123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843 |
- import argparse
- import logging
- import sys
- from copy import deepcopy
- sys.path.append('./')
- logger = logging.getLogger(__name__)
- import torch
- from models.common import *
- from models.experimental import *
- from utils.autoanchor import check_anchor_order
- from utils.general import make_divisible, check_file, set_logging
- from utils.torch_utils import time_synchronized, fuse_conv_and_bn, model_info, scale_img, initialize_weights, \
- select_device, copy_attr
- from utils.loss import SigmoidBin
- try:
- import thop
- except ImportError:
- thop = None
- class Detect(nn.Module):
- stride = None
- export = False
- end2end = False
- include_nms = False
- concat = False
- def __init__(self, nc=80, anchors=(), ch=()):
- super(Detect, self).__init__()
- self.nc = nc
- self.no = nc + 5
- self.nl = len(anchors)
- self.na = len(anchors[0]) // 2
- self.grid = [torch.zeros(1)] * self.nl
- a = torch.tensor(anchors).float().view(self.nl, -1, 2)
- self.register_buffer('anchors', a)
- self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))
- self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)
- def forward(self, x):
-
- z = []
- self.training |= self.export
- for i in range(self.nl):
- x[i] = self.m[i](x[i])
- bs, _, ny, nx = x[i].shape
- x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
- if not self.training:
- 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()
- if not torch.onnx.is_in_onnx_export():
- y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]
- y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
- else:
- xy, wh, conf = y.split((2, 2, self.nc + 1), 4)
- xy = xy * (2. * self.stride[i]) + (self.stride[i] * (self.grid[i] - 0.5))
- wh = wh ** 2 * (4 * self.anchor_grid[i].data)
- y = torch.cat((xy, wh, conf), 4)
- z.append(y.view(bs, -1, self.no))
- if self.training:
- out = x
- elif self.end2end:
- out = torch.cat(z, 1)
- elif self.include_nms:
- z = self.convert(z)
- out = (z, )
- elif self.concat:
- out = torch.cat(z, 1)
- else:
- out = (torch.cat(z, 1), x)
- return out
- @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()
- def convert(self, z):
- z = torch.cat(z, 1)
- box = z[:, :, :4]
- conf = z[:, :, 4:5]
- score = z[:, :, 5:]
- score *= conf
- convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
- dtype=torch.float32,
- device=z.device)
- box @= convert_matrix
- return (box, score)
- class IDetect(nn.Module):
- stride = None
- export = False
- end2end = False
- include_nms = False
- concat = False
- def __init__(self, nc=80, anchors=(), ch=()):
- super(IDetect, self).__init__()
- self.nc = nc
- self.no = nc + 5
- self.nl = len(anchors)
- self.na = len(anchors[0]) // 2
- self.grid = [torch.zeros(1)] * self.nl
- a = torch.tensor(anchors).float().view(self.nl, -1, 2)
- self.register_buffer('anchors', a)
- self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))
- self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)
-
- self.ia = nn.ModuleList(ImplicitA(x) for x in ch)
- self.im = nn.ModuleList(ImplicitM(self.no * self.na) for _ in ch)
- def forward(self, x):
-
- z = []
- self.training |= self.export
- for i in range(self.nl):
- x[i] = self.m[i](self.ia[i](x[i]))
- x[i] = self.im[i](x[i])
- bs, _, ny, nx = x[i].shape
- x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
- if not self.training:
- 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]) * self.stride[i]
- y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
- z.append(y.view(bs, -1, self.no))
- return x if self.training else (torch.cat(z, 1), x)
-
- def fuseforward(self, x):
-
- z = []
- self.training |= self.export
- for i in range(self.nl):
- x[i] = self.m[i](x[i])
- bs, _, ny, nx = x[i].shape
- x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
- if not self.training:
- 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()
- if not torch.onnx.is_in_onnx_export():
- y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]
- y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
- else:
- xy, wh, conf = y.split((2, 2, self.nc + 1), 4)
- xy = xy * (2. * self.stride[i]) + (self.stride[i] * (self.grid[i] - 0.5))
- wh = wh ** 2 * (4 * self.anchor_grid[i].data)
- y = torch.cat((xy, wh, conf), 4)
- z.append(y.view(bs, -1, self.no))
- if self.training:
- out = x
- elif self.end2end:
- out = torch.cat(z, 1)
- elif self.include_nms:
- z = self.convert(z)
- out = (z, )
- elif self.concat:
- out = torch.cat(z, 1)
- else:
- out = (torch.cat(z, 1), x)
- return out
-
- def fuse(self):
- print("IDetect.fuse")
-
- for i in range(len(self.m)):
- c1,c2,_,_ = self.m[i].weight.shape
- c1_,c2_, _,_ = self.ia[i].implicit.shape
- self.m[i].bias += torch.matmul(self.m[i].weight.reshape(c1,c2),self.ia[i].implicit.reshape(c2_,c1_)).squeeze(1)
-
- for i in range(len(self.m)):
- c1,c2, _,_ = self.im[i].implicit.shape
- self.m[i].bias *= self.im[i].implicit.reshape(c2)
- self.m[i].weight *= self.im[i].implicit.transpose(0,1)
-
- @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()
- def convert(self, z):
- z = torch.cat(z, 1)
- box = z[:, :, :4]
- conf = z[:, :, 4:5]
- score = z[:, :, 5:]
- score *= conf
- convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
- dtype=torch.float32,
- device=z.device)
- box @= convert_matrix
- return (box, score)
- class IKeypoint(nn.Module):
- stride = None
- export = False
- def __init__(self, nc=80, anchors=(), nkpt=17, ch=(), inplace=True, dw_conv_kpt=False):
- super(IKeypoint, self).__init__()
- self.nc = nc
- self.nkpt = nkpt
- self.dw_conv_kpt = dw_conv_kpt
- self.no_det=(nc + 5)
- self.no_kpt = 3*self.nkpt
- self.no = self.no_det+self.no_kpt
- self.nl = len(anchors)
- self.na = len(anchors[0]) // 2
- self.grid = [torch.zeros(1)] * self.nl
- self.flip_test = False
- a = torch.tensor(anchors).float().view(self.nl, -1, 2)
- self.register_buffer('anchors', a)
- self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))
- self.m = nn.ModuleList(nn.Conv2d(x, self.no_det * self.na, 1) for x in ch)
-
- self.ia = nn.ModuleList(ImplicitA(x) for x in ch)
- self.im = nn.ModuleList(ImplicitM(self.no_det * self.na) for _ in ch)
-
- if self.nkpt is not None:
- if self.dw_conv_kpt:
- self.m_kpt = nn.ModuleList(
- nn.Sequential(DWConv(x, x, k=3), Conv(x,x),
- DWConv(x, x, k=3), Conv(x, x),
- DWConv(x, x, k=3), Conv(x,x),
- DWConv(x, x, k=3), Conv(x, x),
- DWConv(x, x, k=3), Conv(x, x),
- DWConv(x, x, k=3), nn.Conv2d(x, self.no_kpt * self.na, 1)) for x in ch)
- else:
- self.m_kpt = nn.ModuleList(nn.Conv2d(x, self.no_kpt * self.na, 1) for x in ch)
- self.inplace = inplace
- def forward(self, x):
-
- z = []
- self.training |= self.export
- for i in range(self.nl):
- if self.nkpt is None or self.nkpt==0:
- x[i] = self.im[i](self.m[i](self.ia[i](x[i])))
- else :
- x[i] = torch.cat((self.im[i](self.m[i](self.ia[i](x[i]))), self.m_kpt[i](x[i])), axis=1)
- bs, _, ny, nx = x[i].shape
- x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
- x_det = x[i][..., :6]
- x_kpt = x[i][..., 6:]
- if not self.training:
- if self.grid[i].shape[2:4] != x[i].shape[2:4]:
- self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
- kpt_grid_x = self.grid[i][..., 0:1]
- kpt_grid_y = self.grid[i][..., 1:2]
- if self.nkpt == 0:
- y = x[i].sigmoid()
- else:
- y = x_det.sigmoid()
- if self.inplace:
- xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]
- wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].view(1, self.na, 1, 1, 2)
- if self.nkpt != 0:
- x_kpt[..., 0::3] = (x_kpt[..., ::3] * 2. - 0.5 + kpt_grid_x.repeat(1,1,1,1,17)) * self.stride[i]
- x_kpt[..., 1::3] = (x_kpt[..., 1::3] * 2. - 0.5 + kpt_grid_y.repeat(1,1,1,1,17)) * self.stride[i]
-
-
-
-
-
-
-
-
-
-
- x_kpt[..., 2::3] = x_kpt[..., 2::3].sigmoid()
- y = torch.cat((xy, wh, y[..., 4:], x_kpt), dim = -1)
- else:
- xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]
- wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
- if self.nkpt != 0:
- y[..., 6:] = (y[..., 6:] * 2. - 0.5 + self.grid[i].repeat((1,1,1,1,self.nkpt))) * self.stride[i]
- y = torch.cat((xy, wh, y[..., 4:]), -1)
- 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 IAuxDetect(nn.Module):
- stride = None
- export = False
- end2end = False
- include_nms = False
- concat = False
- def __init__(self, nc=80, anchors=(), ch=()):
- super(IAuxDetect, self).__init__()
- self.nc = nc
- self.no = nc + 5
- self.nl = len(anchors)
- self.na = len(anchors[0]) // 2
- self.grid = [torch.zeros(1)] * self.nl
- a = torch.tensor(anchors).float().view(self.nl, -1, 2)
- self.register_buffer('anchors', a)
- self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))
- self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch[:self.nl])
- self.m2 = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch[self.nl:])
-
- self.ia = nn.ModuleList(ImplicitA(x) for x in ch[:self.nl])
- self.im = nn.ModuleList(ImplicitM(self.no * self.na) for _ in ch[:self.nl])
- def forward(self, x):
-
- z = []
- self.training |= self.export
- for i in range(self.nl):
- x[i] = self.m[i](self.ia[i](x[i]))
- x[i] = self.im[i](x[i])
- bs, _, ny, nx = x[i].shape
- x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
-
- x[i+self.nl] = self.m2[i](x[i+self.nl])
- x[i+self.nl] = x[i+self.nl].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
- if not self.training:
- 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()
- if not torch.onnx.is_in_onnx_export():
- y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]
- y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
- else:
- xy, wh, conf = y.split((2, 2, self.nc + 1), 4)
- xy = xy * (2. * self.stride[i]) + (self.stride[i] * (self.grid[i] - 0.5))
- wh = wh ** 2 * (4 * self.anchor_grid[i].data)
- y = torch.cat((xy, wh, conf), 4)
- z.append(y.view(bs, -1, self.no))
- return x if self.training else (torch.cat(z, 1), x[:self.nl])
- def fuseforward(self, x):
-
- z = []
- self.training |= self.export
- for i in range(self.nl):
- x[i] = self.m[i](x[i])
- bs, _, ny, nx = x[i].shape
- x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
- if not self.training:
- 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()
- if not torch.onnx.is_in_onnx_export():
- y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]
- y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
- else:
- xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]
- wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].data
- y = torch.cat((xy, wh, y[..., 4:]), -1)
- z.append(y.view(bs, -1, self.no))
- if self.training:
- out = x
- elif self.end2end:
- out = torch.cat(z, 1)
- elif self.include_nms:
- z = self.convert(z)
- out = (z, )
- elif self.concat:
- out = torch.cat(z, 1)
- else:
- out = (torch.cat(z, 1), x)
- return out
-
- def fuse(self):
- print("IAuxDetect.fuse")
-
- for i in range(len(self.m)):
- c1,c2,_,_ = self.m[i].weight.shape
- c1_,c2_, _,_ = self.ia[i].implicit.shape
- self.m[i].bias += torch.matmul(self.m[i].weight.reshape(c1,c2),self.ia[i].implicit.reshape(c2_,c1_)).squeeze(1)
-
- for i in range(len(self.m)):
- c1,c2, _,_ = self.im[i].implicit.shape
- self.m[i].bias *= self.im[i].implicit.reshape(c2)
- self.m[i].weight *= self.im[i].implicit.transpose(0,1)
- @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()
- def convert(self, z):
- z = torch.cat(z, 1)
- box = z[:, :, :4]
- conf = z[:, :, 4:5]
- score = z[:, :, 5:]
- score *= conf
- convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
- dtype=torch.float32,
- device=z.device)
- box @= convert_matrix
- return (box, score)
- class IBin(nn.Module):
- stride = None
- export = False
- def __init__(self, nc=80, anchors=(), ch=(), bin_count=21):
- super(IBin, self).__init__()
- self.nc = nc
- self.bin_count = bin_count
- self.w_bin_sigmoid = SigmoidBin(bin_count=self.bin_count, min=0.0, max=4.0)
- self.h_bin_sigmoid = SigmoidBin(bin_count=self.bin_count, min=0.0, max=4.0)
-
- self.no = nc + 3 + \
- self.w_bin_sigmoid.get_length() + self.h_bin_sigmoid.get_length()
-
-
- self.nl = len(anchors)
- self.na = len(anchors[0]) // 2
- self.grid = [torch.zeros(1)] * self.nl
- a = torch.tensor(anchors).float().view(self.nl, -1, 2)
- self.register_buffer('anchors', a)
- self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))
- self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)
-
- self.ia = nn.ModuleList(ImplicitA(x) for x in ch)
- self.im = nn.ModuleList(ImplicitM(self.no * self.na) for _ in ch)
- def forward(self, x):
-
-
- self.w_bin_sigmoid.use_fw_regression = True
- self.h_bin_sigmoid.use_fw_regression = True
-
-
- z = []
- self.training |= self.export
- for i in range(self.nl):
- x[i] = self.m[i](self.ia[i](x[i]))
- x[i] = self.im[i](x[i])
- bs, _, ny, nx = x[i].shape
- x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
- if not self.training:
- 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]) * self.stride[i]
-
-
-
-
- pw = self.w_bin_sigmoid.forward(y[..., 2:24]) * self.anchor_grid[i][..., 0]
- ph = self.h_bin_sigmoid.forward(y[..., 24:46]) * self.anchor_grid[i][..., 1]
-
-
- y[..., 2] = pw
- y[..., 3] = ph
-
- y = torch.cat((y[..., 0:4], y[..., 46:]), dim=-1)
-
- z.append(y.view(bs, -1, y.shape[-1]))
- 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, cfg='yolor-csp-c.yaml', ch=3, nc=None, anchors=None):
- super(Model, self).__init__()
- self.traced = False
- if isinstance(cfg, dict):
- self.yaml = cfg
- else:
- import yaml
- self.yaml_file = Path(cfg).name
- with open(cfg) as f:
- self.yaml = yaml.load(f, Loader=yaml.SafeLoader)
-
- ch = self.yaml['ch'] = self.yaml.get('ch', ch)
- if nc and nc != self.yaml['nc']:
- logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
- self.yaml['nc'] = nc
- if anchors:
- logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
- self.yaml['anchors'] = round(anchors)
- self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])
- self.names = [str(i) for i in range(self.yaml['nc'])]
-
-
- m = self.model[-1]
- if isinstance(m, Detect):
- s = 256
- m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])
- check_anchor_order(m)
- m.anchors /= m.stride.view(-1, 1, 1)
- self.stride = m.stride
- self._initialize_biases()
-
- if isinstance(m, IDetect):
- s = 256
- m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])
- check_anchor_order(m)
- m.anchors /= m.stride.view(-1, 1, 1)
- self.stride = m.stride
- self._initialize_biases()
-
- if isinstance(m, IAuxDetect):
- s = 256
- m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))[:4]])
-
- check_anchor_order(m)
- m.anchors /= m.stride.view(-1, 1, 1)
- self.stride = m.stride
- self._initialize_aux_biases()
-
- if isinstance(m, IBin):
- s = 256
- m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])
- check_anchor_order(m)
- m.anchors /= m.stride.view(-1, 1, 1)
- self.stride = m.stride
- self._initialize_biases_bin()
-
- if isinstance(m, IKeypoint):
- s = 256
- m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])
- check_anchor_order(m)
- m.anchors /= m.stride.view(-1, 1, 1)
- self.stride = m.stride
- self._initialize_biases_kpt()
-
-
- initialize_weights(self)
- self.info()
- logger.info('')
- def forward(self, x, augment=False, profile=False):
- if augment:
- img_size = x.shape[-2:]
- s = [1, 0.83, 0.67]
- f = [None, 3, None]
- y = []
- for si, fi in zip(s, f):
- xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
- yi = self.forward_once(xi)[0]
-
- yi[..., :4] /= si
- if fi == 2:
- yi[..., 1] = img_size[0] - yi[..., 1]
- elif fi == 3:
- yi[..., 0] = img_size[1] - yi[..., 0]
- y.append(yi)
- return torch.cat(y, 1), None
- else:
- return self.forward_once(x, profile)
- def forward_once(self, x, profile=False):
- y, dt = [], []
- for m in self.model:
- if m.f != -1:
- x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]
- if not hasattr(self, 'traced'):
- self.traced=False
- if self.traced:
- if isinstance(m, Detect) or isinstance(m, IDetect) or isinstance(m, IAuxDetect) or isinstance(m, IKeypoint):
- break
- if profile:
- c = isinstance(m, (Detect, IDetect, IAuxDetect, IBin))
- o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0
- for _ in range(10):
- m(x.copy() if c else x)
- t = time_synchronized()
- for _ in range(10):
- m(x.copy() if c else x)
- dt.append((time_synchronized() - t) * 100)
- print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))
- x = m(x)
-
- y.append(x if m.i in self.save else None)
- if profile:
- print('%.1fms total' % sum(dt))
- return x
- def _initialize_biases(self, cf=None):
-
-
- m = self.model[-1]
- for mi, s in zip(m.m, m.stride):
- b = mi.bias.view(m.na, -1)
- b.data[:, 4] += math.log(8 / (640 / s) ** 2)
- b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())
- mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
- def _initialize_aux_biases(self, cf=None):
-
-
- m = self.model[-1]
- for mi, mi2, s in zip(m.m, m.m2, m.stride):
- b = mi.bias.view(m.na, -1)
- b.data[:, 4] += math.log(8 / (640 / s) ** 2)
- b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())
- mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
- b2 = mi2.bias.view(m.na, -1)
- b2.data[:, 4] += math.log(8 / (640 / s) ** 2)
- b2.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())
- mi2.bias = torch.nn.Parameter(b2.view(-1), requires_grad=True)
- def _initialize_biases_bin(self, cf=None):
-
-
- m = self.model[-1]
- bc = m.bin_count
- for mi, s in zip(m.m, m.stride):
- b = mi.bias.view(m.na, -1)
- old = b[:, (0,1,2,bc+3)].data
- obj_idx = 2*bc+4
- b[:, :obj_idx].data += math.log(0.6 / (bc + 1 - 0.99))
- b[:, obj_idx].data += math.log(8 / (640 / s) ** 2)
- b[:, (obj_idx+1):].data += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())
- b[:, (0,1,2,bc+3)].data = old
- mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
- def _initialize_biases_kpt(self, cf=None):
-
-
- m = self.model[-1]
- for mi, s in zip(m.m, m.stride):
- b = mi.bias.view(m.na, -1)
- b.data[:, 4] += math.log(8 / (640 / s) ** 2)
- b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())
- mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
- def _print_biases(self):
- m = self.model[-1]
- for mi in m.m:
- b = mi.bias.detach().view(m.na, -1).T
- print(('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
-
-
-
-
- def fuse(self):
- print('Fusing layers... ')
- for m in self.model.modules():
- if isinstance(m, RepConv):
-
- m.fuse_repvgg_block()
- elif isinstance(m, RepConv_OREPA):
-
- m.switch_to_deploy()
- elif type(m) is Conv and hasattr(m, 'bn'):
- m.conv = fuse_conv_and_bn(m.conv, m.bn)
- delattr(m, 'bn')
- m.forward = m.fuseforward
- elif isinstance(m, (IDetect, IAuxDetect)):
- m.fuse()
- m.forward = m.fuseforward
- self.info()
- return self
- def nms(self, mode=True):
- present = type(self.model[-1]) is NMS
- if mode and not present:
- print('Adding NMS... ')
- m = NMS()
- m.f = -1
- m.i = self.model[-1].i + 1
- self.model.add_module(name='%s' % m.i, module=m)
- self.eval()
- elif not mode and present:
- print('Removing NMS... ')
- self.model = self.model[:-1]
- return self
- def autoshape(self):
- print('Adding autoShape... ')
- m = autoShape(self)
- copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=())
- return m
- def info(self, verbose=False, img_size=640):
- model_info(self, verbose, img_size)
- def parse_model(d, ch):
- logger.info('\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
- no = na * (nc + 5)
- layers, save, c2 = [], [], ch[-1]
- for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):
- m = eval(m) if isinstance(m, str) else m
- for j, a in enumerate(args):
- try:
- args[j] = eval(a) if isinstance(a, str) else a
- except:
- pass
- n = max(round(n * gd), 1) if n > 1 else n
- if m in [nn.Conv2d, Conv, RobustConv, RobustConv2, DWConv, GhostConv, RepConv, RepConv_OREPA, DownC,
- SPP, SPPF, SPPCSPC, GhostSPPCSPC, MixConv2d, Focus, Stem, GhostStem, CrossConv,
- Bottleneck, BottleneckCSPA, BottleneckCSPB, BottleneckCSPC,
- RepBottleneck, RepBottleneckCSPA, RepBottleneckCSPB, RepBottleneckCSPC,
- Res, ResCSPA, ResCSPB, ResCSPC,
- RepRes, RepResCSPA, RepResCSPB, RepResCSPC,
- ResX, ResXCSPA, ResXCSPB, ResXCSPC,
- RepResX, RepResXCSPA, RepResXCSPB, RepResXCSPC,
- Ghost, GhostCSPA, GhostCSPB, GhostCSPC,
- SwinTransformerBlock, STCSPA, STCSPB, STCSPC,
- SwinTransformer2Block, ST2CSPA, ST2CSPB, ST2CSPC]:
- c1, c2 = ch[f], args[0]
- if c2 != no:
- c2 = make_divisible(c2 * gw, 8)
- args = [c1, c2, *args[1:]]
- if m in [DownC, SPPCSPC, GhostSPPCSPC,
- BottleneckCSPA, BottleneckCSPB, BottleneckCSPC,
- RepBottleneckCSPA, RepBottleneckCSPB, RepBottleneckCSPC,
- ResCSPA, ResCSPB, ResCSPC,
- RepResCSPA, RepResCSPB, RepResCSPC,
- ResXCSPA, ResXCSPB, ResXCSPC,
- RepResXCSPA, RepResXCSPB, RepResXCSPC,
- GhostCSPA, GhostCSPB, GhostCSPC,
- STCSPA, STCSPB, STCSPC,
- ST2CSPA, ST2CSPB, ST2CSPC]:
- 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 Chuncat:
- c2 = sum([ch[x] for x in f])
- elif m is Shortcut:
- c2 = ch[f[0]]
- elif m is Foldcut:
- c2 = ch[f] // 2
- elif m in [Detect, IDetect, IAuxDetect, IBin, IKeypoint]:
- args.append([ch[x] for x in f])
- if isinstance(args[1], int):
- args[1] = [list(range(args[1] * 2))] * len(f)
- elif m is ReOrg:
- c2 = ch[f] * 4
- elif m is Contract:
- c2 = ch[f] * args[0] ** 2
- elif m is Expand:
- c2 = ch[f] // args[0] ** 2
- else:
- c2 = ch[f]
- m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args)
- t = str(m)[8:-2].replace('__main__.', '')
- np = sum([x.numel() for x in m_.parameters()])
- m_.i, m_.f, m_.type, m_.np = i, f, t, np
- logger.info('%3s%18s%3s%10.0f %-40s%-30s' % (i, f, n, np, t, args))
- save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)
- layers.append(m_)
- if i == 0:
- ch = []
- ch.append(c2)
- return nn.Sequential(*layers), sorted(save)
- if __name__ == '__main__':
- parser = argparse.ArgumentParser()
- parser.add_argument('--cfg', type=str, default='yolor-csp-c.yaml', help='model.yaml')
- parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
- parser.add_argument('--profile', action='store_true', help='profile model speed')
- opt = parser.parse_args()
- opt.cfg = check_file(opt.cfg)
- set_logging()
- device = select_device(opt.device)
-
- model = Model(opt.cfg).to(device)
- model.train()
-
- if opt.profile:
- img = torch.rand(1, 3, 640, 640).to(device)
- y = model(img, profile=True)
-
-
-
-
-
-
-
-
-
|