koubun-ko-df

Results 10 issues of koubun-ko-df

I have a question that what does the super parameter 'input_size' mean. Could you please help me? Thanks!

Hello, I'm trying to use AlphaPose to detect the poses of my dataset. However, it seems that the output only includes keypoints and bounding boxes, without heatmaps. Could you tell...

Hello! I'm interested in MARS dataset and papers based on it, so I want to create my own MARS-like dataset for Person Re-ID. Now I have the original videos and...

I have trained the model for 100 epochs on SUNRGBD with pretrained ResNet34 on Imagenet, and the best mIoU is still 10%. Is it normal? My batchsize is 16, and...

Hello, I have run the evaluation process: "python eval.py \ --dataset sunrgbd \ --dataset_dir ./datasets/sunrgbd \ --ckpt_path ./trained_models/sunrgbd/r34_NBt1D.pth", where are the results saved?

Hello! Thank you for uploading this impressive work! According to the paper, you have tested your method on several datasets. Could you share the already trained models on these datasets?...

您好,为什么我使用coco的train14训练,loss一开始就是0.0几,后面也一直是0.0几呢?

Hello! I'm trying to create behavior annotations for my original video, but I cannot find "trace" on **Display → Toggle object visibility** after I followed the instructions of Wiki: ![image](https://user-images.githubusercontent.com/54608650/148175962-1e1818df-ff8c-4d55-a271-a230017230af.png)...

Hello! When I tested MARS on my videos as below, ![捕获](https://user-images.githubusercontent.com/54608650/147734911-da6028ca-dc18-4f47-b5ab-b0f767e0fadc.PNG) there seems to be something wrong with the saved video, the size is 1 KB: ![image](https://user-images.githubusercontent.com/54608650/147735178-97a760c8-347b-46ef-a6d5-beb4dc7975e3.png) May I ask...

Hi, Thanks for sharing your excellent work! I plan to develop an activity recognition method with your hand-object module integrated and conduct experiments on CharadesEgo. I noticed that you have...