Hi,
I can run the tensorboard in the output directory. But couldn’t see the AP values and validation values. Based on the train loss and validation loss , i can predict the model is over fitting or not … How to see the validation values in the tensorboard
Which network did you use for training?
Now using Detectnet_v2…
I couldn’t even find training logs when i used retinanet
in Retinanet , i can see the following files in the result directory
retinanet_training_log_resnet.csv weights
So there is no log files. if i run tensorboard on this directory , then i can see the folllowig error in the localhost (tensorboard --logdir . --port 16002
)
### No dashboards are active for the current data set.
Probable causes:
* You haven’t written any data to your event files.
* TensorBoard can’t find your event files.
If you’re new to using TensorBoard, and want to find out how to add data and set up your event files, check out the [README](https://github.com/tensorflow/tensorboard/blob/master/README.md) and perhaps the [TensorBoard tutorial](https://www.tensorflow.org/get_started/summaries_and_tensorboard).
If you think TensorBoard is configured properly, please see [the section of the README devoted to missing data problems](https://github.com/tensorflow/tensorboard/blob/master/README.md#my-tensorboard-isnt-showing-any-data-whats-wrong) and consider filing an issue on GitHub.
*Last reload: Tue Jun 09 2020 11:56:03 GMT+0530 (India Standard Time)*
*Data location: .*
OK, so there should be no event files. That’s expected. There are event files only in detectnet_v2 network.