RT-DETR改进策略【模型轻量化】| ShufflenetV2，通过通道划分构建高效网络
一、本文介绍
本文记录的是
基于ShufflenetV2的RT-DETR目标检测轻量化改进方法研究
。
FLOPs
是评价模型复杂独的重要指标，但其无法考虑到模型的内存访问成本和并行度，因此本文在
RT-DETR
的基础上引入
ShufflenetV2
，
使其在在保持准确性的同时提高模型的运行效率
。
| 模型 | 参数量 | 计算量 | 推理速度 |
|---|---|---|---|
| rtdetr-l | 32.8M | 108.0GFLOPs | 11.6ms |
| Improved | 19.2M | 62.9GFLOPs | 10.5ms |
二、ShuffleNet V2设计原理
ShuffleNet V2
是一种高效的卷积神经网络架构，其模型结构及优势如下：
2.1 模型结构
-
回顾ShuffleNet v1
：
ShuffleNet是一种广泛应用于低端设备的先进网络架构，为增加在给定计算预算下的特征通道数量，采用了点组卷积和瓶颈结构，但这增加了内存访问成本（MAC），且过多的组卷积和元素级“Add”操作也存在问题。 -
引入Channel Split和ShuffleNet V2
：为解决上述问题，引入了名为
Channel Split的简单操作。在每个单元开始时，将 c c c 个特征通道的输入分为两个分支，分别具有 c − c ′ c - c' c − c ′ 和 c ′ c' c ′ 个通道。一个分支保持不变，另一个分支由三个具有相同输入和输出通道的卷积组成，以满足G1（平衡卷积，即相等的通道宽度可最小化MAC）。两个 1 × 1 1 \times 1 1 × 1 卷积不再是组式的，这部分是为了遵循G2（避免过多的组卷积增加MAC），部分是因为拆分操作已经产生了两个组。卷积后，两个分支连接，通道数量保持不变，并使用与ShuffleNet v1相同的“通道洗牌”操作来实现信息通信。对于空间下采样，单元进行了略微修改，删除了通道拆分操作，使输出通道数量加倍。 -
整体网络结构
：通过反复堆叠构建块来构建整个网络，设置
c
′
=
c
/
2
c' = c/2
c
′
=
c
/2
，整体网络结构与
ShuffleNet v1相似，并在全局平均池化之前添加了一个额外的 1 × 1 1 \times 1 1 × 1 卷积层来混合特征。
2.2 优势
- 高效且准确 ：遵循了高效网络设计的所有准则，每个构建块的高效率使其能够使用更多的特征通道和更大的网络容量，并且在每个块中，一半的特征通道直接通过块并加入下一个块，实现了一种特征重用模式，类似于DenseNet，但更高效。
- 速度优势明显 ：在与其他网络架构的比较中，ShuffleNet v2在速度方面表现出色，特别是在GPU上明显快于其他网络（如MobileNet v2、ShuffleNet v1和Xception）。在ARM上，ShuffleNet v1、Xception和ShuffleNet v2的速度相当，但MobileNet v2较慢，这是因为MobileNet v2的MAC较高。
- 兼容性好 ：可以与其他技术（如Squeeze - and - excitation模块）结合进一步提高性能。
论文： https://arxiv.org/pdf/1807.11164.pdf
源码： https://gitcode.com/gh_mirrors/sh/ShuffleNet-Series/blob/master/ShuffleNetV2/blocks.py?utm_source=csdn_github_accelerator&isLogin=1
三、ShuffleNet V2基础模块的实现代码
ShuffleNet V2基础模块
的实现代码如下：
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
from collections import OrderedDict
from torch.nn import init
import math
__all__ = ['shufflenetv2']
def conv_bn(inp, oup, stride):
return nn.Sequential(
nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
nn.BatchNorm2d(oup),
nn.ReLU(inplace=True)
)
def conv_1x1_bn(inp, oup):
return nn.Sequential(
nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup),
nn.ReLU(inplace=True)
)
def channel_shuffle(x, groups):
batchsize, num_channels, height, width = x.data.size()
channels_per_group = num_channels // groups
# reshape
x = x.view(batchsize, groups,
channels_per_group, height, width)
x = torch.transpose(x, 1, 2).contiguous()
# flatten
x = x.view(batchsize, -1, height, width)
return x
class InvertedResidual(nn.Module):
def __init__(self, inp, oup, stride, benchmodel):
super(InvertedResidual, self).__init__()
self.benchmodel = benchmodel
self.stride = stride
assert stride in [1, 2]
oup_inc = oup // 2
if self.benchmodel == 1:
# assert inp == oup_inc
self.banch2 = nn.Sequential(
# pw
nn.Conv2d(oup_inc, oup_inc, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup_inc),
nn.ReLU(inplace=True),
# dw
nn.Conv2d(oup_inc, oup_inc, 3, stride, 1, groups=oup_inc, bias=False),
nn.BatchNorm2d(oup_inc),
# pw-linear
nn.Conv2d(oup_inc, oup_inc, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup_inc),
nn.ReLU(inplace=True),
)
else:
self.banch1 = nn.Sequential(
# dw
nn.Conv2d(inp, inp, 3, stride, 1, groups=inp, bias=False),
nn.BatchNorm2d(inp),
# pw-linear
nn.Conv2d(inp, oup_inc, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup_inc),
nn.ReLU(inplace=True),
)
self.banch2 = nn.Sequential(
# pw
nn.Conv2d(inp, oup_inc, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup_inc),
nn.ReLU(inplace=True),
# dw
nn.Conv2d(oup_inc, oup_inc, 3, stride, 1, groups=oup_inc, bias=False),
nn.BatchNorm2d(oup_inc),
# pw-linear
nn.Conv2d(oup_inc, oup_inc, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup_inc),
nn.ReLU(inplace=True),
)
@staticmethod
def _concat(x, out):
# concatenate along channel axis
return torch.cat((x, out), 1)
def forward(self, x):
if 1 == self.benchmodel:
x1 = x[:, :(x.shape[1] // 2), :, :]
x2 = x[:, (x.shape[1] // 2):, :, :]
out = self._concat(x1, self.banch2(x2))
elif 2 == self.benchmodel:
out = self._concat(self.banch1(x), self.banch2(x))
return channel_shuffle(out, 2)
class ShuffleNetV2(nn.Module):
def __init__(self, n_class=1000, input_size=224, width_mult=1.):
super(ShuffleNetV2, self).__init__()
assert input_size % 32 == 0
self.stage_repeats = [8, 4, 4]
# index 0 is invalid and should never be called.
# only used for indexing convenience.
if width_mult == 0.5:
self.stage_out_channels = [-1, 24, 48, 96, 192, 1024]
elif width_mult == 1.0:
self.stage_out_channels = [-1, 24, 116, 232, 464, 1024]
elif width_mult == 1.5:
self.stage_out_channels = [-1, 24, 176, 352, 704, 1024]
elif width_mult == 2.0:
self.stage_out_channels = [-1, 24, 224, 488, 976, 2048]
else:
raise ValueError(
"""groups is not supported for
1x1 Grouped Convolutions""")
# building first layer
input_channel = self.stage_out_channels[1]
self.conv1 = conv_bn(3, input_channel, 2)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.features = []
# building inverted residual blocks
for idxstage in range(len(self.stage_repeats)):
numrepeat = self.stage_repeats[idxstage]
output_channel = self.stage_out_channels[idxstage + 2]
for i in range(numrepeat):
if i == 0:
# inp, oup, stride, benchmodel):
self.features.append(InvertedResidual(input_channel, output_channel, 2, 2))
else:
self.features.append(InvertedResidual(input_channel, output_channel, 1, 1))
input_channel = output_channel
# make it nn.Sequential
self.features = nn.Sequential(*self.features)
self.index = self.stage_out_channels[2: 2 + len(self.stage_repeats)]
self.width_list = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]
def forward(self, x):
x = self.conv1(x)
x = self.maxpool(x)
results = [None, None, None, None]
for index, model in enumerate(self.features):
x = model(x)
# results.append(x)
if index == 0:
results[index] = x
if x.size(1) in self.index:
position = self.index.index(x.size(1)) # Find the position in the index list
results[position + 1] = x
return results
def shufflenetv2(width_mult=1.):
model = ShuffleNetV2(width_mult=width_mult)
return model
if __name__ == "__main__":
"""Testing
"""
model = ShuffleNetV2()
print(model)
四、修改步骤
4.1 修改一
① 在
ultralytics/nn/
目录下新建
AddModules
文件夹用于存放模块代码
② 在
AddModules
文件夹下新建
ShuffleNetV2.py
，将
第三节
中的代码粘贴到此处
4.2 修改二
在
AddModules
文件夹下新建
__init__.py
（已有则不用新建），在文件内导入模块：
from .ShuffleNetV2 import *
4.3 修改三
在
ultralytics/nn/modules/tasks.py
文件中，需要添加各模块类。
① 首先：导入模块
② 在BaseModel类的predict函数中，在如下两处位置中去掉
embed
参数：
③ 在BaseModel类的_predict_once函数，替换如下代码：
def _predict_once(self, x, profile=False, visualize=False):
"""
Perform a forward pass through the network.
Args:
x (torch.Tensor): The input tensor to the model.
profile (bool): Print the computation time of each layer if True, defaults to False.
visualize (bool): Save the feature maps of the model if True, defaults to False.
Returns:
(torch.Tensor): The last output of the model.
"""
y, dt = [], [] # 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
if profile:
self._profile_one_layer(m, x, dt)
x = m(x) # run
y.append(x if m.i in self.save else None) # save output
if visualize:
feature_visualization(x, m.type, m.i, save_dir=visualize)
return x
④ 将
RTDETRDetectionModel类
中的
predict函数
完整替换：
def predict(self, x, profile=False, visualize=False, batch=None, augment=False):
"""
Perform a forward pass through the model.
Args:
x (torch.Tensor): The input tensor.
profile (bool, optional): If True, profile the computation time for each layer. Defaults to False.
visualize (bool, optional): If True, save feature maps for visualization. Defaults to False.
batch (dict, optional): Ground truth data for evaluation. Defaults to None.
augment (bool, optional): If True, perform data augmentation during inference. Defaults to False.
Returns:
(torch.Tensor): Model's output tensor.
"""
y, dt = [], [] # outputs
for m in self.model[:-1]: # except the head part
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
if profile:
self._profile_one_layer(m, x, dt)
if hasattr(m, 'backbone'):
x = m(x)
for _ in range(5 - len(x)):
x.insert(0, None)
for i_idx, i in enumerate(x):
if i_idx in self.save:
y.append(i)
else:
y.append(None)
# for i in x:
# if i is not None:
# print(i.size())
x = x[-1]
else:
x = m(x) # run
y.append(x if m.i in self.save else None) # save output
if visualize:
feature_visualization(x, m.type, m.i, save_dir=visualize)
head = self.model[-1]
x = head([y[j] for j in head.f], batch) # head inference
return x
⑤ 在
parse_model函数
如下位置替换如下代码:
if verbose:
LOGGER.info(f"\n{'':>3}{'from':>20}{'n':>3}{'params':>10} {'module':<45}{'arguments':<30}")
ch = [ch]
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
is_backbone = False
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
try:
if m == 'node_mode':
m = d[m]
if len(args) > 0:
if args[0] == 'head_channel':
args[0] = int(d[args[0]])
t = m
m = getattr(torch.nn, m[3:]) if 'nn.' in m else globals()[m] # get module
except:
pass
for j, a in enumerate(args):
if isinstance(a, str):
with contextlib.suppress(ValueError):
try:
args[j] = locals()[a] if a in locals() else ast.literal_eval(a)
except:
args[j] = a
替换后如下：
⑥ 在
parse_model
函数，添加如下代码。
elif m in {
shufflenetv2,
}:
m = m(*args)
c2 = m.width_list
⑦ 在
parse_model函数
如下位置替换如下代码:
if isinstance(c2, list):
is_backbone = True
m_ = m
m_.backbone = True
else:
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
m_.np = sum(x.numel() for x in m_.parameters()) # number params
m_.i, m_.f, m_.type = i + 4 if is_backbone else i, f, t # attach index, 'from' index, type
if verbose:
LOGGER.info(f'{i:>3}{str(f):>20}{n_:>3}{m_.np:10.0f} {t:<45}{str(args):<30}') # print
save.extend(x % (i + 4 if is_backbone else i) for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
layers.append(m_)
if i == 0:
ch = []
if isinstance(c2, list):
ch.extend(c2)
for _ in range(5 - len(ch)):
ch.insert(0, 0)
else:
ch.append(c2)
return nn.Sequential(*layers), sorted(save)
⑧ 在
ultralytics\nn\autobackend.py
文件的
AutoBackend类
中的
forward函数
，完整替换如下代码：
def forward(self, im, augment=False, visualize=False):
"""
Runs inference on the YOLOv8 MultiBackend model.
Args:
im (torch.Tensor): The image tensor to perform inference on.
augment (bool): whether to perform data augmentation during inference, defaults to False
visualize (bool): whether to visualize the output predictions, defaults to False
Returns:
(tuple): Tuple containing the raw output tensor, and processed output for visualization (if visualize=True)
"""
b, ch, h, w = im.shape # batch, channel, height, width
if self.fp16 and im.dtype != torch.float16:
im = im.half() # to FP16
if self.nhwc:
im = im.permute(0, 2, 3, 1) # torch BCHW to numpy BHWC shape(1,320,192,3)
if self.pt or self.nn_module: # PyTorch
y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im)
elif self.jit: # TorchScript
y = self.model(im)
elif self.dnn: # ONNX OpenCV DNN
im = im.cpu().numpy() # torch to numpy
self.net.setInput(im)
y = self.net.forward()
elif self.onnx: # ONNX Runtime
im = im.cpu().numpy() # torch to numpy
y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im})
elif self.xml: # OpenVINO
im = im.cpu().numpy() # FP32
y = list(self.ov_compiled_model(im).values())
elif self.engine: # TensorRT
if self.dynamic and im.shape != self.bindings['images'].shape:
i = self.model.get_binding_index('images')
self.context.set_binding_shape(i, im.shape) # reshape if dynamic
self.bindings['images'] = self.bindings['images']._replace(shape=im.shape)
for name in self.output_names:
i = self.model.get_binding_index(name)
self.bindings[name].data.resize_(tuple(self.context.get_binding_shape(i)))
s = self.bindings['images'].shape
assert im.shape == s, f"input size {im.shape} {'>' if self.dynamic else 'not equal to'} max model size {s}"
self.binding_addrs['images'] = int(im.data_ptr())
self.context.execute_v2(list(self.binding_addrs.values()))
y = [self.bindings[x].data for x in sorted(self.output_names)]
elif self.coreml: # CoreML
im = im[0].cpu().numpy()
im_pil = Image.fromarray((im * 255).astype('uint8'))
# im = im.resize((192, 320), Image.BILINEAR)
y = self.model.predict({'image': im_pil}) # coordinates are xywh normalized
if 'confidence' in y:
raise TypeError('Ultralytics only supports inference of non-pipelined CoreML models exported with '
f"'nms=False', but 'model={w}' has an NMS pipeline created by an 'nms=True' export.")
# TODO: CoreML NMS inference handling
# from ultralytics.utils.ops import xywh2xyxy
# box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]]) # xyxy pixels
# conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float32)
# y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1)
elif len(y) == 1: # classification model
y = list(y.values())
elif len(y) == 2: # segmentation model
y = list(reversed(y.values())) # reversed for segmentation models (pred, proto)
elif self.paddle: # PaddlePaddle
im = im.cpu().numpy().astype(np.float32)
self.input_handle.copy_from_cpu(im)
self.predictor.run()
y = [self.predictor.get_output_handle(x).copy_to_cpu() for x in self.output_names]
elif self.ncnn: # ncnn
mat_in = self.pyncnn.Mat(im[0].cpu().numpy())
ex = self.net.create_extractor()
input_names, output_names = self.net.input_names(), self.net.output_names()
ex.input(input_names[0], mat_in)
y = []
for output_name in output_names:
mat_out = self.pyncnn.Mat()
ex.extract(output_name, mat_out)
y.append(np.array(mat_out)[None])
elif self.triton: # NVIDIA Triton Inference Server
im = im.cpu().numpy() # torch to numpy
y = self.model(im)
else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
im = im.cpu().numpy()
if self.saved_model: # SavedModel
y = self.model(im, training=False) if self.keras else self.model(im)
if not isinstance(y, list):
y = [y]
elif self.pb: # GraphDef
y = self.frozen_func(x=self.tf.constant(im))
if len(y) == 2 and len(self.names) == 999: # segments and names not defined
ip, ib = (0, 1) if len(y[0].shape) == 4 else (1, 0) # index of protos, boxes
nc = y[ib].shape[1] - y[ip].shape[3] - 4 # y = (1, 160, 160, 32), (1, 116, 8400)
self.names = {i: f'class{i}' for i in range(nc)}
else: # Lite or Edge TPU
details = self.input_details[0]
integer = details['dtype'] in (np.int8, np.int16) # is TFLite quantized int8 or int16 model
if integer:
scale, zero_point = details['quantization']
im = (im / scale + zero_point).astype(details['dtype']) # de-scale
self.interpreter.set_tensor(details['index'], im)
self.interpreter.invoke()
y = []
for output in self.output_details:
x = self.interpreter.get_tensor(output['index'])
if integer:
scale, zero_point = output['quantization']
x = (x.astype(np.float32) - zero_point) * scale # re-scale
if x.ndim > 2: # if task is not classification
# Denormalize xywh by image size. See https://github.com/ultralytics/ultralytics/pull/1695
# xywh are normalized in TFLite/EdgeTPU to mitigate quantization error of integer models
x[:, [0, 2]] *= w
x[:, [1, 3]] *= h
y.append(x)
# TF segment fixes: export is reversed vs ONNX export and protos are transposed
if len(y) == 2: # segment with (det, proto) output order reversed
if len(y[1].shape) != 4:
y = list(reversed(y)) # should be y = (1, 116, 8400), (1, 160, 160, 32)
y[1] = np.transpose(y[1], (0, 3, 1, 2)) # should be y = (1, 116, 8400), (1, 32, 160, 160)
y = [x if isinstance(x, np.ndarray) else x.numpy() for x in y]
# for x in y:
# print(type(x), len(x)) if isinstance(x, (list, tuple)) else print(type(x), x.shape) # debug shapes
if isinstance(y, (list, tuple)):
return self.from_numpy(y[0]) if len(y) == 1 else [self.from_numpy(x) for x in y]
else:
return self.from_numpy(y)
至此就修改完成了，可以配置模型开始训练了
六、yaml模型文件
6.1 模型改进⭐
在代码配置完成后，配置模型的YAML文件。
此处以
ultralytics/cfg/models/rt-detr/rtdetr-l.yaml
为例，在同目录下创建一个用于自己数据集训练的模型文件
rtdetr-shufflenetv2.yaml
。
将
rtdetr-l.yaml
中的内容复制到
rtdetr-shufflenetv2.yaml
文件下，修改
nc
数量等于自己数据中目标的数量。
📌 模型的修改方法是将
骨干网络
替换成
shufflenetv2模块
。
# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-l object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/rtdetr
# Parameters
nc: 1 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
l: [1.00, 1.00, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, shufflenetv2, []] # 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5 input_proj.2
- [-1, 1, AIFI, [1024, 8]] # 6
- [-1, 1, Conv, [256, 1, 1]] # 7, Y5, lateral_convs.0
- [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 8
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9 input_proj.1
- [[-2, -1], 1, Concat, [1]] # 10
- [-1, 3, RepC3, [256]] # 11, fpn_blocks.0
- [-1, 1, Conv, [256, 1, 1]] # 12, Y4, lateral_convs.1
- [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 13
- [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14 input_proj.0
- [[-2, -1], 1, Concat, [1]] # 15 cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0
- [[-1, 12], 1, Concat, [1]] # 18 cat Y4
- [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1
- [[-1, 7], 1, Concat, [1]] # 21 cat Y5
- [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1
- [[16, 19, 22], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)
七、成功运行结果
分别打印网络模型可以看到
shufflenetv2模块
已经加入到模型中，并可以进行训练了。
rtdetr-shufflenetv2 ：
rtdetr-ShuffleNetV2 summary: 555 layers, 19,237,327 parameters, 19,237,327 gradients, 62.9 GFLOPs
from n params module arguments
0 -1 1 692204 shufflenetv2 []
1 -1 1 119296 ultralytics.nn.modules.conv.Conv [464, 256, 1, 1, None, 1, 1, False]
2 -1 1 789760 ultralytics.nn.modules.transformer.AIFI [256, 1024, 8]
3 -1 1 66048 ultralytics.nn.modules.conv.Conv [256, 256, 1, 1]
4 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
5 3 1 59904 ultralytics.nn.modules.conv.Conv [232, 256, 1, 1, None, 1, 1, False]
6 [-2, -1] 1 0 ultralytics.nn.modules.conv.Concat [1]
7 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
8 -1 1 66048 ultralytics.nn.modules.conv.Conv [256, 256, 1, 1]
9 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
10 2 1 30208 ultralytics.nn.modules.conv.Conv [116, 256, 1, 1, None, 1, 1, False]
11 [-2, -1] 1 0 ultralytics.nn.modules.conv.Concat [1]
12 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
13 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2]
14 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1]
15 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
16 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2]
17 [-1, 7] 1 0 ultralytics.nn.modules.conv.Concat [1]
18 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
19 [16, 19, 22] 1 7303907 ultralytics.nn.modules.head.RTDETRDecoder [1, [256, 256, 256]]
rtdetr-ShuffleNetV2 summary: 555 layers, 19,237,327 parameters, 19,237,327 gradients, 62.9 GFLOPs