资源算法detectron-trainings-visualization

detectron-trainings-visualization

2020-03-05 | |  59 |   0 |   0

Detectron trainings visualization

With this software you can visualize your Detectron training process. The software reads the accuracy, the loss, the loss_cls and the loss_bbox.

To get started just unpack the vis-tool.zip and start the "train-vis.jar" in the zip-folder "vis-tool.zip".

When you train you network just save the standard out into a file and paste it into the software directory. For example use this command:

python2 tools/train_net.py --cfg path/to/config/file.yaml OUTPUT_DIR path/to/output/directory | tee /home/ubuntu/output/trainingsoutput.txt

You can configure the chart with the form at the start of the tool. Select the higher boundaries as well as the ticks and choose which data you want to show. You can also create a linear regression of the accuracy.

When you run the software you should get a chart like this:

For more information visit my website.

References


上一篇:VoVNet-Detectron

下一篇:detectron2-licenseplates

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...