two-stream-action-recognition

two-stream-action-recognition copied to clipboard

UnicodeDecodeError: 'ascii' codec can't decode byte 0xd0 in position 0: ordinal not in range(128)

2

i try to reload the spatial model but it's not useful,,,..... the report errors as follows: torch.Size([3, 224, 224]) ==> Validation data :71877frames torch.Size([3, 224, 224]) ==> Build model and...

fcxmcc

Can l use the two stream model as a feature extractor ?

1

Hello, thank you for your work. l'm asking how can l use spatial and temporal model on UCF-101 for features extraction ? Thank you

pinkfloyd06

请问frame_count.pickle文件是如何生成的，谢谢

2

JWZhao-uestc

syfffffff

pickle文件怎么生成的，具体都要包括什么内容啊，谢谢

1

syfffffff

Dear jeffreyyihuang: Base your code,I don't clear how to make Spatial input data -> rgb frames, and how to make ture below load_ucf_image function ` def load_ucf_image(self,video_name, index): if video_name.split('_')[0]...

inkplatform

spatial_cnn overfitting

5

hello all, when i run the spatial_cnn.py, i found the loss function for test is very strange. does someone have the same problem? many thanks! 

Robinxin123

how can i use this code in Win10?

1

Thanks for you kindly sharing. Can I use run the pretrained model in Win10?

goforfar

Dear friend, the link of pretrained model has lost, could you please share a new link with me again? Thank you very much!

wuyifujia

博主你好，GitHub上公布预训练模型无法下载，能不能发我邮箱一份[email protected]

18

博主你好，GitHub上公布预训练模型无法下载，能不能发我邮箱一份[email protected]

zhangjia3