layumi / 2016_person_re-ID

TOMM2017 A Discriminatively Learned CNN Embedding for Person Re-identification

Home Page:https://dl.acm.org/citation.cfm?id=3159171

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

there is an error when i am running the train_id_net_res_2stream

feixiaoyu2223 opened this issue · comments

When i run the 'train_id_net_res_2stream ',there is an error shows:
"The subscript index must be a positive integer type or a logical type.
Wrong in train_id_net_res_2stream (line 13)
net.params(net.getParamIndex('fc751f')).learningRate = 0.01;"
My enviroment is win10 +matlab2016.
Can you tell me where is the problem?Thank you.

Hi @feixiaoyu2223
Could you print

net.getParamIndex('fc751f')

It should be a positive number.

When i add this commend ,It shows:
ans =

NaN
The subscript index must be a positive integer type or a logical type.
Wrong in train_id_net_res_2stream (line 13)
net.params(net.getParamIndex('fc751f')).learningRate = 0.01;

The code seems not find the weight fc751f, which is the weight for the last classification layer.

Could you try

net = resnet52_market()
net.getParamIndex('fc751f')

It shows
ans =

214
train: epoch 01: 1/2366:错误使用 dagnn.DagNN/eval (line 83)
No variable of name 'data_2' could be found in the DAG.

出错 cnn_train_dag>processEpoch (line 223)
net.eval(inputs, params.derOutputs, 'holdOn', s < params.numSubBatches) ;

出错 cnn_train_dag (line 91)
[net, state] = processEpoch(net, state, params, 'train',opts) ;

出错 train_id_net_res_2stream (line 35)
[net,info] = cnn_train_dag(net, imdb, @GetBatch,opts) ;