AmingWu
AmingWu
I use the default settings. And I do not modify the code. The dataset is correct. But, I do not reproduce your result.
Could you share your trained model?
OK, I have test your model. I find the result is still wrong.
dataset_Test = SiameseTest( input_size=1024, path='/home/room/wam/P2B/trackingdata/testing', split='Test', category_name='Car', offset_BB=0, scale_BB=1.25) I only modify the path from opt.data_dir to '/home/room/wam/P2B/trackingdata/testing',
Thank you very much. I have reproduced your results. The path of training and test should be the same.
If I want to run other categories, I only need to modify parser.add_argument('--category_name', type=str, default = 'Car', help='Object to Track (Car/Pedetrian/Van/Cyclist)')?
How could obtain the test_set.json?
OK, Thank you very much
Yes, the current code is based on MPSR. But our method could be easily plugged into other methods. We will continue to update the code. Thank you very much.
Yes, it should be fusion_visual = tf.reduce_mean(text_vector * visual_f, 1) and fusion_text = tf.reduce_mean(visual_vector * text_f, 1). Please see the line 53 and 54 of fusion.py. Thank you very much.