num_classes` (3) in Shared2FCBBoxHead of MMDataParallel does not

AssertionError: The num_classes (3) in Shared2FCBBoxHead of MMDataParallel does not matches the …

一届书生# 2021-10-13 11:07:00 85 收藏 1
文章标签： 深度学习 tensorflow tomcat anaconda python
版权
mmdetection训练自己的数据集时报错 ⚠️ ：

AssertionError: The num_classes (3) in Shared2FCBBoxHead of MMDataParallel does not matches the length of CLASSES 80) in CocoDataset

意思就是你指定的类别(3种)与CocoDataset的类别(80种)不匹配。

你可能已经修改了以下文件，但是还是报错：

mmdetection-master\mmdet\core\evaluation\class_names.py

def coco_classes():
return [
# ‘person’, ‘bicycle’, ‘car’, ‘motorcycle’, ‘airplane’, ‘bus’, ‘train’,
# ‘truck’, ‘boat’, ‘traffic_light’, ‘fire_hydrant’, ‘stop_sign’,
# ‘parking_meter’, ‘bench’, ‘bird’, ‘cat’, ‘dog’, ‘horse’, ‘sheep’,
# ‘cow’, ‘elephant’, ‘bear’, ‘zebra’, ‘giraffe’, ‘backpack’, ‘umbrella’,
# ‘handbag’, ‘tie’, ‘suitcase’, ‘frisbee’, ‘skis’, ‘snowboard’,
# ‘sports_ball’, ‘kite’, ‘baseball_bat’, ‘baseball_glove’, ‘skateboard’,
# ‘surfboard’, ‘tennis_racket’, ‘bottle’, ‘wine_glass’, ‘cup’, ‘fork’,
# ‘knife’, ‘spoon’, ‘bowl’, ‘banana’, ‘apple’, ‘sandwich’, ‘orange’,
# ‘broccoli’, ‘carrot’, ‘hot_dog’, ‘pizza’, ‘donut’, ‘cake’, ‘chair’,
# ‘couch’, ‘potted_plant’, ‘bed’, ‘dining_table’, ‘toilet’, ‘tv’,
# ‘laptop’, ‘mouse’, ‘remote’, ‘keyboard’, ‘cell_phone’, ‘microwave’,
# ‘oven’, ‘toaster’, ‘sink’, ‘refrigerator’, ‘book’, ‘clock’, ‘vase’,
# ‘scissors’, ‘teddy_bear’, ‘hair_drier’, ‘toothbrush’
‘lm’,‘ls’
]
mmdetection-master\mmdet\datasets\coco.py

class CocoDataset(CustomDataset):
# CLASSES = (
# ‘person’, ‘bicycle’, ‘car’, ‘motorcycle’, ‘airplane’, ‘bus’,
# ‘train’, ‘truck’, ‘boat’, ‘traffic light’, ‘fire hydrant’,
# ‘stop sign’, ‘parking meter’, ‘bench’, ‘bird’, ‘cat’, ‘dog’,
# ‘horse’, ‘sheep’, ‘cow’, ‘elephant’, ‘bear’, ‘zebra’, ‘giraffe’,
# ‘backpack’, ‘umbrella’, ‘handbag’, ‘tie’, ‘suitcase’, ‘frisbee’,
# ‘skis’, ‘snowboard’, ‘sports ball’, ‘kite’, ‘baseball bat’,
# ‘baseball glove’, ‘skateboard’, ‘surfboard’, ‘tennis racket’,
# ‘bottle’, ‘wine glass’, ‘cup’, ‘fork’, ‘knife’, ‘spoon’, ‘bowl’,
# ‘banana’, ‘apple’, ‘sandwich’, ‘orange’, ‘broccoli’, ‘carrot’,
# ‘hot dog’, ‘pizza’, ‘donut’, ‘cake’, ‘chair’, ‘couch’,
# ‘potted plant’, ‘bed’, ‘dining table’, ‘toilet’, ‘tv’, ‘laptop’,
# ‘mouse’, ‘remote’, ‘keyboard’, ‘cell phone’, ‘microwave’,
# ‘oven’, ‘toaster’, ‘sink’, ‘refrigerator’, ‘book’, ‘clock’,
# ‘vase’, ‘scissors’, ‘teddy bear’, ‘hair drier’, ‘toothbrush’
# )
CLASSES = (‘lm’, ‘ls’)
废话不多说，直接上方法。有以下几种方法：

1️⃣ 是修改最少的，假设你有2个类，你就把上边两处地方，前2个类替换成你的类别。方法比较简单，但是可能存在隐患。

2️⃣ 第二种方法就是修改完 class_names.py 和 voc.py 之后一定要重新编译代码(运行python setup.py install)，再进行训练。

我试了，还是报同样的错误，可能是我方法不对。

参考：

新版 MMDetection V2.3.0训练测试笔记 - it610.com

mmdetectionV2.x版本 训练自己的VOC数据集_桃子酱momo的博客-CSDN博客

3️⃣ 第三种方法，也是我使用的方法，其实跟重新编译一样，重新编译的原因就是因为环境里的源文件没有修改，所以你才会报错。mmdetection-master目录下只是一些python文件，真正运行程序时，运行的还是环境里的源文件，因为我们直接去环境里修改源文件。

假设我的conda环境名为conda_env_name，因此去下面的目录下，分别修改两个文件：

\anaconda3\envs\conda_env_name\lib\python3.7\site-packages\mmdet\core\evaluation\class_names.py

\anaconda3\envs\conda_env_name\lib\python3.7\site-packages\mmdet\datasets\coco.py

在conda环境里把这两个文件里的类别修改了，就可以了。

⭐ 最终也功夫不负有心人，解决掉了这个bug，写此博客，以帮助大家少走弯路。
————————————————
版权声明：本文为CSDN博主「一届书生#」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/qq_39435411/article/details/120756080