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