JimLee1996

Sorry, I don't have time. You could google it or refer to other project.

`print(y)`

Since we adopt CELoss(https://pytorch.org/docs/stable/nn.html#torch.nn.CrossEntropyLoss), the output value is not probability. However, you can utilize the signs and abs() values to evaluate how sure the model is about this category.

Try SoftMax. Please inform me if it is feasible. `exp(1.9981)/(exp(1.9981)+exp(-1.9514))=0.98`?

放出来是为了让大家能看到我精简的过程，以后都可以自己选择性使用。 主要使用了opkg和binwalk工具。具体内容参见 [配置过程](https://github.com/JimLee1996/K2P-FW/blob/master/README.md)和[Commits](https://github.com/JimLee1996/K2P-FW/commits/master)

please see https://github.com/JimLee1996/AVSS2019/tree/master/src/Demo

Yep

We use deep learning methods to do this job. 3DCNNs are proved to be effective on learning spatio-temporal features. Here we introduce DenseNet architecture to better learn the motion pattern...

Use softmax. Please refer to https://github.com/JimLee1996/AVSS2019/issues/2.

mt7621是双核四线程，所以负载应该为1.34/4大约为29%左右吧。