euwern

I am unable to reproduce the correct inception score.

I get the following error, after uncmment line 31. Undefined variable "caffe" or class "caffe.init_log". Error in script_faster_rcnn_demo (line 31) caffe.init_log(fullfile(pwd, 'caffe_log')); Error in run (line 63) evalin('caller', [script ';']);

The external/caffe file was empty in my source (hence I grabbed caffe from the original source). I removed the entire faster_rcnn directory and start from scratch. The following is what...

no i did not, I just switch to the python version of faster rcnn, and it works fine for me. https://github.com/rbgirshick/py-faster-rcnn note: py-faster-rcnn is working for me on ubuntu. remember...

> Thanks for your comment! The code is coming soon. The sample code and segments are currently in my Dropbox link [here](https://www.dropbox.com/s/jhhbb5r174hj2jq/miou_calculation_example.zip?dl=0). > > ``` > $ python miou_calculation.py --bsd500...

See lines 307 (base_lr) and 311 (proxy_lr). These values are set in the config file (e.g.: cub.json - lines 43 (proxy_lr) and line 46 (base_lr)).

It is used by the optimizer (train.py - line 290 ) "config['opt']['type']", which is defined in the config file (cub.json - line 33) "torch.optim.Adam". Do checkout the Pytorch documentation regarding...