qdinfish
qdinfish
So I need do some changes to meet the 10 steps temporal case ? I mean 120 rows (12 person *10 steps).
OK, thanks a lot. I see "window=1" is set in code. For the data format, the target shall be the label of the activity, right?
How can I extract the person‘s feature after relation layer？ eg. save them to a file
Python 2.7.6 and nvcaffe 0.16 version (https://github.com/NVIDIA/caffe)
any idea？
@stevefoy could you send protobuf-python-3.5.1.tar.gz again ? no attached file.
I got the folloiwng erro with the new code :( Please wait for tracking and ranking! about 240min + 180min Traceback (most recent call last): File "GAR.py", line 22, in...
I updated the old version code and it works fine for the CAD , but the Confusion matrix is as below, looks queue and waiting can't be differentiated. Your thougts...
I changed lr from 0.0001 to 0.00001 or 0.001, 0.8099838969404187 is the best result :(. Do you have used other trick ? Thansk a lot! Confusion matrix: [[ 98.09 0.48...
I used the same lr and batch ( batch_size=500 and init_lr=0.0001), the Acc can reach 1 and test acc is not stable , it can reach from 0.69 to 0.90....