{
"backbone": "resnet34",
"classes_names": [
"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"
],
"max_size": 800,
"min_size": 1333,
"model_path": "BaseModel\\fasterrcnn_res34_coco_3x_800size.pkl",
"network": "fasterrcnn"
}
基于megengine的FasterRCNN的目标检测模型,主干网络ResNet34
需积分: 0 123 浏览量
2022-10-17
14:39:51
上传
评论
收藏 137.56MB ZIP 举报
爱学习的广东仔
- 粉丝: 1w+
- 资源: 130
最新资源
- 蓝zapro.apk
- chromedriver-linux64.zip
- 基于Python和PyTorch框架完成的一个手写数字识别实验源码(带MINIST手写数字数据集)+详细注释(高分项目)
- 基于Matlab在MNIST数据集上利用CNN完成手写体数字识别任务,并实现单层CNN反向传播算法+源代码+文档说明(高分项目)
- NVIDIA驱动、CUDA和Pytorch及其依赖
- html动态爱心代码一(附源码)
- c40539bc-071a-486c-9d52-9d0c18d62dac 4.html
- 基于物理的非视域成像(NLOS)算法,利用了nerf+python源码+文档说明
- yuluer知更鸟.7z(1).001
- python课程设计-基于tensorflow实现的图文生成程序,数据集flickr30k-images+源代码+文档说明+截图
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
评论0