lichen/detecttracking
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add yolo v10 and modify pipeline

Browse Source
This commit is contained in:
王庆刚
2025-03-28 13:19:54 +08:00
parent 183299c06b
commit 798c596acc
471 changed files with 19109 additions and 7342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

107
ultralytics/nn/modules/conv.py
View File

@ -1,7 +1,5 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
"""
Convolution modules
"""
"""Convolution modules."""
import math
@ -9,8 +7,21 @@ import numpy as np
import torch
import torch.nn as nn
__all__ = ('Conv', 'Conv2', 'LightConv', 'DWConv', 'DWConvTranspose2d', 'ConvTranspose', 'Focus', 'GhostConv',
'ChannelAttention', 'SpatialAttention', 'CBAM', 'Concat', 'RepConv')
__all__ = (
"Conv",
"Conv2",
"LightConv",
"DWConv",
"DWConvTranspose2d",
"ConvTranspose",
"Focus",
"GhostConv",
"ChannelAttention",
"SpatialAttention",
"CBAM",
"Concat",
"RepConv",
)
def autopad(k, p=None, d=1): # kernel, padding, dilation
@ -24,6 +35,7 @@ def autopad(k, p=None, d=1): # kernel, padding, dilation
class Conv(nn.Module):
"""Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
default_act = nn.SiLU() # default activation
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
@ -62,14 +74,16 @@ class Conv2(Conv):
"""Fuse parallel convolutions."""
w = torch.zeros_like(self.conv.weight.data)
i = [x // 2 for x in w.shape[2:]]
w[:, :, i[0]:i[0] + 1, i[1]:i[1] + 1] = self.cv2.weight.data.clone()
w[:, :, i[0] : i[0] + 1, i[1] : i[1] + 1] = self.cv2.weight.data.clone()
self.conv.weight.data += w
self.__delattr__('cv2')
self.__delattr__("cv2")
self.forward = self.forward_fuse
class LightConv(nn.Module):
"""Light convolution with args(ch_in, ch_out, kernel).
"""
Light convolution with args(ch_in, ch_out, kernel).
https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py
"""
@ -88,6 +102,7 @@ class DWConv(Conv):
"""Depth-wise convolution."""
def __init__(self, c1, c2, k=1, s=1, d=1, act=True): # ch_in, ch_out, kernel, stride, dilation, activation
"""Initialize Depth-wise convolution with given parameters."""
super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)
@ -95,11 +110,13 @@ class DWConvTranspose2d(nn.ConvTranspose2d):
"""Depth-wise transpose convolution."""
def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0): # ch_in, ch_out, kernel, stride, padding, padding_out
"""Initialize DWConvTranspose2d class with given parameters."""
super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))
class ConvTranspose(nn.Module):
"""Convolution transpose 2d layer."""
default_act = nn.SiLU() # default activation
def __init__(self, c1, c2, k=2, s=2, p=0, bn=True, act=True):
@ -121,12 +138,18 @@ class ConvTranspose(nn.Module):
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
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):
"""Initializes Focus object with user defined channel, convolution, padding, group and activation values."""
super().__init__()
self.conv = Conv(c1 * 4, c2, k, s, p, g, act=act)
# self.contract = Contract(gain=2)
def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2)
def forward(self, x):
"""
Applies convolution to concatenated tensor and returns the output.
Input shape is (b,c,w,h) and output shape is (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))
# return self.conv(self.contract(x))
@ -134,7 +157,10 @@ class Focus(nn.Module):
class GhostConv(nn.Module):
"""Ghost Convolution https://github.com/huawei-noah/ghostnet."""
def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups
def __init__(self, c1, c2, k=1, s=1, g=1, act=True):
"""Initializes the GhostConv object with input channels, output channels, kernel size, stride, groups and
activation.
"""
super().__init__()
c_ = c2 // 2 # hidden channels
self.cv1 = Conv(c1, c_, k, s, None, g, act=act)
@ -148,12 +174,16 @@ class GhostConv(nn.Module):
class RepConv(nn.Module):
"""
RepConv is a basic rep-style block, including training and deploy status. This module is used in RT-DETR.
RepConv is a basic rep-style block, including training and deploy status.
This module is used in RT-DETR.
Based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py
"""
default_act = nn.SiLU() # default activation
def __init__(self, c1, c2, k=3, s=1, p=1, g=1, d=1, act=True, bn=False, deploy=False):
"""Initializes Light Convolution layer with inputs, outputs & optional activation function."""
super().__init__()
assert k == 3 and p == 1
self.g = g
@ -166,27 +196,30 @@ class RepConv(nn.Module):
self.conv2 = Conv(c1, c2, 1, s, p=(p - k // 2), g=g, act=False)
def forward_fuse(self, x):
"""Forward process"""
"""Forward process."""
return self.act(self.conv(x))
def forward(self, x):
"""Forward process"""
"""Forward process."""
id_out = 0 if self.bn is None else self.bn(x)
return self.act(self.conv1(x) + self.conv2(x) + id_out)
def get_equivalent_kernel_bias(self):
"""Returns equivalent kernel and bias by adding 3x3 kernel, 1x1 kernel and identity kernel with their biases."""
kernel3x3, bias3x3 = self._fuse_bn_tensor(self.conv1)
kernel1x1, bias1x1 = self._fuse_bn_tensor(self.conv2)
kernelid, biasid = self._fuse_bn_tensor(self.bn)
return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid
def _pad_1x1_to_3x3_tensor(self, kernel1x1):
"""Pads a 1x1 tensor to a 3x3 tensor."""
if kernel1x1 is None:
return 0
else:
return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])
def _fuse_bn_tensor(self, branch):
"""Generates appropriate kernels and biases for convolution by fusing branches of the neural network."""
if branch is None:
return 0, 0
if isinstance(branch, Conv):
@ -197,7 +230,7 @@ class RepConv(nn.Module):
beta = branch.bn.bias
eps = branch.bn.eps
elif isinstance(branch, nn.BatchNorm2d):
if not hasattr(self, 'id_tensor'):
if not hasattr(self, "id_tensor"):
input_dim = self.c1 // self.g
kernel_value = np.zeros((self.c1, input_dim, 3, 3), dtype=np.float32)
for i in range(self.c1):
@ -214,41 +247,46 @@ class RepConv(nn.Module):
return kernel * t, beta - running_mean * gamma / std
def fuse_convs(self):
if hasattr(self, 'conv'):
"""Combines two convolution layers into a single layer and removes unused attributes from the class."""
if hasattr(self, "conv"):
return
kernel, bias = self.get_equivalent_kernel_bias()
self.conv = nn.Conv2d(in_channels=self.conv1.conv.in_channels,
out_channels=self.conv1.conv.out_channels,
kernel_size=self.conv1.conv.kernel_size,
stride=self.conv1.conv.stride,
padding=self.conv1.conv.padding,
dilation=self.conv1.conv.dilation,
groups=self.conv1.conv.groups,
bias=True).requires_grad_(False)
self.conv = nn.Conv2d(
in_channels=self.conv1.conv.in_channels,
out_channels=self.conv1.conv.out_channels,
kernel_size=self.conv1.conv.kernel_size,
stride=self.conv1.conv.stride,
padding=self.conv1.conv.padding,
dilation=self.conv1.conv.dilation,
groups=self.conv1.conv.groups,
bias=True,
).requires_grad_(False)
self.conv.weight.data = kernel
self.conv.bias.data = bias
for para in self.parameters():
para.detach_()
self.__delattr__('conv1')
self.__delattr__('conv2')
if hasattr(self, 'nm'):
self.__delattr__('nm')
if hasattr(self, 'bn'):
self.__delattr__('bn')
if hasattr(self, 'id_tensor'):
self.__delattr__('id_tensor')
self.__delattr__("conv1")
self.__delattr__("conv2")
if hasattr(self, "nm"):
self.__delattr__("nm")
if hasattr(self, "bn"):
self.__delattr__("bn")
if hasattr(self, "id_tensor"):
self.__delattr__("id_tensor")
class ChannelAttention(nn.Module):
"""Channel-attention module https://github.com/open-mmlab/mmdetection/tree/v3.0.0rc1/configs/rtmdet."""
def __init__(self, channels: int) -> None:
"""Initializes the class and sets the basic configurations and instance variables required."""
super().__init__()
self.pool = nn.AdaptiveAvgPool2d(1)
self.fc = nn.Conv2d(channels, channels, 1, 1, 0, bias=True)
self.act = nn.Sigmoid()
def forward(self, x: torch.Tensor) -> torch.Tensor:
"""Applies forward pass using activation on convolutions of the input, optionally using batch normalization."""
return x * self.act(self.fc(self.pool(x)))
@ -258,7 +296,7 @@ class SpatialAttention(nn.Module):
def __init__(self, kernel_size=7):
"""Initialize Spatial-attention module with kernel size argument."""
super().__init__()
assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
assert kernel_size in (3, 7), "kernel size must be 3 or 7"
padding = 3 if kernel_size == 7 else 1
self.cv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
self.act = nn.Sigmoid()
@ -271,7 +309,8 @@ class SpatialAttention(nn.Module):
class CBAM(nn.Module):
"""Convolutional Block Attention Module."""
def __init__(self, c1, kernel_size=7): # ch_in, kernels
def __init__(self, c1, kernel_size=7):
"""Initialize CBAM with given input channel (c1) and kernel size."""
super().__init__()
self.channel_attention = ChannelAttention(c1)
self.spatial_attention = SpatialAttention(kernel_size)