xsl
443cfa298f
包含： - hair_service_sd: 主服务（换发型/换发色/生发，端口8801） - photo_service: LoRA调度+训练（端口32678） - hair_grow_service: 调试测试页（端口8888，含4个测试页） - 批量训练脚本（batch_train_hairstyles.py） - 发际线mask自动识别（hairline_mask.py，4种方案） - 手绘mask换发型（hair_swap_manual.py） - 文档：README.md + LARGE_FILES.md + docs/ 大文件（模型权重200G、训练数据123G）已排除，见 LARGE_FILES.md OSS/COS密钥已脱敏为环境变量，原文件备份在本地
234 lines
10 KiB
Python
234 lines
10 KiB
Python
import argparse
|
||
|
||
from models.experimental 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):
|
||
# x = x.copy() # for profiling
|
||
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_cfg='yolov5s.yaml', ch=3, nc=None): # model, input channels, number of classes
|
||
super(Model, self).__init__()
|
||
if type(model_cfg) is dict:
|
||
self.md = model_cfg # model dict
|
||
else: # is *.yaml
|
||
with open(model_cfg) as f:
|
||
self.md = yaml.load(f, Loader=yaml.FullLoader) # model dict
|
||
|
||
# Define model
|
||
if nc:
|
||
self.md['nc'] = nc # override yaml value
|
||
self.model, self.save = parse_model(self.md, ch=[ch]) # model, savelist, ch_out
|
||
# print([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
|
||
|
||
# Build strides, anchors
|
||
m = self.model[-1] # Detect()
|
||
m.stride = torch.tensor([128 / x.shape[-2] for x in self.forward(torch.zeros(1, ch, 128, 128))]) # forward
|
||
m.anchors /= m.stride.view(-1, 1, 1)
|
||
check_anchor_order(m)
|
||
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):
|
||
if augment:
|
||
img_size = x.shape[-2:] # height, width
|
||
s = [0.83, 0.67] # scales
|
||
y = []
|
||
for i, xi in enumerate((x,
|
||
torch_utils.scale_img(x.flip(3), s[0]), # flip-lr and scale
|
||
torch_utils.scale_img(x, s[1]), # scale
|
||
)):
|
||
# cv2.imwrite('img%g.jpg' % i, 255 * xi[0].numpy().transpose((1, 2, 0))[:, :, ::-1])
|
||
y.append(self.forward_once(xi)[0])
|
||
|
||
y[1][..., :4] /= s[0] # scale
|
||
y[1][..., 0] = img_size[1] - y[1][..., 0] # flip lr
|
||
y[2][..., :4] /= s[1] # scale
|
||
return torch.cat(y, 1), None # augmented inference, train
|
||
else:
|
||
return self.forward_once(x, profile) # single-scale inference, train
|
||
|
||
def forward_once(self, x, profile=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:
|
||
try:
|
||
import thop
|
||
o = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 # FLOPS
|
||
except:
|
||
o = 0
|
||
t = torch_utils.time_synchronized()
|
||
for _ in range(10):
|
||
_ = m(x)
|
||
dt.append((torch_utils.time_synchronized() - t) * 100)
|
||
print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))
|
||
|
||
x = m(x) # run
|
||
y.append(x if m.i in self.save else None) # save output
|
||
|
||
if profile:
|
||
print('%.1fms total' % sum(dt))
|
||
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 _print_weights(self):
|
||
# for m in self.model.modules():
|
||
# if type(m) is Bottleneck:
|
||
# print('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
|
||
|
||
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
|
||
print('Fusing layers...')
|
||
for m in self.model.modules():
|
||
if type(m) is Conv:
|
||
m.conv = torch_utils.fuse_conv_and_bn(m.conv, m.bn) # update conv
|
||
m.bn = None # remove batchnorm
|
||
m.forward = m.fuseforward # update forward
|
||
torch_utils.model_info(self)
|
||
|
||
|
||
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]:
|
||
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[-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]))
|
||
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)
|
||
|
||
|
||
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 = check_file(opt.cfg) # check 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)
|
||
|
||
# ONNX export
|
||
# model.model[-1].export = True
|
||
# torch.onnx.export(model, img, opt.cfg.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
|