msracver
How to train Deep Feature Flow on another dataset (2-labels)
After i read the codes,I found that Train Deep Feature Flow trained on DET and VID (30 classes). Now,I want to train the net on dataset of 2 classes. I have labeled the dataset as the format of VID. How to remove the part of DET, and just train my 2 classes dataset?
@Jessespace I also encountered the same problem. I want to train my data set with DFF, but I haven't downloaded ILSVRC2015 VID data set yet. I don't know what format the data set is. Can you send some data sets? Let me see the format? My mailbox: [email protected],thank you very much!
U can just make your datasets as the DET/VID format, or u can change the data loading codes.....
U can just make your datasets as the DET/VID format, or u can change the data loading codes.....
I have tried and succeed. But honestly，the mAP is very slow,have you some advices for adjusting the param?Thanks.
@Jessespace I also encountered the same problem. I want to train my data set with DFF, but I haven't downloaded ILSVRC2015 VID data set yet. I don't know what format the data set is. Can you send some data sets? Let me see the format? My mailbox: [email protected],thank you very much!
download link:http://bvisionweb1.cs.unc.edu/ilsvrc2015/download-videos-3j16.php#vid I'm sorry because the dataset is very big,the dataset contains video snippets ,train images,test images,val images, Annotations,and some other scripts. The annotation format likes PASCAL VOC,
@Jessespace I also encountered the same problem. I want to train my data set with DFF, but I haven't downloaded ILSVRC2015 VID data set yet. I don't know what format the data set is. Can you send some data sets? Let me see the format? My mailbox: [email protected],thank you very much!
download link:http://bvisionweb1.cs.unc.edu/ilsvrc2015/download-videos-3j16.php#vid I'm sorry because the dataset is very big,the dataset contains video snippets ,train images,test images,val images, Annotations,and some other scripts. The annotation format likes PASCAL VOC,
Thank you for reminding. I have downloaded the dataset.
@Jessespace
U can just make your datasets as the DET/VID format, or u can change the data loading codes.....
I have tried and succeed. But honestly，the mAP is very slow,have you some advices for adjusting the param?Thanks.
Did you train your data set successfully? I also want to train my own data set. The data set has been completed according to the VID format and changed some code that needs to be changed. But the training is still wrong. Can you add my QQ: 1304020120 ? I would like to ask you for advice.