Fengshuanglang

而且有些API你们没有更新，比如upsample2D()里面，英文官方已经提供了插值方式了，而中文没有，我顺便想问一下，Keras有没有更新记录？就是版本更新记录？我这两个月的时间由于其他原因没有登录Keras官网，这几天进来一看发现更新了很多API，但是都是我自己一点点找的发现的，想问一下有没有提供更新记录，多谢了！！！！

I have modified it ,it is because it's not match between "input_channel" of config.py and "in_channels" of train.py

666

没啥区别，就是编码器和解码器变成残差连接了

@geroge-gao your result is 1.000,Why do you think he is not very good，

@geroge-gao I know your problem,i got a same issue,you should replace you trained model in predict_c3d_ucf101.py before you start predicting it

@geroge-gao mybe you should try reducing the num of training iterations

you should trian it use pre-trained model ,it is very hard and no-rubustness if you train the C3D from scratch .why do you train it from scratch?by the way ,i...

I don't understand what you said about "use the .model file to cover the .data file simply",I can tell you what i did ,first you should download the pre-trained model(.model...

You can try to change a pre-training network，for example “sports1m_finetuning_ucf101.model”