luminoth
luminoth copied to clipboard
tryolabs
Deep Learning toolkit for Computer Vision.
# Feature Request I want to obtain the evaluation of different datasets of a single job ` lumi eval -h && lumi eval -c config_ssd.yml --split valid --split train --split...
When we are trying to train luminoth by using ssd/fasterrcnn on our own dataset and constantly tweaking the training configurations and retraining multiple times, it really helps if we can...
I want to bring to attention, the following code snippet - https://github.com/tryolabs/luminoth/blob/master/luminoth/models/base/base_network.py#L69-L101 In the above snippet 1. vgg_16 is declared without specifying num_classes meaning it gets built with the default...
train.yml: ``` train: run_name: fashion-train-2 job_dir: C:\workspaces\geco\faster-rcnn-object-detect\coco\jobs-gpu\ dataset: type: object_detection dir: C:\workspaces\geco\faster-rcnn-object-detect\coco\tf model: type: ssd network: num_classes: 3 ``` after 1000 steps: ``` INFO:tensorflow:finished training after 10000 epoch limit INFO:tensorflow:Saving...
Hi, I got the predict function to work with only the cpu, but when I run with gpu it just returns nothing. This is what I am getting in the...
Investigate if with the job id alone, we are able to get stuff like: ```json { "scaleTier": "BASIC_GPU", "packageUris": [ "gs://luminoth-alan-train-jobs/lumi_train_20180815_173243/packages/luminoth-0.1.3.dev1.tar.gz" ], "pythonModule": "luminoth.train", "args": [ "--config", "gs://luminoth-alan-train-jobs/lumi_train_20180815_173243/config.yml" ], "region":...
It was build as a debugging tool but it adds real value when being able to view intermediate images in TensorBoard. We should: - [ ] Revamp the code -...
I could not find the guidelines for writing my own conversion tool on a new dataset.
