记录yolov5更改backbone为ShuffleBlock网络迁移训练出错问题以及解决方法

最新推荐文章于 2024-05-21 12:57:49 发布
最新推荐文章于 2024-05-21 12:57:49 发布
阅读量2.6k 收藏 13
点赞数 6
分类专栏： ！！！！！！ 文章标签： pytorch 深度学习 目标检测
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_43676817/article/details/124641058
版权

前言:最近在学习yolov5，记录一些报错

1. 张量不对

Sizes of tensors must match except in dimension 1. Expected size 16 but got size 8 for tensor number 1 in the list.

报错信息如下：

Traceback (most recent call last):
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\site-packages\IPython\core\interactiveshell.py", line 3343, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-2-1475e912e0b9>", line 1, in <module>
    runfile('I:/GraduationProject/yolov5-5.0-sniperitf798/train.py', wdir='I:/GraduationProject/yolov5-5.0-sniperitf798')
  File "I:\DevSoftware\Python\JetBrains\PyCharm 2020.2.3\plugins\python\helpers\pydev\_pydev_bundle\pydev_umd.py", line 198, in runfile
    pydev_imports.execfile(filename, global_vars, local_vars)  # execute the script
  File "I:\DevSoftware\Python\JetBrains\PyCharm 2020.2.3\plugins\python\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "I:/GraduationProject/yolov5-5.0-sniperitf798/train.py", line 543, in <module>
    train(hyp, opt, device, tb_writer)
  File "I:/GraduationProject/yolov5-5.0-sniperitf798/train.py", line 88, in train
    model = Model(opt.cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
  File "I:\GraduationProject\yolov5-5.0-sniperitf798\models\yolo.py", line 93, in __init__
    m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
  File "I:\GraduationProject\yolov5-5.0-sniperitf798\models\yolo.py", line 123, in forward
    return self.forward_once(x, profile)  # single-scale inference, train
  File "I:\GraduationProject\yolov5-5.0-sniperitf798\models\yolo.py", line 139, in forward_once
    x = m(x)  # run
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "I:\GraduationProject\yolov5-5.0-sniperitf798\models\common.py", line 210, in forward
    return torch.cat(x, self.d)
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 16 but got size 8 for tensor number 1 in the list.

初步估计是模型网络结构出了问题。
下面是报错的网络结构：

backbone:
  # [from, number, module, args]
  # Shuffle_Block: [out, stride]
  [[ -1, 1, conv_bn_relu_maxpool, [ 32 ] ], # 0-P2/4
   [ -1, 1, Shuffle_Block, [ 128, 2 ] ],  # 1-P3/8
   [ -1, 3, Shuffle_Block, [ 128, 1 ] ],  # 2
   [ -1, 1, Shuffle_Block, [ 256, 2 ] ],  # 3-P4/16
   [ -1, 7, Shuffle_Block, [ 256, 1 ] ],  # 4
   [ -1, 1, Shuffle_Block, [ 512, 2 ] ],  # 5-P5/32
   [ -1, 3, Shuffle_Block, [ 512, 1 ] ],  # 6
   [ -1, 1, Shuffle_Block, [ 1024, 2 ] ],  # 7-P6/64
#   [ -1, 3, Shuffle_Block, [ 1024, 1 ] ],  # 8
  ]

# YOLOv5 v5.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]], # 7
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],# 8
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4 # 9
   [-1, 3, C3, [512, False]],  # 10

   [-1, 1, Conv, [256, 1, 1]], # 11
   [-1, 1, nn.Upsample, [None, 2, 'nearest']], # 12
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3 # 13
   [-1, 3, C3, [256, False]],  # 14 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]], # 15
   [[-1, 14], 1, Concat, [1]],  # cat head P4 # 16
   [-1, 3, C3, [512, False]],  # 17(P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],# 18
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 20 (P5/32-large)

   [[15, 18, 21], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

解决方法：在backbone网络末尾加上了Conv，spp，c3网络

# YOLOv5  backbone
backbone:
  # [from, number, module, args]
  # Shuffle_Block: [out, stride]
  [[ -1, 1, conv_bn_relu_maxpool, [ 32 ] ], # 0-P2/4
   [ -1, 1, Shuffle_Block, [ 128, 2 ] ],  # 1-P3/8
   [ -1, 3, Shuffle_Block, [ 128, 1 ] ],  # 2
   [ -1, 1, Shuffle_Block, [ 256, 2 ] ],  # 3-P4/16
   [ -1, 7, Shuffle_Block, [ 256, 1 ] ],  # 4
   [ -1, 1, Shuffle_Block, [ 512, 2 ] ],  # 5-P5/32
   [ -1, 3, Shuffle_Block, [ 512, 1 ] ],  # 6
   [ -1, 1, Conv, [ 1024, 3, 2 ] ],  # 7-P5/32
   [ -1, 1, SPP, [ 1024, [ 5, 9, 13 ] ] ],# 8
   [ -1, 3, C3, [ 1024, False ] ],  # 9
  ]

2. [WinError 1455] 页面文件太小

但是开始训练，又报新的错

train: Scanning 'VOC\labels\train' images and labels... 16551 found, 0 missing, 0 empty, 0 corrupted: 100%|██████████| 16551/16551 [00:11<00:00, 1491.29it/s]
train: New cache created: VOC\labels\train.cache
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\multiprocessing\spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\multiprocessing\spawn.py", line 114, in _main
    prepare(preparation_data)
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\multiprocessing\spawn.py", line 225, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path
    run_name="__mp_main__")
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "I:\GraduationProject\yolov5-5.0-sniperitf798\train.py", line 12, in <module>
    import torch.distributed as dist
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\site-packages\torch\__init__.py", line 124, in <module>
    raise err
OSError: [WinError 1455] 页面文件太小，无法完成操作。 Error loading "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\site-packages\torch\lib\caffe2_detectron_ops_gpu.dll" or one of its dependencies.
Traceback (most recent call last):
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\site-packages\IPython\core\interactiveshell.py", line 3343, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-2-1475e912e0b9>", line 1, in <module>
    runfile('I:/GraduationProject/yolov5-5.0-sniperitf798/train.py', wdir='I:/GraduationProject/yolov5-5.0-sniperitf798')
  File "I:\DevSoftware\Python\JetBrains\PyCharm 2020.2.3\plugins\python\helpers\pydev\_pydev_bundle\pydev_umd.py", line 198, in runfile
    pydev_imports.execfile(filename, global_vars, local_vars)  # execute the script
  File "I:\DevSoftware\Python\JetBrains\PyCharm 2020.2.3\plugins\python\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "I:/GraduationProject/yolov5-5.0-sniperitf798/train.py", line 545, in <module>
    train(hyp, opt, device, tb_writer)
  File "I:/GraduationProject/yolov5-5.0-sniperitf798/train.py", line 194, in train
    image_weights=opt.image_weights, quad=opt.quad, prefix=colorstr('train: '))
  File "I:\GraduationProject\yolov5-5.0-sniperitf798\utils\datasets.py", line 84, in create_dataloader
    collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn)
  File "I:\GraduationProject\yolov5-5.0-sniperitf798\utils\datasets.py", line 97, in __init__
    self.iterator = super().__iter__()
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 359, in __iter__
    return self._get_iterator()
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 305, in _get_iterator
    return _MultiProcessingDataLoaderIter(self)
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 918, in __init__
    w.start()
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\multiprocessing\process.py", line 105, in start
    self._popen = self._Popen(self)
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\multiprocessing\context.py", line 223, in _Popen
    return _default_context.get_context().Process._Popen(process_obj)
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\multiprocessing\context.py", line 322, in _Popen
    return Popen(process_obj)
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\multiprocessing\popen_spawn_win32.py", line 65, in __init__
    reduction.dump(process_obj, to_child)
  File "I:\EnvVariable\ML\Anaconda3\envs\pytorch\lib\multiprocessing\reduction.py", line 60, in dump
    ForkingPickler(file, protocol).dump(obj)
BrokenPipeError: [Errno 32] Broken pipe

出现的原因

电脑在默认情况下没有给I盘分配虚拟内存，所以将Python装在I盘的，在跑程序的时候，没有分配虚拟内存，就会遇到上面的问题。所以，只要给I盘分派虚拟内存即可。如果Python安装在C盘，更改C盘的虚拟内存的值，调大些。

解决方法

  1. 查找：查看高级系统设置
    在这里插入图片描述
  2. 进行如下图的操作
    在这里插入图片描述
  3. 重新启动计算机，重新运行程序

3. MP: Hint This means that multiple copies of the OpenMP runtime have been linked into the

解决上面一二问题开始出现新的问题，具体报错如下：

train: Scanning 'VOC\labels\train.cache' images and labels... 16551 found, 0 missing, 0 empty, 0 corrupted: 100%|██████████| 16551/16551 [00:00<?, ?it/s]
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
Scanning images:   0%|          | 0/4952 [00:00<?, ?it/s]OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
val: Scanning 'VOC\labels\val' images and labels... 4952 found, 0 missing, 0 empty, 0 corrupted: 100%|██████████| 4952/4952 [00:05<00:00, 846.03it/s]
val: New cache created: VOC\labels\val.cache
Plotting labels... 
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.

解决方法：
在train.py开头添加以下代码：

##OMP报错
import os
os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'

参考：
彻底解决pycharm中: OSError: [WinError 1455] 页面文件太小，无法完成操作的问题–亲测

Zhixiong Sun
关注
  • 6
    点赞
  • 踩
  • 13
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
YOLOv5：修改backbone为ConvNeXt
09-14
1、官方源项目地址 ：https://github.com/ultralytics/yolov5 2、在yolov5-6.1中修改backbone为ConvNeXt。 3、训练、测试、预测命令与官方版本一致。
生成器报错，RuntimeError: Sizes of tensors must match except in dimension
nanaminanaki的博客
04-13 5566
这个模型的代码里找的，本来是做pix2pix但是输入为300*300的时候就报错，256*256就不报错，后面发现是中间反卷积的时候输出形状和下采样的形状不一样，cat就不好使了，上了这个函数就好使了，但是会慢不少。padder_size根据最接近你数据集的来，这个函数是从。常见的模型报错，比方说pix2pix模型。
记录解决RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 27 but got size
h363924219的博客
11-09 1万+
在做目标检测服务过程中，将yolov7模型通过flask打包成预测服务API，此次训练的图像输入大小是1280，输入预测图片是如果图像大于1280则预测成功，小于1280则报RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 27 but got size。由于只有小图片预测报错，猜测是图像处理过程中resize问题，提示下面代码行错误。
YOLOv5改进 | 主干网络 | 用EfficientNet卷积替换backbone【教程+代码 】
最新发布
kay_545
05-21 1429
YOLOv5改进，优化，efficientnet
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 58 but got size 57 fo
热门推荐
梦在黎明破晓时的博客
11-13 1万+
在使用yolo v5n进行网络训练时使用的，在第12层Concat处连接第11层和第6层的Feature Map时出现维度不同的问题。
Sizes of tensors must match except in dimension 1. Expected size 44 but got size 45 for tensor numbe
踩坑博客
05-22 1万+
项目场景： 跑U-net网络的时候，有一步是torch.cat()操作，出现 下面是代码 class UNet(nn.Module): def __init__(self, in_channels, out_channels): super(UNet, self).__init__() self.conv1 = DoubleConv(in_channels, 32) self.pool1 = nn.MaxPool2d(2) self.
YOLOv7跑detect.py过程中出现RuntimeError: Sizes of tensors must match except in dimension 1. Expected size
m0_72096792的博客
08-07 2079
img0 = cv2.imread(path) # BGR后面加上。当我们验证的数据不满足YOLOv7图片要求时(640*640),直接运行可能会报错。
YOLOV5的多主干网络（backbone）实现.zip
03-05
# 复现TPH-YOLOv5 # 支持的backbone为Ghostnet、Shufflenetv2、Mobilenetv3Small、EagleEye、EfficientNetLite-0、PP-LCNet-1x、SwinTrans-YOLOv5
第P9周：YOLOv5-Backbone模块实现
12-30
第P9周：YOLOv5-Backbone模块实现
YOLOV5 改进实战项目【更换backbone为MobileNet】：大型海上图像目标检测数据集
03-19
基于YOLOV5【更换backbone为MobileNet】对大型海上目标检测数据集的目标检测实战项目，包含代码、数据集、训练好的权重参数，经测试，代码可以直接使用 【数据集介绍】海上目标图像数据，类别：邮轮、小鸟、鱼、...
YOLOv5：修改backbone为SPPCSPC
11-02
1、官方源项目地址 ：https://github.com/ultralytics/yolov5 2、在yolov5-6.1中修改backbone为SPPCSPC。 3、训练、测试、预测命令与官方版本一致。
pytorch dataloader 取batch_size时候出现bug的解决方式
12-20
1、 RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 342 and 281 in dimension 3 at /pytorch/aten/src/TH/generic/THTensorMoreMath.cpp:1333 2、 RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 3 and 1 in dimension 1 bug1
深度学习Pytorch-常见问题(二)
yanzhiwen2的博客
04-14 2457
深度学习Pytorch-常见问题(二)
Sizes of tensors must match except in dimension 1. Expected size 24 but got size 25 for tensor numbe
AI浩
04-08 1万+
在做图像分割的时候遇到了错误，错误如下： File "D:/segmentation/Pytorch-UNet-master/train.py", line 193, in <module> amp=args.amp) File "D:/segmentation/Pytorch-UNet-master/train.py", line 88, in train_net masks_pred = net(images) File "D:\ProgramData\Anacond
模型预测过程中报错 RuntimeError: Sizes of tensors must match except in dimension 1.
weixin_45636772的博客
12-05 6073
调用YOLOv7检测时报错：RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 58 but got size 57 for tensor number 1 in the list.
“RuntimeError：Sizes of tensors must match except in dimension1.Expected size 512 but got size 256
m0_61955067的博客
09-01 1383
3、解决删除模型中的两个Upsample模块，后面的tconcat和detect对应的层数也改一下即可。2、原因：主要是Upsample将图像维度变为原来两倍导致维度对不上，后面concat的时候就有问题。1、问题：完全按照他的步骤来一步步做下来，结果yaml文件有问题导致这个问题。
pytorch多个显卡并行训练 RuntimeError: Caught RuntimeError in replica 0 on device 0.
lq942797525的博客
11-17 1382
pytorch多个显卡并行训练 RuntimeError: Caught RuntimeError in replica 0 on device 0.
BlockShuffle-一个使模型训练速度提升20%的Trick
yaohaishen的专栏
10-19 491
BlockShuffle，就是在训练过程中使用分块打乱替代随机打乱的一种方法，即将原始数据按照数据长度进行排序，然后进行batch划分，在对batch训练进行打乱。这样操作，可以减少数据padding长度，缩短训练时长。 注意：该方法适用的前提是数据输入为变长。（不适合将所有数据padding到模型最大长度的代码） 举例说明 这里简单举个例子，大家就可以理解BlockShuffle为什么可以提高训练速度。 假如，数据长度为[1,2,3,4,512,512,512,512]，训练时batch_size
模型优化论文笔记5----采用shuffled block和group convolutional的MBNet(71K)用于AMC
qq_40616042的博客
01-17 878
1.主要思想： 提出一种MBNet网络，应用于AMC。网络由一系列带有残差连接的shuffle blocks（混洗块？）模块组成，每一个block由grouped convolutional layers分组卷积层和一个shuffling module组成。channel shuffling module是为了避免分组卷积层的无效组交互问题而提出的。除此之外，通过元素附加层从IQ信号中学习时空特征，建立从每一个混洗模块的输入到对应输出的残差连接。实验基于RadioML2018.01A数据集。 2.背景： 物
介绍一下yolov5的BackBone网络
05-10
YoloV5的Backbone网络采用的是CSPDarknet53，它是一种基于Darknet的卷积神经网络，由Alexey Bochkovskiy等人于2019年提出，是一个高效的网络结构，在目标检测任务中表现出色。 CSPDarknet53的结构与ResNet类似，采用了残差连接的方法，有助于网络的训练和优化。同时，CSPDarknet53还采用了Cross-Stage Partial connection（CSP）的方法，将网络分为两个阶段，每个阶段都包含一个CSP模块和一个残差块。CSP模块中采用了跨阶段连接的方式，将两个阶段的特征图进行拼接，提高了网络的特征表达能力和检测精度。 在YoloV5中，CSPDarknet53作为Backbone网络，负责提取图像的特征，然后通过FPN（Feature Pyramid Network）结构将高层次的语义信息和低层次的细节信息进行融合，提高了检测的准确率和效率。同时，在模型大小和速度上的优化也使得YoloV5在目标检测领域具有更好的性能表现。

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值