|
def __init__(self, nc=80, anchors=()): # detection layer
|
|
|
super(Detect, self).__init__()
|
|
|
self.stride = None # strides computed during build
|
|
|
self.nc = nc # number of classes
|
|
|
self.no = nc + 5 # number of outputs per anchor
|
|
|
self.nl = len(anchors) # number of detection layers
|
|
|
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)
|
|
|
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.export = False # onnx export
|
|
|
|
|
|
def forward(self, x):
|
|
|
z = [] # inference output
|
|
|
self.training |= self.export
|
|
|
for i in range(self.nl):
|
|
|
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()
|
|
|
|
|
|
if not self.training: # inference
|
|
|
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
|
|
|
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
|
|
|
|
|
|
y = x[i].sigmoid()
|
|
|
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i].to(x[i].device)) * self.stride[i] # xy
|
|
|
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
|
|
z.append(y.view(bs, -1, self.no))
|
|
|
|
|
|
return x if self.training else (torch.cat(z, 1), x)
|
|
|
|
|
|
@staticmethod
|
|
|
def _make_grid(nx=20, ny=20):
|
|
|
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
|
|
|
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
|
|
|
|
|
|
|
|
|
class Model(nn.Module):
|
|
|
def __init__(self, model_yaml='yolov5s.yaml'): # cfg, number of classes, depth-width gains
|
|
|
super(Model, self).__init__()
|
|
|
with open(model_yaml) as f:
|
|
|
self.md = yaml.load(f, Loader=yaml.FullLoader) # model dict
|
|
|
|
|
|
# Define model
|
|
|
self.model, self.save, ch = parse_model(self.md, ch=[3]) # model, savelist, ch_out
|
|
|
# print([x.shape for x in self.forward(torch.zeros(1, 3, 64, 64))])
|
|
|
|
|
|
# Build strides, anchors
|
|
|
m = self.model[-1] # Detect()
|
|
|
m.stride = torch.tensor([64 / x.shape[-2] for x in self.forward(torch.zeros(1, 3, 64, 64))]) # forward
|
|
|
m.anchors /= m.stride.view(-1, 1, 1)
|
|
|
self.stride = m.stride
|
|
|
|
|
|
# Init weights, biases
|
|
|
torch_utils.initialize_weights(self)
|
|
|
self._initialize_biases() # only run once
|
|
|
torch_utils.model_info(self)
|
|
|
print('')
|
|
|
|
|
|
def forward(self, x, augment=False, profile=False):
|
|
|
y, ts = [], 0 # 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:
|
|
|
import thop
|
|
|
o = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 # FLOPS
|
|
|
t = torch_utils.time_synchronized()
|
|
|
for _ in range(10):
|
|
|
_ = m(x)
|
|
|
dt = torch_utils.time_synchronized() - t
|
|
|
ts += dt
|
|
|
print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt * 100, m.type))
|
|
|
|
|
|
x = m(x) # run
|
|
|
y.append(x if m.i in self.save else None) # save output
|
|
|
|
|
|
if profile:
|
|
|
print(ts * 100)
|
|
|
return x
|
|
|
|
|
|
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]
|
|
|
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
|
|
|
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
|
|
|
|
|
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()))
|
|
|
|
|
|
|
|
|
def parse_model(md, ch): # model_dict, input_channels(3)
|
|
|
print('\n%3s%15s%3s%10s %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
|
|
|
anchors, nc, gd, gw = md['anchors'], md['nc'], md['depth_multiple'], md['width_multiple']
|
|
|
na = (len(anchors[0]) // 2) # 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(md['backbone'] + md['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 = max(round(n * gd), 1) if n > 1 else n # depth gain
|
|
|
if m in [nn.Conv2d, Conv, Bottleneck, SPP, DWConv, MixConv2d, Focus, ConvPlus, BottleneckCSP, BottleneckLight]:
|
|
|
c1, c2 = ch[f], args[0]
|
|
|
|
|
|
# Normal
|
|
|
# if i > 0 and args[0] != no: # channel expansion factor
|
|
|
# ex = 1.75 # exponential (default 2.0)
|
|
|
# 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
|
|
|
# if i > 0 and args[0] != no: # channel expansion factor
|
|
|
# ex = 1 + gw # exponential (default 2.0)
|
|
|
# ch1 = 32 # ch[1]
|
|
|
# e = math.log(c2 / ch1) / math.log(2) # level 1-n
|
|
|
# c2 = int(ch1 * ex ** e)
|
|
|
# if m != Focus:
|
|
|
# c2 = make_divisible(c2, 8) if c2 != no else c2
|
|
|
|
|
|
args = [c1, c2, *args[1:]]
|
|
|
if m is BottleneckCSP:
|
|
|
args.insert(2, n)
|
|
|
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 Origami:
|
|
|
c2 = ch[f] * 5
|
|
|
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]))
|
|
|
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
|
|
|
print('%3s%15s%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_)
|
|
|
ch.append(c2)
|
|
|
return nn.Sequential(*layers), sorted(save), ch
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
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')
|
|
|
opt = parser.parse_args()
|
|
|
opt.cfg = glob.glob('./**/' + opt.cfg, recursive=True)[0] # find file
|
|
|
device = torch_utils.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, 640, 640).to(device)
|
|
|
# y = model(img, profile=True)
|
|
|
# print([y[0].shape] + [x.shape for x in y[1]])
|
|
|
|
|
|
# ONNX export
|
|
|
# model.model[-1].export = True
|
|
|
# torch.onnx.export(model, img, f.replace('.yaml', '.onnx'), verbose=True, opset_version=11)
|
|
|
|
|
|
# Tensorboard
|
|
|
# from torch.utils.tensorboard import SummaryWriter
|
|
|
# tb_writer = SummaryWriter()
|
|
|
# print("Run 'tensorboard --logdir=models/runs' to view tensorboard at http://localhost:6006/")
|
|
|
# tb_writer.add_graph(model.model, img) # add model to tensorboard
|
|
|
# tb_writer.add_image('test', img[0], dataformats='CWH') # add model to tensorboard
|
