From a543b85f641c9a5b4a710cf0ba42740383e4f84c Mon Sep 17 00:00:00 2001 From: Zhora Begloyan Date: Mon, 14 Nov 2022 11:54:11 +0400 Subject: [PATCH] Updated yolo.py to support models trained by yolov5 v6.2 --- asone/detectors/yolov5/yolov5/models/yolo.py | 248 +++++++++++-------- 1 file changed, 147 insertions(+), 101 deletions(-) diff --git a/asone/detectors/yolov5/yolov5/models/yolo.py b/asone/detectors/yolov5/yolov5/models/yolo.py index c72eaf6..8b258c2 100644 --- a/asone/detectors/yolov5/yolov5/models/yolo.py +++ b/asone/detectors/yolov5/yolov5/models/yolo.py @@ -16,24 +16,16 @@ FILE = Path(__file__).resolve() ROOT = FILE.parents[1] # YOLOv5 root directory -# if str(ROOT) not in sys.path: -# sys.path.append(str(ROOT)) # add ROOT to PATH +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH if platform.system() != 'Windows': ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative from asone.detectors.yolov5.yolov5.models.common import * from asone.detectors.yolov5.yolov5.models.experimental import * -from asone.detectors.yolov5.yolov5.models.general import (LOGGER, check_version, - check_yaml, make_divisible, - print_args) -from asone.detectors.yolov5.yolov5.utils.torch_utils import ( - fuse_conv_and_bn, - initialize_weights, - model_info, - profile, - scale_img, - select_device, - time_sync) +from asone.detectors.yolov5.yolov5.models.general import LOGGER, check_version, check_yaml, make_divisible, print_args +from asone.detectors.yolov5.yolov5.utils.torch_utils import (fuse_conv_and_bn, initialize_weights, model_info, profile, scale_img, select_device, + time_sync) try: import thop # for FLOPs computation @@ -42,8 +34,9 @@ class Detect(nn.Module): + # YOLOv5 Detect head for detection models stride = None # strides computed during build - onnx_dynamic = False # ONNX export parameter + dynamic = False # force grid reconstruction export = False # export mode def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer @@ -52,8 +45,8 @@ def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer 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 - self.anchor_grid = [torch.zeros(1)] * self.nl # init anchor grid + self.grid = [torch.empty(0) for _ in range(self.nl)] # init grid + self.anchor_grid = [torch.empty(0) for _ in range(self.nl)] # init anchor grid self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2) self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv self.inplace = inplace # use inplace ops (e.g. slice assignment) @@ -66,38 +59,109 @@ def forward(self, x): 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.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]: + if self.dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]: self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i) - y = x[i].sigmoid() - if self.inplace: - y[..., 0:2] = (y[..., 0:2] * 2 + 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, wh, conf = y.split((2, 2, self.nc + 1), 4) # y.tensor_split((2, 4, 5), 4) # torch 1.8.0 + if isinstance(self, Segment): # (boxes + masks) + xy, wh, conf, mask = x[i].split((2, 2, self.nc + 1, self.no - self.nc - 5), 4) + xy = (xy.sigmoid() * 2 + self.grid[i]) * self.stride[i] # xy + wh = (wh.sigmoid() * 2) ** 2 * self.anchor_grid[i] # wh + y = torch.cat((xy, wh, conf.sigmoid(), mask), 4) + else: # Detect (boxes only) + xy, wh, conf = x[i].sigmoid().split((2, 2, self.nc + 1), 4) xy = (xy * 2 + self.grid[i]) * self.stride[i] # xy wh = (wh * 2) ** 2 * self.anchor_grid[i] # wh y = torch.cat((xy, wh, conf), 4) - z.append(y.view(bs, -1, self.no)) + z.append(y.view(bs, self.na * nx * ny, self.no)) return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x) - def _make_grid(self, nx=20, ny=20, i=0): + def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')): d = self.anchors[i].device t = self.anchors[i].dtype shape = 1, self.na, ny, nx, 2 # grid shape y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t) - if check_version(torch.__version__, '1.10.0'): # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility - yv, xv = torch.meshgrid(y, x, indexing='ij') - else: - yv, xv = torch.meshgrid(y, x) + yv, xv = torch.meshgrid(y, x, indexing='ij') if torch_1_10 else torch.meshgrid(y, x) # torch>=0.7 compatibility grid = torch.stack((xv, yv), 2).expand(shape) - 0.5 # add grid offset, i.e. y = 2.0 * x - 0.5 anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape) return grid, anchor_grid -class Model(nn.Module): - # YOLOv5 model +class Segment(Detect): + # YOLOv5 Segment head for segmentation models + def __init__(self, nc=80, anchors=(), nm=32, npr=256, ch=(), inplace=True): + super().__init__(nc, anchors, ch, inplace) + self.nm = nm # number of masks + self.npr = npr # number of protos + self.no = 5 + nc + self.nm # number of outputs per anchor + self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv + self.proto = Proto(ch[0], self.npr, self.nm) # protos + self.detect = Detect.forward + + def forward(self, x): + p = self.proto(x[0]) + x = self.detect(self, x) + return (x, p) if self.training else (x[0], p) if self.export else (x[0], p, x[1]) + + +class BaseModel(nn.Module): + # YOLOv5 base model + def forward(self, x, profile=False, visualize=False): + return self._forward_once(x, profile, visualize) # single-scale 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: + self._profile_one_layer(m, x, dt) + 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) + return x + + def _profile_one_layer(self, m, x, dt): + c = m == self.model[-1] # is final layer, copy input as inplace fix + o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs + t = time_sync() + for _ in range(10): + m(x.copy() if c else 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}') + if c: + LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total") + + 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 info(self, verbose=False, img_size=640): # print model information + model_info(self, verbose, img_size) + + def _apply(self, fn): + # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers + self = super()._apply(fn) + m = self.model[-1] # Detect() + if isinstance(m, (Detect, Segment)): + m.stride = fn(m.stride) + m.grid = list(map(fn, m.grid)) + if isinstance(m.anchor_grid, list): + m.anchor_grid = list(map(fn, m.anchor_grid)) + return self + + +class DetectionModel(BaseModel): + # YOLOv5 detection model def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes super().__init__() if isinstance(cfg, dict): @@ -122,11 +186,12 @@ def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, i # Build strides, anchors m = self.model[-1] # Detect() - if isinstance(m, Detect): + if isinstance(m, (Detect, Segment)): 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 - check_anchor_order(m) # must be in pixel-space (not grid-space) + forward = lambda x: self.forward(x)[0] if isinstance(m, Segment) else self.forward(x) + m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))]) # forward + check_anchor_order(m) m.anchors /= m.stride.view(-1, 1, 1) self.stride = m.stride self._initialize_biases() # only run once @@ -155,19 +220,6 @@ def _forward_augment(self, x): y = self._clip_augmented(y) # clip augmented tails 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: - self._profile_one_layer(m, x, dt) - 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) - return x - def _descale_pred(self, p, flips, scale, img_size): # de-scale predictions following augmented inference (inverse operation) if self.inplace: @@ -196,69 +248,59 @@ def _clip_augmented(self, y): y[-1] = y[-1][:, i:] # small return y - def _profile_one_layer(self, m, x, dt): - c = isinstance(m, Detect) # is final layer, copy input as inplace fix - o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs - t = time_sync() - for _ in range(10): - m(x.copy() if c else 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}') - if c: - LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total") - 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).detach() # 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 - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # cls + 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[:, 5:5 + m.nc] += math.log(0.6 / (m.nc - 0.99999)) 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 +Model = DetectionModel # retain YOLOv5 'Model' class for backwards compatibility - 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 info(self, verbose=False, img_size=640): # print model information - model_info(self, verbose, img_size) +class SegmentationModel(DetectionModel): + # YOLOv5 segmentation model + def __init__(self, cfg='yolov5s-seg.yaml', ch=3, nc=None, anchors=None): + super().__init__(cfg, ch, nc, anchors) - def _apply(self, fn): - # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers - self = super()._apply(fn) - m = self.model[-1] # Detect() - if isinstance(m, Detect): - m.stride = fn(m.stride) - m.grid = list(map(fn, m.grid)) - if isinstance(m.anchor_grid, list): - m.anchor_grid = list(map(fn, m.anchor_grid)) - return self + +class ClassificationModel(BaseModel): + # YOLOv5 classification model + def __init__(self, cfg=None, model=None, nc=1000, cutoff=10): # yaml, model, number of classes, cutoff index + super().__init__() + self._from_detection_model(model, nc, cutoff) if model is not None else self._from_yaml(cfg) + + def _from_detection_model(self, model, nc=1000, cutoff=10): + # Create a YOLOv5 classification model from a YOLOv5 detection model + if isinstance(model, DetectMultiBackend): + model = model.model # unwrap DetectMultiBackend + model.model = model.model[:cutoff] # backbone + m = model.model[-1] # last layer + ch = m.conv.in_channels if hasattr(m, 'conv') else m.cv1.conv.in_channels # ch into module + c = Classify(ch, nc) # Classify() + c.i, c.f, c.type = m.i, m.f, 'models.common.Classify' # index, from, type + model.model[-1] = c # replace + self.model = model.model + self.stride = model.stride + self.save = [] + self.nc = nc + + def _from_yaml(self, cfg): + # Create a YOLOv5 classification model from a *.yaml file + self.model = None def parse_model(d, ch): # model_dict, input_channels(3) + # Parse a YOLOv5 model.yaml dictionary LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}") - anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'] + anchors, nc, gd, gw, act = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation') + if act: + Conv.default_act = eval(act) # redefine default activation, i.e. Conv.default_act = nn.SiLU() + LOGGER.info(f"{colorstr('activation:')} {act}") # print na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors no = na * (nc + 5) # number of outputs = anchors * (classes + 5) @@ -270,24 +312,28 @@ def parse_model(d, ch): # model_dict, input_channels(3) args[j] = eval(a) if isinstance(a, str) else a # eval strings n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain - if m in (Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, - BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x): + if m in { + Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, + BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}: 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, C3Ghost, C3x]: + if m in {BottleneckCSP, C3, C3TR, C3Ghost, C3x}: 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: + # TODO: channel, gw, gd + elif m in {Detect, Segment}: 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) + if m is Segment: + args[3] = make_divisible(args[3] * gw, 8) elif m is Contract: c2 = ch[f] * args[0] ** 2 elif m is Expand: @@ -327,7 +373,7 @@ def parse_model(d, ch): # model_dict, input_channels(3) # Options if opt.line_profile: # profile layer by layer - _ = model(im, profile=True) + model(im, profile=True) elif opt.profile: # profile forward-backward results = profile(input=im, ops=[model], n=3) @@ -340,4 +386,4 @@ def parse_model(d, ch): # model_dict, input_channels(3) print(f'Error in {cfg}: {e}') else: # report fused model summary - model.fuse() + model.fuse() \ No newline at end of file