kracwarlock / action-recognition-visual-attention

Action recognition using soft attention based deep recurrent neural networks
http://www.cs.toronto.edu/~shikhar/projects/action-recognition-attention
351 stars 158 forks source link

How to get the dataset? #15

Closed cumtwb closed 7 years ago

cumtwb commented 8 years ago

How did you require the dataset? just like train_features.h5, train_framenum.txt and train_labels.txt, etc. self.data_file = '/ais/gobi3/u/shikhar/ucf11/dataset/train_features.h5' self.num_frames_file = '/ais/gobi3/u/shikhar/ucf11/dataset/train_framenum.txt' self.labels_file = '/ais/gobi3/u/shikhar/ucf11/dataset/train_labels.txt' self.vid_name_file = '/ais/gobi3/u/shikhar/ucf11/dataset/train_filename.txt' self.dataset_name = 'features' I don't know how to get these? Download from web or generate these yourself? Could you tell me the method. Thanks.

kracwarlock commented 8 years ago

The file format for these is provided at https://github.com/kracwarlock/action-recognition-visual-attention/blob/master/util/README.md

I uploaded some of these scripts in #2, #6 and #1 Let me know if there is any other issue

ozgemercanoglu commented 6 years ago

Dear @kracwarlock, could you please share train_filename.txt, train_labels.txt, train_framenum.txt and train_features.h5 for HMDB-51 dataset?