Spaces:
Runtime error
Runtime error
| #!/usr/bin/env python3 | |
| # -*- coding:utf-8 -*- | |
| import warnings | |
| from pathlib import Path | |
| import numpy as np | |
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| from yolov6.layers.dbb_transforms import * | |
| class SiLU(nn.Module): | |
| '''Activation of SiLU''' | |
| def forward(x): | |
| return x * torch.sigmoid(x) | |
| class Conv(nn.Module): | |
| '''Normal Conv with SiLU activation''' | |
| def __init__(self, in_channels, out_channels, kernel_size, stride, groups=1, bias=False): | |
| super().__init__() | |
| padding = kernel_size // 2 | |
| self.conv = nn.Conv2d( | |
| in_channels, | |
| out_channels, | |
| kernel_size=kernel_size, | |
| stride=stride, | |
| padding=padding, | |
| groups=groups, | |
| bias=bias, | |
| ) | |
| self.bn = nn.BatchNorm2d(out_channels) | |
| self.act = nn.SiLU() | |
| def forward(self, x): | |
| return self.act(self.bn(self.conv(x))) | |
| def forward_fuse(self, x): | |
| return self.act(self.conv(x)) | |
| class SimConv(nn.Module): | |
| '''Normal Conv with ReLU activation''' | |
| def __init__(self, in_channels, out_channels, kernel_size, stride, groups=1, bias=False): | |
| super().__init__() | |
| padding = kernel_size // 2 | |
| self.conv = nn.Conv2d( | |
| in_channels, | |
| out_channels, | |
| kernel_size=kernel_size, | |
| stride=stride, | |
| padding=padding, | |
| groups=groups, | |
| bias=bias, | |
| ) | |
| self.bn = nn.BatchNorm2d(out_channels) | |
| self.act = nn.ReLU() | |
| def forward(self, x): | |
| return self.act(self.bn(self.conv(x))) | |
| def forward_fuse(self, x): | |
| return self.act(self.conv(x)) | |
| class SimSPPF(nn.Module): | |
| '''Simplified SPPF with ReLU activation''' | |
| def __init__(self, in_channels, out_channels, kernel_size=5): | |
| super().__init__() | |
| c_ = in_channels // 2 # hidden channels | |
| self.cv1 = SimConv(in_channels, c_, 1, 1) | |
| self.cv2 = SimConv(c_ * 4, out_channels, 1, 1) | |
| self.m = nn.MaxPool2d(kernel_size=kernel_size, stride=1, padding=kernel_size // 2) | |
| def forward(self, x): | |
| x = self.cv1(x) | |
| with warnings.catch_warnings(): | |
| warnings.simplefilter('ignore') | |
| y1 = self.m(x) | |
| y2 = self.m(y1) | |
| return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1)) | |
| class Transpose(nn.Module): | |
| '''Normal Transpose, default for upsampling''' | |
| def __init__(self, in_channels, out_channels, kernel_size=2, stride=2): | |
| super().__init__() | |
| self.upsample_transpose = torch.nn.ConvTranspose2d( | |
| in_channels=in_channels, | |
| out_channels=out_channels, | |
| kernel_size=kernel_size, | |
| stride=stride, | |
| bias=True | |
| ) | |
| def forward(self, x): | |
| return self.upsample_transpose(x) | |
| class Concat(nn.Module): | |
| def __init__(self, dimension=1): | |
| super().__init__() | |
| self.d = dimension | |
| def forward(self, x): | |
| return torch.cat(x, self.d) | |
| def conv_bn(in_channels, out_channels, kernel_size, stride, padding, groups=1): | |
| '''Basic cell for rep-style block, including conv and bn''' | |
| result = nn.Sequential() | |
| result.add_module('conv', nn.Conv2d(in_channels=in_channels, out_channels=out_channels, | |
| kernel_size=kernel_size, stride=stride, padding=padding, groups=groups, bias=False)) | |
| result.add_module('bn', nn.BatchNorm2d(num_features=out_channels)) | |
| return result | |
| class RepBlock(nn.Module): | |
| ''' | |
| RepBlock is a stage block with rep-style basic block | |
| ''' | |
| def __init__(self, in_channels, out_channels, n=1): | |
| super().__init__() | |
| self.conv1 = RepVGGBlock(in_channels, out_channels) | |
| self.block = nn.Sequential(*(RepVGGBlock(out_channels, out_channels) for _ in range(n - 1))) if n > 1 else None | |
| def forward(self, x): | |
| x = self.conv1(x) | |
| if self.block is not None: | |
| x = self.block(x) | |
| return x | |
| class RepVGGBlock(nn.Module): | |
| '''RepVGGBlock is a basic rep-style block, including training and deploy status | |
| This code is based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py | |
| ''' | |
| def __init__(self, in_channels, out_channels, kernel_size=3, | |
| stride=1, padding=1, dilation=1, groups=1, padding_mode='zeros', deploy=False, use_se=False): | |
| super(RepVGGBlock, self).__init__() | |
| """ Initialization of the class. | |
| Args: | |
| in_channels (int): Number of channels in the input image | |
| out_channels (int): Number of channels produced by the convolution | |
| kernel_size (int or tuple): Size of the convolving kernel | |
| stride (int or tuple, optional): Stride of the convolution. Default: 1 | |
| padding (int or tuple, optional): Zero-padding added to both sides of | |
| the input. Default: 1 | |
| dilation (int or tuple, optional): Spacing between kernel elements. Default: 1 | |
| groups (int, optional): Number of blocked connections from input | |
| channels to output channels. Default: 1 | |
| padding_mode (string, optional): Default: 'zeros' | |
| deploy: Whether to be deploy status or training status. Default: False | |
| use_se: Whether to use se. Default: False | |
| """ | |
| self.deploy = deploy | |
| self.groups = groups | |
| self.in_channels = in_channels | |
| self.out_channels = out_channels | |
| assert kernel_size == 3 | |
| assert padding == 1 | |
| padding_11 = padding - kernel_size // 2 | |
| self.nonlinearity = nn.ReLU() | |
| if use_se: | |
| raise NotImplementedError("se block not supported yet") | |
| else: | |
| self.se = nn.Identity() | |
| if deploy: | |
| self.rbr_reparam = nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, | |
| padding=padding, dilation=dilation, groups=groups, bias=True, padding_mode=padding_mode) | |
| else: | |
| self.rbr_identity = nn.BatchNorm2d(num_features=in_channels) if out_channels == in_channels and stride == 1 else None | |
| self.rbr_dense = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding, groups=groups) | |
| self.rbr_1x1 = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=stride, padding=padding_11, groups=groups) | |
| def forward(self, inputs): | |
| '''Forward process''' | |
| if hasattr(self, 'rbr_reparam'): | |
| return self.nonlinearity(self.se(self.rbr_reparam(inputs))) | |
| if self.rbr_identity is None: | |
| id_out = 0 | |
| else: | |
| id_out = self.rbr_identity(inputs) | |
| return self.nonlinearity(self.se(self.rbr_dense(inputs) + self.rbr_1x1(inputs) + id_out)) | |
| def get_equivalent_kernel_bias(self): | |
| kernel3x3, bias3x3 = self._fuse_bn_tensor(self.rbr_dense) | |
| kernel1x1, bias1x1 = self._fuse_bn_tensor(self.rbr_1x1) | |
| kernelid, biasid = self._fuse_bn_tensor(self.rbr_identity) | |
| return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid | |
| def _pad_1x1_to_3x3_tensor(self, kernel1x1): | |
| if kernel1x1 is None: | |
| return 0 | |
| else: | |
| return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1]) | |
| def _fuse_bn_tensor(self, branch): | |
| if branch is None: | |
| return 0, 0 | |
| if isinstance(branch, nn.Sequential): | |
| kernel = branch.conv.weight | |
| running_mean = branch.bn.running_mean | |
| running_var = branch.bn.running_var | |
| gamma = branch.bn.weight | |
| beta = branch.bn.bias | |
| eps = branch.bn.eps | |
| else: | |
| assert isinstance(branch, nn.BatchNorm2d) | |
| if not hasattr(self, 'id_tensor'): | |
| input_dim = self.in_channels // self.groups | |
| kernel_value = np.zeros((self.in_channels, input_dim, 3, 3), dtype=np.float32) | |
| for i in range(self.in_channels): | |
| kernel_value[i, i % input_dim, 1, 1] = 1 | |
| self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device) | |
| kernel = self.id_tensor | |
| running_mean = branch.running_mean | |
| running_var = branch.running_var | |
| gamma = branch.weight | |
| beta = branch.bias | |
| eps = branch.eps | |
| std = (running_var + eps).sqrt() | |
| t = (gamma / std).reshape(-1, 1, 1, 1) | |
| return kernel * t, beta - running_mean * gamma / std | |
| def switch_to_deploy(self): | |
| if hasattr(self, 'rbr_reparam'): | |
| return | |
| kernel, bias = self.get_equivalent_kernel_bias() | |
| self.rbr_reparam = nn.Conv2d(in_channels=self.rbr_dense.conv.in_channels, out_channels=self.rbr_dense.conv.out_channels, | |
| kernel_size=self.rbr_dense.conv.kernel_size, stride=self.rbr_dense.conv.stride, | |
| padding=self.rbr_dense.conv.padding, dilation=self.rbr_dense.conv.dilation, groups=self.rbr_dense.conv.groups, bias=True) | |
| self.rbr_reparam.weight.data = kernel | |
| self.rbr_reparam.bias.data = bias | |
| for para in self.parameters(): | |
| para.detach_() | |
| self.__delattr__('rbr_dense') | |
| self.__delattr__('rbr_1x1') | |
| if hasattr(self, 'rbr_identity'): | |
| self.__delattr__('rbr_identity') | |
| if hasattr(self, 'id_tensor'): | |
| self.__delattr__('id_tensor') | |
| self.deploy = True | |
| def conv_bn_v2(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, | |
| padding_mode='zeros'): | |
| conv_layer = nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, | |
| stride=stride, padding=padding, dilation=dilation, groups=groups, | |
| bias=False, padding_mode=padding_mode) | |
| bn_layer = nn.BatchNorm2d(num_features=out_channels, affine=True) | |
| se = nn.Sequential() | |
| se.add_module('conv', conv_layer) | |
| se.add_module('bn', bn_layer) | |
| return se | |
| class IdentityBasedConv1x1(nn.Conv2d): | |
| def __init__(self, channels, groups=1): | |
| super(IdentityBasedConv1x1, self).__init__(in_channels=channels, out_channels=channels, kernel_size=1, stride=1, padding=0, groups=groups, bias=False) | |
| assert channels % groups == 0 | |
| input_dim = channels // groups | |
| id_value = np.zeros((channels, input_dim, 1, 1)) | |
| for i in range(channels): | |
| id_value[i, i % input_dim, 0, 0] = 1 | |
| self.id_tensor = torch.from_numpy(id_value).type_as(self.weight) | |
| nn.init.zeros_(self.weight) | |
| def forward(self, input): | |
| kernel = self.weight + self.id_tensor.to(self.weight.device) | |
| result = F.conv2d(input, kernel, None, stride=1, padding=0, dilation=self.dilation, groups=self.groups) | |
| return result | |
| def get_actual_kernel(self): | |
| return self.weight + self.id_tensor.to(self.weight.device) | |
| class BNAndPadLayer(nn.Module): | |
| def __init__(self, | |
| pad_pixels, | |
| num_features, | |
| eps=1e-5, | |
| momentum=0.1, | |
| affine=True, | |
| track_running_stats=True): | |
| super(BNAndPadLayer, self).__init__() | |
| self.bn = nn.BatchNorm2d(num_features, eps, momentum, affine, track_running_stats) | |
| self.pad_pixels = pad_pixels | |
| def forward(self, input): | |
| output = self.bn(input) | |
| if self.pad_pixels > 0: | |
| if self.bn.affine: | |
| pad_values = self.bn.bias.detach() - self.bn.running_mean * self.bn.weight.detach() / torch.sqrt(self.bn.running_var + self.bn.eps) | |
| else: | |
| pad_values = - self.bn.running_mean / torch.sqrt(self.bn.running_var + self.bn.eps) | |
| output = F.pad(output, [self.pad_pixels] * 4) | |
| pad_values = pad_values.view(1, -1, 1, 1) | |
| output[:, :, 0:self.pad_pixels, :] = pad_values | |
| output[:, :, -self.pad_pixels:, :] = pad_values | |
| output[:, :, :, 0:self.pad_pixels] = pad_values | |
| output[:, :, :, -self.pad_pixels:] = pad_values | |
| return output | |
| def bn_weight(self): | |
| return self.bn.weight | |
| def bn_bias(self): | |
| return self.bn.bias | |
| def running_mean(self): | |
| return self.bn.running_mean | |
| def running_var(self): | |
| return self.bn.running_var | |
| def eps(self): | |
| return self.bn.eps | |
| class DBBBlock(nn.Module): | |
| ''' | |
| RepBlock is a stage block with rep-style basic block | |
| ''' | |
| def __init__(self, in_channels, out_channels, n=1): | |
| super().__init__() | |
| self.conv1 = DiverseBranchBlock(in_channels, out_channels) | |
| self.block = nn.Sequential(*(DiverseBranchBlock(out_channels, out_channels) for _ in range(n - 1))) if n > 1 else None | |
| def forward(self, x): | |
| x = self.conv1(x) | |
| if self.block is not None: | |
| x = self.block(x) | |
| return x | |
| class DiverseBranchBlock(nn.Module): | |
| def __init__(self, in_channels, out_channels, kernel_size=3, | |
| stride=1, padding=1, dilation=1, groups=1, | |
| internal_channels_1x1_3x3=None, | |
| deploy=False, nonlinear=nn.ReLU(), single_init=False): | |
| super(DiverseBranchBlock, self).__init__() | |
| self.deploy = deploy | |
| if nonlinear is None: | |
| self.nonlinear = nn.Identity() | |
| else: | |
| self.nonlinear = nonlinear | |
| self.kernel_size = kernel_size | |
| self.out_channels = out_channels | |
| self.groups = groups | |
| assert padding == kernel_size // 2 | |
| if deploy: | |
| self.dbb_reparam = nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, | |
| padding=padding, dilation=dilation, groups=groups, bias=True) | |
| else: | |
| self.dbb_origin = conv_bn_v2(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups=groups) | |
| self.dbb_avg = nn.Sequential() | |
| if groups < out_channels: | |
| self.dbb_avg.add_module('conv', | |
| nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=1, | |
| stride=1, padding=0, groups=groups, bias=False)) | |
| self.dbb_avg.add_module('bn', BNAndPadLayer(pad_pixels=padding, num_features=out_channels)) | |
| self.dbb_avg.add_module('avg', nn.AvgPool2d(kernel_size=kernel_size, stride=stride, padding=0)) | |
| self.dbb_1x1 = conv_bn_v2(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=stride, | |
| padding=0, groups=groups) | |
| else: | |
| self.dbb_avg.add_module('avg', nn.AvgPool2d(kernel_size=kernel_size, stride=stride, padding=padding)) | |
| self.dbb_avg.add_module('avgbn', nn.BatchNorm2d(out_channels)) | |
| if internal_channels_1x1_3x3 is None: | |
| internal_channels_1x1_3x3 = in_channels if groups < out_channels else 2 * in_channels # For mobilenet, it is better to have 2X internal channels | |
| self.dbb_1x1_kxk = nn.Sequential() | |
| if internal_channels_1x1_3x3 == in_channels: | |
| self.dbb_1x1_kxk.add_module('idconv1', IdentityBasedConv1x1(channels=in_channels, groups=groups)) | |
| else: | |
| self.dbb_1x1_kxk.add_module('conv1', nn.Conv2d(in_channels=in_channels, out_channels=internal_channels_1x1_3x3, | |
| kernel_size=1, stride=1, padding=0, groups=groups, bias=False)) | |
| self.dbb_1x1_kxk.add_module('bn1', BNAndPadLayer(pad_pixels=padding, num_features=internal_channels_1x1_3x3, affine=True)) | |
| self.dbb_1x1_kxk.add_module('conv2', nn.Conv2d(in_channels=internal_channels_1x1_3x3, out_channels=out_channels, | |
| kernel_size=kernel_size, stride=stride, padding=0, groups=groups, bias=False)) | |
| self.dbb_1x1_kxk.add_module('bn2', nn.BatchNorm2d(out_channels)) | |
| # The experiments reported in the paper used the default initialization of bn.weight (all as 1). But changing the initialization may be useful in some cases. | |
| if single_init: | |
| # Initialize the bn.weight of dbb_origin as 1 and others as 0. This is not the default setting. | |
| self.single_init() | |
| def get_equivalent_kernel_bias(self): | |
| k_origin, b_origin = transI_fusebn(self.dbb_origin.conv.weight, self.dbb_origin.bn) | |
| if hasattr(self, 'dbb_1x1'): | |
| k_1x1, b_1x1 = transI_fusebn(self.dbb_1x1.conv.weight, self.dbb_1x1.bn) | |
| k_1x1 = transVI_multiscale(k_1x1, self.kernel_size) | |
| else: | |
| k_1x1, b_1x1 = 0, 0 | |
| if hasattr(self.dbb_1x1_kxk, 'idconv1'): | |
| k_1x1_kxk_first = self.dbb_1x1_kxk.idconv1.get_actual_kernel() | |
| else: | |
| k_1x1_kxk_first = self.dbb_1x1_kxk.conv1.weight | |
| k_1x1_kxk_first, b_1x1_kxk_first = transI_fusebn(k_1x1_kxk_first, self.dbb_1x1_kxk.bn1) | |
| k_1x1_kxk_second, b_1x1_kxk_second = transI_fusebn(self.dbb_1x1_kxk.conv2.weight, self.dbb_1x1_kxk.bn2) | |
| k_1x1_kxk_merged, b_1x1_kxk_merged = transIII_1x1_kxk(k_1x1_kxk_first, b_1x1_kxk_first, k_1x1_kxk_second, b_1x1_kxk_second, groups=self.groups) | |
| k_avg = transV_avg(self.out_channels, self.kernel_size, self.groups) | |
| k_1x1_avg_second, b_1x1_avg_second = transI_fusebn(k_avg.to(self.dbb_avg.avgbn.weight.device), self.dbb_avg.avgbn) | |
| if hasattr(self.dbb_avg, 'conv'): | |
| k_1x1_avg_first, b_1x1_avg_first = transI_fusebn(self.dbb_avg.conv.weight, self.dbb_avg.bn) | |
| k_1x1_avg_merged, b_1x1_avg_merged = transIII_1x1_kxk(k_1x1_avg_first, b_1x1_avg_first, k_1x1_avg_second, b_1x1_avg_second, groups=self.groups) | |
| else: | |
| k_1x1_avg_merged, b_1x1_avg_merged = k_1x1_avg_second, b_1x1_avg_second | |
| return transII_addbranch((k_origin, k_1x1, k_1x1_kxk_merged, k_1x1_avg_merged), (b_origin, b_1x1, b_1x1_kxk_merged, b_1x1_avg_merged)) | |
| def switch_to_deploy(self): | |
| if hasattr(self, 'dbb_reparam'): | |
| return | |
| kernel, bias = self.get_equivalent_kernel_bias() | |
| self.dbb_reparam = nn.Conv2d(in_channels=self.dbb_origin.conv.in_channels, out_channels=self.dbb_origin.conv.out_channels, | |
| kernel_size=self.dbb_origin.conv.kernel_size, stride=self.dbb_origin.conv.stride, | |
| padding=self.dbb_origin.conv.padding, dilation=self.dbb_origin.conv.dilation, groups=self.dbb_origin.conv.groups, bias=True) | |
| self.dbb_reparam.weight.data = kernel | |
| self.dbb_reparam.bias.data = bias | |
| for para in self.parameters(): | |
| para.detach_() | |
| self.__delattr__('dbb_origin') | |
| self.__delattr__('dbb_avg') | |
| if hasattr(self, 'dbb_1x1'): | |
| self.__delattr__('dbb_1x1') | |
| self.__delattr__('dbb_1x1_kxk') | |
| def forward(self, inputs): | |
| if hasattr(self, 'dbb_reparam'): | |
| return self.nonlinear(self.dbb_reparam(inputs)) | |
| out = self.dbb_origin(inputs) | |
| if hasattr(self, 'dbb_1x1'): | |
| out += self.dbb_1x1(inputs) | |
| out += self.dbb_avg(inputs) | |
| out += self.dbb_1x1_kxk(inputs) | |
| return self.nonlinear(out) | |
| def init_gamma(self, gamma_value): | |
| if hasattr(self, "dbb_origin"): | |
| torch.nn.init.constant_(self.dbb_origin.bn.weight, gamma_value) | |
| if hasattr(self, "dbb_1x1"): | |
| torch.nn.init.constant_(self.dbb_1x1.bn.weight, gamma_value) | |
| if hasattr(self, "dbb_avg"): | |
| torch.nn.init.constant_(self.dbb_avg.avgbn.weight, gamma_value) | |
| if hasattr(self, "dbb_1x1_kxk"): | |
| torch.nn.init.constant_(self.dbb_1x1_kxk.bn2.weight, gamma_value) | |
| def single_init(self): | |
| self.init_gamma(0.0) | |
| if hasattr(self, "dbb_origin"): | |
| torch.nn.init.constant_(self.dbb_origin.bn.weight, 1.0) | |
| class DetectBackend(nn.Module): | |
| def __init__(self, weights='yolov6s.pt', device=None, dnn=True): | |
| super().__init__() | |
| assert isinstance(weights, str) and Path(weights).suffix == '.pt', f'{Path(weights).suffix} format is not supported.' | |
| from yolov6.utils.checkpoint import load_checkpoint | |
| model = load_checkpoint(weights, map_location=device) | |
| stride = int(model.stride.max()) | |
| self.__dict__.update(locals()) # assign all variables to self | |
| def forward(self, im, val=False): | |
| y = self.model(im) | |
| if isinstance(y, np.ndarray): | |
| y = torch.tensor(y, device=self.device) | |
| return y | |