import argparse from copy import deepcopy import torch #from experimental import * from .common import * #from .common_v3 import * from pathlib import Path import math import yaml class Detect(nn.Module): def __init__(self, nc=80, anchors=(), ch=()): # 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.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv 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): x[i] = self.m[i](x[i]) # conv # 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() x[i] = x[i].sigmoid() # return x if self.training else (torch.cat(z, 1), x) return 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, cfg='yolov5s.yaml', ch=3, nc=None): # model, input channels, number of classes super(Model, self).__init__() with open(cfg) as f: self.yaml = yaml.load(f, Loader=yaml.FullLoader) # model dict # Define model if nc and nc != self.yaml['nc']: print('Overriding %s nc=%g with nc=%g' % (cfg, self.yaml['nc'], nc)) self.yaml['nc'] = nc # override yaml value self.model, self.save = parse_model(deepcopy(self.yaml), 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() if isinstance(m, Detect): s = 128 # 2x min stride #m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward # FocusNoSliceCat m.stride = torch.tensor([8.0,16.0,32.0]) # forward m.anchors /= m.stride.view(-1, 1, 1) check_anchor_order(m) self.stride = m.stride self._initialize_biases() # only run once # print('Strides: %s' % m.stride.tolist()) # Init weights, biases initialize_weights(self) def forward(self, x, augment=False, 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 x = m(x) # run y.append(x if m.i in self.save else None) # save output 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 mi, s in zip(m.m, m.stride): #  from 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 make_divisible(x, divisor): # Returns x evenly divisble by divisor return math.ceil(x / divisor) * divisor def check_anchor_order(m): # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary a = m.anchor_grid.prod(-1).view(-1) # anchor area da = a[-1] - a[0] # delta a ds = m.stride[-1] - m.stride[0] # delta s if da.sign() != ds.sign(): # same order print('Reversing anchor order') m.anchors[:] = m.anchors.flip(0) m.anchor_grid[:] = m.anchor_grid.flip(0) def initialize_weights(model): for m in model.modules(): t = type(m) if t is nn.Conv2d: pass # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') elif t is nn.BatchNorm2d: m.eps = 1e-3 m.momentum = 0.03 elif t in [nn.LeakyReLU, nn.ReLU, nn.ReLU6]: m.inplace = True def parse_model(d, ch): # model_dict, input_channels(3) #original #print('\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 = max(round(n * gd), 1) if n > 1 else n # depth gain if m in [nn.Conv2d, Conv, Bottleneck, SPP, DWConv, Focus, BottleneckCSP]: #print('*m',m) c1, c2 = ch[f], args[0] c2 = make_divisible(c2 * gw, 8) if c2 != no else c2 args = [c1, c2, *args[1:]] if m in [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: args.append([ch[x + 1] for x in f]) if isinstance(args[1], int): # number of anchors args[1] = [list(range(args[1] * 2))] * len(f) 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%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_) ch.append(c2) return nn.Sequential(*layers), sorted(save)