yoyomimi / as-net Goto Github PK

你好呀，请问下有没有HOI-A相关的模型以及脚本呢？
另外关于HOIA数据集里有部分错误标注请问你是怎么处理的呀0.0

running the test code on HICO-DET python3 tools/eval.py --cfg configs/hico.yaml

Thanks for your great work. There is a question haunting me about the evaluation process.
The line 139 in hico_eval.py only ensures the human and the object are rightly localized. Why does the TP not consider the object class for a TP?

@yoyomimi hi thanks for sharing the code base great work, but i had one query, currently when i tested the model for some scenes like an only person running on a beach without any other object present there is no detections/activity in the output, is there any way i can get results like people walking , fighting, waving without depending on the object present in the scene

Thanks in advance

Could u provide the final checkpoint in freezing DETR mode on HICO-DET dataset? Thanks.

can this repo use distribute training, thanks

您好，我想请问一下如果想自己制作HOI数据集，类似hoia或hico-det，可以用什么标注工具？

Dear Chen, thanks for sharing this excellent idea, and I am very grateful for you. But there is a question I want to ask you is that I have found all the metrics is 0 after I run eval.py. Could you please tell the reason? Thank you very much!

Dear Chen. Hello. May I ask how long do we need to train this model?

hello, could you please release the vcoco version code, thanks!

The HOI-A test set used in AS-Net is test_2019.zip or test_2021_5_16_final.zip in the google link you provide? Thanks

Dear Chen, thanks for sharing your excellent idea, after reading the paper, I have a question about Qr and Qd, are these two learnable variables randomly initialized?

Thanks for your great work, but I am bit confused about the Known Object Evaluation mode. Is is possible to release the code for this?

HI thanks for providing nice work!
I currently do some projects in HOI using V-COCO.
I wonder could you provide me a rel_np.py for V-COCO.

Hello Mingfei Chen, everything works normally when I use single GPU for training, but when I use multiple GPUs to train HOIA dataset, I encounter a problem, I would like to ask you how to solve it,there is a problem with the image shape of the input model

RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[8, 1, 864, 1251] to have 3 channels, but
got 1 channels instead

Hi, thanks for your work!
When I eval on hoia dataset, I got this ERROR:
bash eval_hoia.sh

python tools/eval.py --cfg configs/hoia.yaml \
    MODEL.RESUME_PATH checkpoints/ASNet_hoia_res50.pth

RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[1, 2, 800, 1066] to have 3 channels, but got 2 channels instead

But I print the img size at

def evaluate(self, eval_loader, mode, rel_topk=100):
        self.model.eval()
        results = []
        count = 0
        for data in tqdm(eval_loader):
            imgs, targets, filenames = data
            imgs = [img.to(self.device) for img in imgs]
            # targets are list type
            targets = [{k: v.to(self.device) for k, v in t.items()} for t in targets]
            bs = len(imgs)
            target_sizes = targets[0]['size'].expand(bs, 2)
            target_sizes = target_sizes.to(self.device)
            print("====================", imgs[0].size())
            outputs_dict = self.model(imgs)
            file_name = filenames[0]
            pred_out = self.postprocessors(outputs_dict, file_name, target_sizes,
                rel_topk=rel_topk)
            results.append(pred_out)
            count += 1

I got (3, 800, 1066). But in model forward, channel size changes to 2 ?
Please help me~
I used ASNet_hoia_res50.pth on HOIA dataset

thank you very much.