GitHub - TronicLT/lrcn_activity_recognition: Modified code to based on the LRCN code.

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
README.txt		README.txt
action_hash_rev.p		action_hash_rev.p
classify_video.py		classify_video.py
create_flow_images_LRCN.m		create_flow_images_LRCN.m
deploy_lstm.prototxt		deploy_lstm.prototxt
deploy_singleFrame.prototxt		deploy_singleFrame.prototxt
extract_frames.sh		extract_frames.sh
lstm_solver_RGB.prototxt		lstm_solver_RGB.prototxt
lstm_solver_flow.prototxt		lstm_solver_flow.prototxt
run_lstm_RGB.sh		run_lstm_RGB.sh
run_lstm_flow.sh		run_lstm_flow.sh
run_singleFrame_RGB.sh		run_singleFrame_RGB.sh
run_singleFrame_flow.sh		run_singleFrame_flow.sh
sequence_input_layer.py		sequence_input_layer.py
singleFrame_solver_RGB.prototxt		singleFrame_solver_RGB.prototxt
singleFrame_solver_flow.prototxt		singleFrame_solver_flow.prototxt
test_flow_singleFrame.out		test_flow_singleFrame.out
train_test_lstm_RGB.prototxt		train_test_lstm_RGB.prototxt
train_test_lstm_flow.prototxt		train_test_lstm_flow.prototxt
train_test_singleFrame_RGB.prototxt		train_test_singleFrame_RGB.prototxt
train_test_singleFrame_flow.prototxt		train_test_singleFrame_flow.prototxt
ucf101_singleFrame_RGB_test_split1.txt		ucf101_singleFrame_RGB_test_split1.txt
ucf101_singleFrame_RGB_train_split1.txt		ucf101_singleFrame_RGB_train_split1.txt
ucf101_singleFrame_flow_test_split1.txt		ucf101_singleFrame_flow_test_split1.txt
ucf101_singleFrame_flow_train_split1.txt		ucf101_singleFrame_flow_train_split1.txt
ucf101_split1_testVideos.txt		ucf101_split1_testVideos.txt
ucf101_split1_trainVideos.txt		ucf101_split1_trainVideos.txt

Repository files navigation

This code should help you reimplement the experiments in:

Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., & Darrell, T. (2014). Long-term recurrent convolutional networks for visual recognition and description. arXiv preprint arXiv:1411.4389.
Chicago	

Please see http://www.eecs.berkeley.edu/~lisa_anne/LRCN_video for detailed instructions on how to reimplement experiments and download pre-trained models.