bravewhh

> Hi, I have not trained MobileNetV2 on UCF by myself. I would suggest you fine-tune from the Kinetics pre-trained weights since smaller models are generally more difficult to train....

> > > > @mkocabas @mayoudong1993 This problem should not be from pyrender. The biggest problem is the code : os.environ['PYOPENGL_PLATFORM'] = 'egl' in [demo.py](https://github.com/mkocabas/VIBE/blob/cee26151ea880ea7547e78afd7faff92b102a353/demo.py#L18). > > > > It...

When I used the steps provided by Deepstream YOLO to convert the YOLO model from ONNX to Engine, I received the following error message:  May I ask what I...

> Yes, it supports. Which YOLO model is this error? it's yolov5n model

你好，我想问一下到底哪个才是pytorch版本？

> 为什么两个eco lite和eco full在第一个测试集上的top1精度与原论文差了10%左右，试过很多次了， > https://github.com/mzolfaghari/ECO-pytorch，从这转过来的，那个没有issue。我用pytorch1.3 你好，我想问一下你的预训练模型都下载了吗？为什么我下载下来显示数据损坏呢?

> 为什么两个eco lite和eco full在第一个测试集上的top1精度与原论文差了10%左右，试过很多次了， > https://github.com/mzolfaghari/ECO-pytorch，从这转过来的，那个没有issue。我用pytorch1.3 论文中是top1精度吗，我的top5差10%左右

Hi，do you find any code about 2D-3D registration? thank you so much,looking forward you reply!

> 您好，很感谢你提供的代码，现在有一个问题，我按照你的参数去训练，预训练模型用的是eco_lite_rgb_16F_kinetics_v3.pth.tar，但是loss一直不降低 维持在4.61左右。 您好，方便发我一份预训练模型文件吗，作者提供的显示数据损坏呢

> I would like to see the results of the ECO trained model. Please share with me. Thank you very much. > 想看一下训练好的模型的结果，请大神分享一下，非常感谢。 你好，请问你训练好的精度是多少呢~交流下