Caffe Log Visualization

1.Record your train/test log as a log file

TOOLS=./build/tools  
GLOG_logtostderr=0 GLOG_log_dir=caffe/Log/   

TOOLS/caffe train --solver=caffe/solver.prototxt  

2.Parse you log file

./parse_log.sh caffe.train.log  

3.Save plot results

./plot_training_log.py.example 6 train.png log_file/caffe.bin.ubuntu.rlcheng.log 

Paramaters:

Notes:  
    1. Supporting multiple logs.  
    2. Log file name must end with the lower-cased ".log".  
--------------------------------------------------
Supported chart types:  
    0: Test accuracy  vs. Iters  
    1: Test accuracy  vs. Seconds  
    2: Test loss  vs. Iters  
    3: Test loss  vs. Seconds  
    4: Train learning rate  vs. Iters  
    5: Train learning rate  vs. Seconds  
    6: Train loss  vs. Iters  
    7: Train loss  vs. Seconds  

你可能感兴趣的:(Caffe,Deep,Learning)