jiangfeng-xiong / siamrpn-tf Goto Github PK

Hello, I find the train batchsize is 128(more than 1), but in model.py line87: z = tf.reshape(z, [filter_size, filter_size, self.embed_dim , 2 * self.anchor_nums_per_location]) , how can you reshape z like this, since z is (128, filter_size, file_size, embed_dim2anchor_nums_per_location).

Hope for your reply, thanks a lot.

Hi, when I run 'python demo.py', it shows "ImportError: No module named alexnet_tweak".
I guess alexnet_tweak is a pretrained model? How can I solve this issue?
Thanks.

There's no model_config.json.
No such file or directory: 'Logs/SiamRPN/track_model_checkpoints\model_config.json'

Hello, can you give me more details about test and train the tracking codes. Thanks very much!

Hi, your siamRPN is really great, I do have a good tracking performance with your code. However, I wonder whether you will update it to siamrpn++ or not. I am looking forward to your continuing progress. Thank you very much.!