andrewowens multisensory issues

andrewowens / multisensory

Code for the paper: Audio-Visual Scene Analysis with Self-Supervised Multisensory Features

http://andrewowens.com/multisensory/

Apache License 2.0

220 stars 61 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

difference between "large" and "full" sep models

#47 sanjeelparekh opened 2 years ago
0
Download sample-data.zip NOT FOUND

#46 elinaoikonomaki opened 2 years ago
1
model architecture

#45 riyaj8888 opened 3 years ago
1
Download pretrain models

#44 WikiChao opened 3 years ago
3
Question about the original audio waveform input

#43 luhuijun666 closed 3 years ago
0
Question about the test in Table 2 GRID transfer

#42 ruizewang opened 4 years ago
0
How to calculate SDR?

#41 ruizewang opened 4 years ago
1
Improvement on using pretrained model

#40 ChaitanyaBoggavarapu opened 4 years ago
0
Questions about sourcesep.py

#39 ruizewang opened 4 years ago
2
What GPU used?

#38 ruizewang closed 4 years ago
0
duration_mult flag

#37 kzhang3256 opened 5 years ago
0
Questions about VoxCeleb2 dataset

#36 YiyuLuo opened 5 years ago
1
Issue on datasets

#35 LindaCY opened 5 years ago
1
Some questions about training and testing shift model

#34 ruizewang opened 5 years ago
0
Issue with sound source localization

#33 jacobsharp10 opened 5 years ago
1
Issue on Large Videos

#32 ChaitanyaBoggavarapu closed 5 years ago
2
Why acc doesn't change when shift_model training?

#31 ruizewang opened 5 years ago
10
What are feats['im_0'] and feats['im_1'] of example for shift model?

#30 ruizewang closed 5 years ago
2
About the input file for shift model training

#29 ruizewang opened 5 years ago
0
Could you provide the dataset?

#28 ruizewang closed 5 years ago
0
Add Dockerfile and requirepment.txt

#27 meokz opened 5 years ago
0
What is the format of the tensor in the code?

#26 tuffr5 closed 5 years ago
0
In which way the video frames combine

#25 tuffr5 closed 5 years ago
10
I RuntimeError: Command failed! ffmpeg -i "/tmp/ao_wmjz0ezg.wav" -r 29.970000 -loglevel warning -safe 0 -f concat -i "/tmp/ao_i2pwi0b8.txt" -pix_fmt yuv420p -vcodec h264 -strict -2 -y -acodec aac "results/fg_translator.mp4"

#24 ghost closed 5 years ago
4
question about using 'sep_example.tf'

#23 wl3b10s opened 5 years ago
2
> > In the source separation model it seems like you are using *.tf files as input (rec_files_from_path in sep_dset.py).Can you please provide the format to create those TFRecord files

#22 xuanhanyu opened 5 years ago
0
question about sourcesep training result on new dataset

#21 xiaoyiming opened 5 years ago
7
file input for blind audio source separation

#20 prashantmaheshwari94 opened 5 years ago
1
Question about the test in Table 3

#19 THU-cui opened 5 years ago
1
Questions about the files in ".txt" format used to train the "shift" model

#18 yxixi opened 5 years ago
2
How to train the "shift" and "cam" model for sound source location?

#17 yxixi opened 5 years ago
4
Question about the shift_net.py' training

#16 xiaoyiming opened 5 years ago
3
whre is the sep_module (calss or funtion）in sourcesep.py

#15 xiaoyiming opened 5 years ago
3
Questions about the entrance of the training function

#14 yxixi opened 5 years ago
1
Test set used in paper

#13 medhini opened 5 years ago
0
Update README.md

#12 vcuculo opened 5 years ago
0
About the input format

#11 ASHA-KOTERU opened 6 years ago
6
error compiling

#10 Askdeep closed 6 years ago
0
Question about training

#9 Lugangz opened 6 years ago
10
make_video_helper() missing 3 required positional arguments: 'x', 'in_dir', and 'tmp_ext'

#8 Lugangz opened 6 years ago
1
TypeError: convolution() got multiple values for argument 'weights_regularizer'

#7 chouqin3 closed 5 years ago
5
Questions about the models

#6 orthosiphon opened 6 years ago
3
RuntimeError: Command failed! ffmpeg -i "/tmp/ao_M0QAze.wav" -r 29.970000 -loglevel warning -safe 0 -f concat -i "/tmp/ao_cnpblR.txt" -pix_fmt yuv420p -vcodec h264 -strict -2 -y -acodec aac "../results/fg_cam_translator.mp4"

#5 xsingit closed 6 years ago
4
Supported on Linux

#4 rsmithgi opened 6 years ago
0
Question about fine-tune for full sep model

#3 LionnelBall opened 6 years ago
3
How do I run source separation on a different video?

#2 jayavanth closed 6 years ago
2
Getting /bin/sh: 1: ffmpeg-length: not found

#1 jayavanth closed 6 years ago
2