File size: 7,812 Bytes
ab35335 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 |
#!/usr/bin/env python3
# -*- coding:utf-8 -*-
# Copyright (c) Megvii Inc. All rights reserved.
import torch
import torch.nn as nn
from .network_blocks import BaseConv, DWConv
_TORCH_VER = [int(x) for x in torch.__version__.split(".")[:2]]
def meshgrid(*tensors):
"""
Copied from YOLOX/yolox/utils/compat.py
"""
if _TORCH_VER >= [1, 10]:
return torch.meshgrid(*tensors, indexing="ij")
else:
return torch.meshgrid(*tensors)
def bboxes_iou(bboxes_a, bboxes_b, xyxy=True):
"""
Copied from YOLOX/yolox/utils/boxes.py
"""
if bboxes_a.shape[1] != 4 or bboxes_b.shape[1] != 4:
raise IndexError
if xyxy:
tl = torch.max(bboxes_a[:, None, :2], bboxes_b[:, :2])
br = torch.min(bboxes_a[:, None, 2:], bboxes_b[:, 2:])
area_a = torch.prod(bboxes_a[:, 2:] - bboxes_a[:, :2], 1)
area_b = torch.prod(bboxes_b[:, 2:] - bboxes_b[:, :2], 1)
else:
tl = torch.max(
(bboxes_a[:, None, :2] - bboxes_a[:, None, 2:] / 2),
(bboxes_b[:, :2] - bboxes_b[:, 2:] / 2),
)
br = torch.min(
(bboxes_a[:, None, :2] + bboxes_a[:, None, 2:] / 2),
(bboxes_b[:, :2] + bboxes_b[:, 2:] / 2),
)
area_a = torch.prod(bboxes_a[:, 2:], 1)
area_b = torch.prod(bboxes_b[:, 2:], 1)
en = (tl < br).type(tl.type()).prod(dim=2)
area_i = torch.prod(br - tl, 2) * en # * ((tl < br).all())
return area_i / (area_a[:, None] + area_b - area_i)
class YOLOXHead(nn.Module):
def __init__(
self,
num_classes,
width=1.0,
strides=[8, 16, 32],
in_channels=[256, 512, 1024],
act="silu",
depthwise=False,
):
"""
Args:
act (str): activation type of conv. Defalut value: "silu".
depthwise (bool): whether apply depthwise conv in conv branch. Defalut value: False.
"""
super().__init__()
self.num_classes = num_classes
self.decode_in_inference = True # for deploy, set to False
self.cls_convs = nn.ModuleList()
self.reg_convs = nn.ModuleList()
self.cls_preds = nn.ModuleList()
self.reg_preds = nn.ModuleList()
self.obj_preds = nn.ModuleList()
self.stems = nn.ModuleList()
Conv = DWConv if depthwise else BaseConv
for i in range(len(in_channels)):
self.stems.append(
BaseConv(
in_channels=int(in_channels[i] * width),
out_channels=int(256 * width),
ksize=1,
stride=1,
act=act,
)
)
self.cls_convs.append(
nn.Sequential(
*[
Conv(
in_channels=int(256 * width),
out_channels=int(256 * width),
ksize=3,
stride=1,
act=act,
),
Conv(
in_channels=int(256 * width),
out_channels=int(256 * width),
ksize=3,
stride=1,
act=act,
),
]
)
)
self.reg_convs.append(
nn.Sequential(
*[
Conv(
in_channels=int(256 * width),
out_channels=int(256 * width),
ksize=3,
stride=1,
act=act,
),
Conv(
in_channels=int(256 * width),
out_channels=int(256 * width),
ksize=3,
stride=1,
act=act,
),
]
)
)
self.cls_preds.append(
nn.Conv2d(
in_channels=int(256 * width),
out_channels=self.num_classes,
kernel_size=1,
stride=1,
padding=0,
)
)
self.reg_preds.append(
nn.Conv2d(
in_channels=int(256 * width),
out_channels=4,
kernel_size=1,
stride=1,
padding=0,
)
)
self.obj_preds.append(
nn.Conv2d(
in_channels=int(256 * width),
out_channels=1,
kernel_size=1,
stride=1,
padding=0,
)
)
self.use_l1 = False
self.l1_loss = nn.L1Loss(reduction="none")
self.bcewithlog_loss = nn.BCEWithLogitsLoss(reduction="none")
self.iou_loss = None
self.strides = strides
self.grids = [torch.zeros(1)] * len(in_channels)
def forward(self, xin, labels=None, imgs=None):
outputs = []
for k, (cls_conv, reg_conv, stride_this_level, x) in enumerate(
zip(self.cls_convs, self.reg_convs, self.strides, xin)
):
x = self.stems[k](x)
cls_x = x
reg_x = x
cls_feat = cls_conv(cls_x)
cls_output = self.cls_preds[k](cls_feat)
reg_feat = reg_conv(reg_x)
reg_output = self.reg_preds[k](reg_feat)
obj_output = self.obj_preds[k](reg_feat)
output = torch.cat(
[reg_output, obj_output.sigmoid(), cls_output.sigmoid()], 1
)
outputs.append(output)
self.hw = [x.shape[-2:] for x in outputs]
# [batch, n_anchors_all, 85]
outputs = torch.cat(
[x.flatten(start_dim=2) for x in outputs], dim=2
).permute(0, 2, 1)
if self.decode_in_inference:
return self.decode_outputs(outputs, dtype=xin[0].type())
else:
return outputs
def get_output_and_grid(self, output, k, stride, dtype):
grid = self.grids[k]
batch_size = output.shape[0]
n_ch = 5 + self.num_classes
hsize, wsize = output.shape[-2:]
if grid.shape[2:4] != output.shape[2:4]:
yv, xv = meshgrid([torch.arange(hsize), torch.arange(wsize)])
grid = torch.stack((xv, yv), 2).view(1, 1, hsize, wsize, 2).type(dtype)
self.grids[k] = grid
output = output.view(batch_size, 1, n_ch, hsize, wsize)
output = output.permute(0, 1, 3, 4, 2).reshape(
batch_size, hsize * wsize, -1
)
grid = grid.view(1, -1, 2)
output[..., :2] = (output[..., :2] + grid) * stride
output[..., 2:4] = torch.exp(output[..., 2:4]) * stride
return output, grid
def decode_outputs(self, outputs, dtype):
grids = []
strides = []
for (hsize, wsize), stride in zip(self.hw, self.strides):
yv, xv = meshgrid([torch.arange(hsize), torch.arange(wsize)])
grid = torch.stack((xv, yv), 2).view(1, -1, 2)
grids.append(grid)
shape = grid.shape[:2]
strides.append(torch.full((*shape, 1), stride))
grids = torch.cat(grids, dim=1).type(dtype)
strides = torch.cat(strides, dim=1).type(dtype)
outputs = torch.cat([
(outputs[..., 0:2] + grids) * strides,
torch.exp(outputs[..., 2:4]) * strides,
outputs[..., 4:]
], dim=-1)
return outputs
|