diff options
Diffstat (limited to 'r_facelib/detection/yolov5face/models')
| -rw-r--r-- | r_facelib/detection/yolov5face/models/__init__.py | 0 | ||||
| -rw-r--r-- | r_facelib/detection/yolov5face/models/common.py | 299 | ||||
| -rw-r--r-- | r_facelib/detection/yolov5face/models/experimental.py | 45 | ||||
| -rw-r--r-- | r_facelib/detection/yolov5face/models/yolo.py | 235 | ||||
| -rw-r--r-- | r_facelib/detection/yolov5face/models/yolov5l.yaml | 47 | ||||
| -rw-r--r-- | r_facelib/detection/yolov5face/models/yolov5n.yaml | 45 |
6 files changed, 671 insertions, 0 deletions
diff --git a/r_facelib/detection/yolov5face/models/__init__.py b/r_facelib/detection/yolov5face/models/__init__.py new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/r_facelib/detection/yolov5face/models/__init__.py diff --git a/r_facelib/detection/yolov5face/models/common.py b/r_facelib/detection/yolov5face/models/common.py new file mode 100644 index 0000000..96894d5 --- /dev/null +++ b/r_facelib/detection/yolov5face/models/common.py @@ -0,0 +1,299 @@ +# This file contains modules common to various models
+
+import math
+
+import numpy as np
+import torch
+from torch import nn
+
+from r_facelib.detection.yolov5face.utils.datasets import letterbox
+from r_facelib.detection.yolov5face.utils.general import (
+ make_divisible,
+ non_max_suppression,
+ scale_coords,
+ xyxy2xywh,
+)
+
+
+def autopad(k, p=None): # kernel, padding
+ # Pad to 'same'
+ if p is None:
+ p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
+ return p
+
+
+def channel_shuffle(x, groups):
+ batchsize, num_channels, height, width = x.data.size()
+ channels_per_group = torch.div(num_channels, groups, rounding_mode="trunc")
+
+ # reshape
+ x = x.view(batchsize, groups, channels_per_group, height, width)
+ x = torch.transpose(x, 1, 2).contiguous()
+
+ # flatten
+ return x.view(batchsize, -1, height, width)
+
+
+def DWConv(c1, c2, k=1, s=1, act=True):
+ # Depthwise convolution
+ return Conv(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
+
+
+class Conv(nn.Module):
+ # Standard convolution
+ def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
+ super().__init__()
+ self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
+ self.bn = nn.BatchNorm2d(c2)
+ self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
+
+ def forward(self, x):
+ return self.act(self.bn(self.conv(x)))
+
+ def fuseforward(self, x):
+ return self.act(self.conv(x))
+
+
+class StemBlock(nn.Module):
+ def __init__(self, c1, c2, k=3, s=2, p=None, g=1, act=True):
+ super().__init__()
+ self.stem_1 = Conv(c1, c2, k, s, p, g, act)
+ self.stem_2a = Conv(c2, c2 // 2, 1, 1, 0)
+ self.stem_2b = Conv(c2 // 2, c2, 3, 2, 1)
+ self.stem_2p = nn.MaxPool2d(kernel_size=2, stride=2, ceil_mode=True)
+ self.stem_3 = Conv(c2 * 2, c2, 1, 1, 0)
+
+ def forward(self, x):
+ stem_1_out = self.stem_1(x)
+ stem_2a_out = self.stem_2a(stem_1_out)
+ stem_2b_out = self.stem_2b(stem_2a_out)
+ stem_2p_out = self.stem_2p(stem_1_out)
+ return self.stem_3(torch.cat((stem_2b_out, stem_2p_out), 1))
+
+
+class Bottleneck(nn.Module):
+ # Standard bottleneck
+ def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
+ super().__init__()
+ c_ = int(c2 * e) # hidden channels
+ self.cv1 = Conv(c1, c_, 1, 1)
+ self.cv2 = Conv(c_, c2, 3, 1, g=g)
+ self.add = shortcut and c1 == c2
+
+ def forward(self, x):
+ return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class BottleneckCSP(nn.Module):
+ # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+ def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
+ super().__init__()
+ c_ = int(c2 * e) # hidden channels
+ self.cv1 = Conv(c1, c_, 1, 1)
+ self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
+ self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
+ self.cv4 = Conv(2 * c_, c2, 1, 1)
+ self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3)
+ self.act = nn.LeakyReLU(0.1, inplace=True)
+ self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
+
+ def forward(self, x):
+ y1 = self.cv3(self.m(self.cv1(x)))
+ y2 = self.cv2(x)
+ return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
+
+
+class C3(nn.Module):
+ # CSP Bottleneck with 3 convolutions
+ def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
+ super().__init__()
+ c_ = int(c2 * e) # hidden channels
+ self.cv1 = Conv(c1, c_, 1, 1)
+ self.cv2 = Conv(c1, c_, 1, 1)
+ self.cv3 = Conv(2 * c_, c2, 1) # act=FReLU(c2)
+ self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
+
+ def forward(self, x):
+ return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
+
+
+class ShuffleV2Block(nn.Module):
+ def __init__(self, inp, oup, stride):
+ super().__init__()
+
+ if not 1 <= stride <= 3:
+ raise ValueError("illegal stride value")
+ self.stride = stride
+
+ branch_features = oup // 2
+
+ if self.stride > 1:
+ self.branch1 = nn.Sequential(
+ self.depthwise_conv(inp, inp, kernel_size=3, stride=self.stride, padding=1),
+ nn.BatchNorm2d(inp),
+ nn.Conv2d(inp, branch_features, kernel_size=1, stride=1, padding=0, bias=False),
+ nn.BatchNorm2d(branch_features),
+ nn.SiLU(),
+ )
+ else:
+ self.branch1 = nn.Sequential()
+
+ self.branch2 = nn.Sequential(
+ nn.Conv2d(
+ inp if (self.stride > 1) else branch_features,
+ branch_features,
+ kernel_size=1,
+ stride=1,
+ padding=0,
+ bias=False,
+ ),
+ nn.BatchNorm2d(branch_features),
+ nn.SiLU(),
+ self.depthwise_conv(branch_features, branch_features, kernel_size=3, stride=self.stride, padding=1),
+ nn.BatchNorm2d(branch_features),
+ nn.Conv2d(branch_features, branch_features, kernel_size=1, stride=1, padding=0, bias=False),
+ nn.BatchNorm2d(branch_features),
+ nn.SiLU(),
+ )
+
+ @staticmethod
+ def depthwise_conv(i, o, kernel_size, stride=1, padding=0, bias=False):
+ return nn.Conv2d(i, o, kernel_size, stride, padding, bias=bias, groups=i)
+
+ def forward(self, x):
+ if self.stride == 1:
+ x1, x2 = x.chunk(2, dim=1)
+ out = torch.cat((x1, self.branch2(x2)), dim=1)
+ else:
+ out = torch.cat((self.branch1(x), self.branch2(x)), dim=1)
+ out = channel_shuffle(out, 2)
+ return out
+
+
+class SPP(nn.Module):
+ # Spatial pyramid pooling layer used in YOLOv3-SPP
+ def __init__(self, c1, c2, k=(5, 9, 13)):
+ super().__init__()
+ c_ = c1 // 2 # hidden channels
+ self.cv1 = Conv(c1, c_, 1, 1)
+ self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
+ self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
+
+ def forward(self, x):
+ x = self.cv1(x)
+ return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
+
+
+class Focus(nn.Module):
+ # Focus wh information into c-space
+ def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
+ super().__init__()
+ self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
+
+ def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2)
+ return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
+
+
+class Concat(nn.Module):
+ # Concatenate a list of tensors along dimension
+ def __init__(self, dimension=1):
+ super().__init__()
+ self.d = dimension
+
+ def forward(self, x):
+ return torch.cat(x, self.d)
+
+
+class NMS(nn.Module):
+ # Non-Maximum Suppression (NMS) module
+ conf = 0.25 # confidence threshold
+ iou = 0.45 # IoU threshold
+ classes = None # (optional list) filter by class
+
+ def forward(self, x):
+ return non_max_suppression(x[0], conf_thres=self.conf, iou_thres=self.iou, classes=self.classes)
+
+
+class AutoShape(nn.Module):
+ # input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
+ img_size = 640 # inference size (pixels)
+ conf = 0.25 # NMS confidence threshold
+ iou = 0.45 # NMS IoU threshold
+ classes = None # (optional list) filter by class
+
+ def __init__(self, model):
+ super().__init__()
+ self.model = model.eval()
+
+ def autoshape(self):
+ print("autoShape already enabled, skipping... ") # model already converted to model.autoshape()
+ return self
+
+ def forward(self, imgs, size=640, augment=False, profile=False):
+ # Inference from various sources. For height=720, width=1280, RGB images example inputs are:
+ # OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(720,1280,3)
+ # PIL: = Image.open('image.jpg') # HWC x(720,1280,3)
+ # numpy: = np.zeros((720,1280,3)) # HWC
+ # torch: = torch.zeros(16,3,720,1280) # BCHW
+ # multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
+
+ p = next(self.model.parameters()) # for device and type
+ if isinstance(imgs, torch.Tensor): # torch
+ return self.model(imgs.to(p.device).type_as(p), augment, profile) # inference
+
+ # Pre-process
+ n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs]) # number of images, list of images
+ shape0, shape1 = [], [] # image and inference shapes
+ for i, im in enumerate(imgs):
+ im = np.array(im) # to numpy
+ if im.shape[0] < 5: # image in CHW
+ im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1)
+ im = im[:, :, :3] if im.ndim == 3 else np.tile(im[:, :, None], 3) # enforce 3ch input
+ s = im.shape[:2] # HWC
+ shape0.append(s) # image shape
+ g = size / max(s) # gain
+ shape1.append([y * g for y in s])
+ imgs[i] = im # update
+ shape1 = [make_divisible(x, int(self.stride.max())) for x in np.stack(shape1, 0).max(0)] # inference shape
+ x = [letterbox(im, new_shape=shape1, auto=False)[0] for im in imgs] # pad
+ x = np.stack(x, 0) if n > 1 else x[0][None] # stack
+ x = np.ascontiguousarray(x.transpose((0, 3, 1, 2))) # BHWC to BCHW
+ x = torch.from_numpy(x).to(p.device).type_as(p) / 255.0 # uint8 to fp16/32
+
+ # Inference
+ with torch.no_grad():
+ y = self.model(x, augment, profile)[0] # forward
+ y = non_max_suppression(y, conf_thres=self.conf, iou_thres=self.iou, classes=self.classes) # NMS
+
+ # Post-process
+ for i in range(n):
+ scale_coords(shape1, y[i][:, :4], shape0[i])
+
+ return Detections(imgs, y, self.names)
+
+
+class Detections:
+ # detections class for YOLOv5 inference results
+ def __init__(self, imgs, pred, names=None):
+ super().__init__()
+ d = pred[0].device # device
+ gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1.0, 1.0], device=d) for im in imgs] # normalizations
+ self.imgs = imgs # list of images as numpy arrays
+ self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls)
+ self.names = names # class names
+ self.xyxy = pred # xyxy pixels
+ self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels
+ self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized
+ self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized
+ self.n = len(self.pred)
+
+ def __len__(self):
+ return self.n
+
+ def tolist(self):
+ # return a list of Detections objects, i.e. 'for result in results.tolist():'
+ x = [Detections([self.imgs[i]], [self.pred[i]], self.names) for i in range(self.n)]
+ for d in x:
+ for k in ["imgs", "pred", "xyxy", "xyxyn", "xywh", "xywhn"]:
+ setattr(d, k, getattr(d, k)[0]) # pop out of list
+ return x
diff --git a/r_facelib/detection/yolov5face/models/experimental.py b/r_facelib/detection/yolov5face/models/experimental.py new file mode 100644 index 0000000..bdf7aea --- /dev/null +++ b/r_facelib/detection/yolov5face/models/experimental.py @@ -0,0 +1,45 @@ +# # This file contains experimental modules
+
+import numpy as np
+import torch
+from torch import nn
+
+from r_facelib.detection.yolov5face.models.common import Conv
+
+
+class CrossConv(nn.Module):
+ # Cross Convolution Downsample
+ def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
+ # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
+ super().__init__()
+ c_ = int(c2 * e) # hidden channels
+ self.cv1 = Conv(c1, c_, (1, k), (1, s))
+ self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
+ self.add = shortcut and c1 == c2
+
+ def forward(self, x):
+ return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class MixConv2d(nn.Module):
+ # Mixed Depthwise Conv https://arxiv.org/abs/1907.09595
+ def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
+ super().__init__()
+ groups = len(k)
+ if equal_ch: # equal c_ per group
+ i = torch.linspace(0, groups - 1e-6, c2).floor() # c2 indices
+ c_ = [(i == g).sum() for g in range(groups)] # intermediate channels
+ else: # equal weight.numel() per group
+ b = [c2] + [0] * groups
+ a = np.eye(groups + 1, groups, k=-1)
+ a -= np.roll(a, 1, axis=1)
+ a *= np.array(k) ** 2
+ a[0] = 1
+ c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b
+
+ self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)])
+ self.bn = nn.BatchNorm2d(c2)
+ self.act = nn.LeakyReLU(0.1, inplace=True)
+
+ def forward(self, x):
+ return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
diff --git a/r_facelib/detection/yolov5face/models/yolo.py b/r_facelib/detection/yolov5face/models/yolo.py new file mode 100644 index 0000000..02479dc --- /dev/null +++ b/r_facelib/detection/yolov5face/models/yolo.py @@ -0,0 +1,235 @@ +import math
+from copy import deepcopy
+from pathlib import Path
+
+import torch
+import yaml # for torch hub
+from torch import nn
+
+from r_facelib.detection.yolov5face.models.common import (
+ C3,
+ NMS,
+ SPP,
+ AutoShape,
+ Bottleneck,
+ BottleneckCSP,
+ Concat,
+ Conv,
+ DWConv,
+ Focus,
+ ShuffleV2Block,
+ StemBlock,
+)
+from r_facelib.detection.yolov5face.models.experimental import CrossConv, MixConv2d
+from r_facelib.detection.yolov5face.utils.autoanchor import check_anchor_order
+from r_facelib.detection.yolov5face.utils.general import make_divisible
+from r_facelib.detection.yolov5face.utils.torch_utils import copy_attr, fuse_conv_and_bn
+
+
+class Detect(nn.Module):
+ stride = None # strides computed during build
+ export = False # onnx export
+
+ def __init__(self, nc=80, anchors=(), ch=()): # detection layer
+ super().__init__()
+ self.nc = nc # number of classes
+ self.no = nc + 5 + 10 # 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
+
+ def forward(self, x):
+ z = [] # inference output
+ if self.export:
+ for i in range(self.nl):
+ x[i] = self.m[i](x[i])
+ return x
+ 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()
+
+ 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 = torch.full_like(x[i], 0)
+ y[..., [0, 1, 2, 3, 4, 15]] = x[i][..., [0, 1, 2, 3, 4, 15]].sigmoid()
+ y[..., 5:15] = x[i][..., 5:15]
+
+ y[..., 0:2] = (y[..., 0:2] * 2.0 - 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
+
+ y[..., 5:7] = (
+ y[..., 5:7] * self.anchor_grid[i] + self.grid[i].to(x[i].device) * self.stride[i]
+ ) # landmark x1 y1
+ y[..., 7:9] = (
+ y[..., 7:9] * self.anchor_grid[i] + self.grid[i].to(x[i].device) * self.stride[i]
+ ) # landmark x2 y2
+ y[..., 9:11] = (
+ y[..., 9:11] * self.anchor_grid[i] + self.grid[i].to(x[i].device) * self.stride[i]
+ ) # landmark x3 y3
+ y[..., 11:13] = (
+ y[..., 11:13] * self.anchor_grid[i] + self.grid[i].to(x[i].device) * self.stride[i]
+ ) # landmark x4 y4
+ y[..., 13:15] = (
+ y[..., 13:15] * self.anchor_grid[i] + self.grid[i].to(x[i].device) * self.stride[i]
+ ) # landmark x5 y5
+
+ 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)], indexing="ij") # for pytorch>=1.10
+ 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().__init__()
+ self.yaml_file = Path(cfg).name
+ with Path(cfg).open(encoding="utf8") as f:
+ self.yaml = yaml.safe_load(f) # model dict
+
+ # Define model
+ ch = self.yaml["ch"] = self.yaml.get("ch", ch) # input channels
+ if nc and nc != self.yaml["nc"]:
+ self.yaml["nc"] = nc # override yaml value
+
+ self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
+ self.names = [str(i) for i in range(self.yaml["nc"])] # default names
+
+ # 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
+ m.anchors /= m.stride.view(-1, 1, 1)
+ check_anchor_order(m)
+ self.stride = m.stride
+ self._initialize_biases() # only run once
+
+ def forward(self, x):
+ return self.forward_once(x) # single-scale inference, train
+
+ def forward_once(self, x):
+ y = [] # 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
+ # https://arxiv.org/abs/1708.02002 section 3.3
+ 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.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
+ b.data[:, 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 mi in m.m: # from
+ b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
+ print(("%6g Conv2d.bias:" + "%10.3g" * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
+
+ def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
+ print("Fusing layers... ")
+ for m in self.model.modules():
+ if isinstance(m, Conv) and hasattr(m, "bn"):
+ m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
+ delattr(m, "bn") # remove batchnorm
+ m.forward = m.fuseforward # update forward
+ elif type(m) is nn.Upsample:
+ m.recompute_scale_factor = None # torch 1.11.0 compatibility
+ return self
+
+ def nms(self, mode=True): # add or remove NMS module
+ present = isinstance(self.model[-1], NMS) # last layer is NMS
+ if mode and not present:
+ print("Adding NMS... ")
+ m = NMS() # module
+ m.f = -1 # from
+ m.i = self.model[-1].i + 1 # index
+ self.model.add_module(name=str(m.i), module=m) # add
+ self.eval()
+ elif not mode and present:
+ print("Removing NMS... ")
+ self.model = self.model[:-1] # remove
+ return self
+
+ def autoshape(self): # add autoShape module
+ print("Adding autoShape... ")
+ m = AutoShape(self) # wrap model
+ copy_attr(m, self, include=("yaml", "nc", "hyp", "names", "stride"), exclude=()) # copy attributes
+ return m
+
+
+def parse_model(d, ch): # model_dict, input_channels(3)
+ 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 [
+ Conv,
+ Bottleneck,
+ SPP,
+ DWConv,
+ MixConv2d,
+ Focus,
+ CrossConv,
+ BottleneckCSP,
+ C3,
+ ShuffleV2Block,
+ StemBlock,
+ ]:
+ 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, C3]:
+ 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
+ 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)
diff --git a/r_facelib/detection/yolov5face/models/yolov5l.yaml b/r_facelib/detection/yolov5face/models/yolov5l.yaml new file mode 100644 index 0000000..98a9e2c --- /dev/null +++ b/r_facelib/detection/yolov5face/models/yolov5l.yaml @@ -0,0 +1,47 @@ +# parameters
+nc: 1 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+
+# anchors
+anchors:
+ - [4,5, 8,10, 13,16] # P3/8
+ - [23,29, 43,55, 73,105] # P4/16
+ - [146,217, 231,300, 335,433] # P5/32
+
+# YOLOv5 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, StemBlock, [64, 3, 2]], # 0-P1/2
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 2-P3/8
+ [-1, 9, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 4-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 6-P5/32
+ [-1, 1, SPP, [1024, [3,5,7]]],
+ [-1, 3, C3, [1024, False]], # 8
+ ]
+
+# YOLOv5 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 5], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 12
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 3], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 16 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 13], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 19 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 9], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 22 (P5/32-large)
+
+ [[16, 19, 22], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
\ No newline at end of file diff --git a/r_facelib/detection/yolov5face/models/yolov5n.yaml b/r_facelib/detection/yolov5face/models/yolov5n.yaml new file mode 100644 index 0000000..0a03fb0 --- /dev/null +++ b/r_facelib/detection/yolov5face/models/yolov5n.yaml @@ -0,0 +1,45 @@ +# parameters
+nc: 1 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+
+# anchors
+anchors:
+ - [4,5, 8,10, 13,16] # P3/8
+ - [23,29, 43,55, 73,105] # P4/16
+ - [146,217, 231,300, 335,433] # P5/32
+
+# YOLOv5 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, StemBlock, [32, 3, 2]], # 0-P2/4
+ [-1, 1, ShuffleV2Block, [128, 2]], # 1-P3/8
+ [-1, 3, ShuffleV2Block, [128, 1]], # 2
+ [-1, 1, ShuffleV2Block, [256, 2]], # 3-P4/16
+ [-1, 7, ShuffleV2Block, [256, 1]], # 4
+ [-1, 1, ShuffleV2Block, [512, 2]], # 5-P5/32
+ [-1, 3, ShuffleV2Block, [512, 1]], # 6
+ ]
+
+# YOLOv5 head
+head:
+ [[-1, 1, Conv, [128, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P4
+ [-1, 1, C3, [128, False]], # 10
+
+ [-1, 1, Conv, [128, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 2], 1, Concat, [1]], # cat backbone P3
+ [-1, 1, C3, [128, False]], # 14 (P3/8-small)
+
+ [-1, 1, Conv, [128, 3, 2]],
+ [[-1, 11], 1, Concat, [1]], # cat head P4
+ [-1, 1, C3, [128, False]], # 17 (P4/16-medium)
+
+ [-1, 1, Conv, [128, 3, 2]],
+ [[-1, 7], 1, Concat, [1]], # cat head P5
+ [-1, 1, C3, [128, False]], # 20 (P5/32-large)
+
+ [[14, 17, 20], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
|