Open abhigoku10 opened 4 years ago
@abhigoku10 您好,语义分割已经是像素级别结果了,不需要生成CAM图像
@abhigoku10 wokay for architectures like retina net how to obtain the CAM output or mask rcnn based architecture
@abhigoku10 您好,retina net完成了,通知您哈
@yizt please do let me knw once done it
@yizt 在线等前辈的retinanet CAM,因为retinanet score和box是分开的,自己一直没有搞出来
您好,我尽快,最迟这周末!
易作天 | |
---|---|
邮箱:csuyzt@163.com |
签名由 网易邮箱大师 定制
On 05/12/2020 11:03, wangzyon wrote:
@abhigoku10 您好,retina net完成了,通知您哈
@abhigoku10 您好,语义分割已经是像素级别结果了,不需要生成CAM图像
@yizt 在线等前辈的retinanet CAM,因为retinanet score和box是分开的,自己一直没有搞出来
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.
@abhigoku10 @wangzyon 已增加retinanet的Grad-CAM实现
@yizt thanks for sharing the source code , in your codes both faster rcnn and retina net you have a variable called indices can you let me knw how to do it for custom architecture or for yolact
@abhigoku10 你好,a)个人认为跟indices没有关系,假如retinanet没有使用fpn,也就不需要indices了。对于目标检测网络由于是多输出,且网络结构都不同,没有固定的生成CAM的方法;b)另外yolact是实例分割网络,不需要生成CAM图了,分割结果就是最好的CAM图。c) 如果实在要生成yolact的CAM图,与retinanet应该是一样的,yolact是基于retinanet的
@yizt hwo to get output like this from the above source code
@abhigoku10 您好,这就是原始图像与热图加权求和结果;如main.py
中的
cam = heatmap + np.float32(image)
return norm_image(cam)
@yizt i have following few queries
@abhigoku10 您好
@yizt i am trying to modify the code to run grad cam on the yolact++/yolact, i am stuck at the feature level function where i am not able to get generate the feature level values for this architecture, How to integrate with other architecture
@yizt Thanks for sharing your work . How can we use the current code to for segmentation models like deeplab . Can you share / suggest the modifications required
Thanks in advance