delving-deeper-into-the-decoder-for-video-captioning icon indicating copy to clipboard operation
delving-deeper-into-the-decoder-for-video-captioning copied to clipboard

Source code for Delving Deeper into the Decoder for Video Captioning

Results 2 delving-deeper-into-the-decoder-for-video-captioning issues
Sort by recently updated
recently updated
newest added

hi, after using the checkpoint to test, the output may be the word indexes? `{'testlen': 45403, 'reflen': 46693, 'guess': [45403, 38890, 32377, 25864], 'correct': [40964, 26695, 15019, 7511]}` how to...

我根据您提供的prepare_frames.py文件抽取了视频帧后,再根据 https://github.com/WingsBrokenAngel/ECO-efficient-video-understanding 配置好了环境,同时也下载好了您在 https://github.com/WingsBrokenAngel/Semantics-AssistedVideoCaptioning 提供的模型预训练权重ECO_full_kinetics.caffemodel(经过校验MD5确定下载无误)和对应的deploy.prototxt文件,但是在使用generate_eco_feature.py生成msrvtt_eco_32_feats.npy时,发现生成的结果与您在 https://github.com/WingsBrokenAngel/Semantics-AssistedVideoCaptioning 中的msrvtt_resnext_eco.npy结果有较大差距,尤其是ECO_full的512维3D卷积特征几乎完全不同,我也去对比了generate_res_feature.py生成的msrvtt_res_32_feats.npy文件与msrvtt_resnext_eco.npy中的相应部分,发现两者差距很小,请问您在使用generate_eco_feature.py生成msrvtt_eco_32_feats.npy的过程中时进行了别的处理吗?我要怎样才能生成和您一样的msrvtt_eco_32_feats.npy文件呢?