- Notifications
You must be signed in to change notification settings - Fork37
NanoNets/RaspberryPi-ObjectDetection-TensorFlow
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Script for object detection from training new model on dataset to exporting quantized graph
This is the fastest way to use the repo
# For cpudocker pull docker.nanonets.com/pi_training# For gpudocker pull docker.nanonets.com/pi_training:gpuOR
Should run this script from repository root
# For cpudocker build -t pi_training -f docker/Dockerfile.training .docker image tag pi_training docker.nanonets.com/pi_training# For gpudocker build -t pi_training:gpu -f docker/Dockerfile.training.gpu .docker image tag pi_training:gpu docker.nanonets.com/pi_training:gpuDataset for object detection consists of images of objects you want to detect and annotations which are xml files with coordinates of objects inside images in Pascal VOC format. If you have collected images, you can use tool likeLabelImg to create dataset.
Copy dataset withimages folder containing all training images andannotations folder containing all respective annotations insidedata folder in repo which will be mounted by docker as volume
Tensorboard will be started at port 8000 and run in backgroundYou can specify -h parameter to get help for docker script
If you have a GPU instance, you need to installnvidia-docker
# For cpusudo docker run -p 8000:8000 -v `pwd`/data:/data docker.nanonets.com/pi_training -m train -a ssd_mobilenet_v1_coco -e ssd_mobilenet_v1_coco_0 -p '{"batch_size":8,"learning_rate":0.003}'# For gpusudo nvidia-docker run -p 8000:8000 -v `pwd`/data:/data docker.nanonets.com/pi_training:gpu -m train -a ssd_mobilenet_v1_coco -e ssd_mobilenet_v1_coco_0 -p '{"batch_size":8,"learning_rate":0.003}'The docker instance on startup runs a script run.sh which takes the following parameters:
run.sh [-m mode] [-a architecture] [-h help] [-e experiment_id] [-c checkpoint] [-p hyperparameters]-h display this help and exit-m mode: should be either `train` or `export`-p key value pairs of hyperparameters as json string-e experiment id. Used as path inside data folder to run current experiment-c applicable when mode is export, used to specify checkpoint to use for exportList of Models (that can be passed to -a):
- ssd_mobilenet_v1_coco
- ssd_inception_v2_coco
- faster_rcnn_inception_v2_coco
- faster_rcnn_resnet50_coco
- rfcn_resnet101_coco
- faster_rcnn_resnet101_coco
- faster_rcnn_inception_resnet_v2_atrous_coco
- faster_rcnn_nas
Possible hyperparameters to override from -p command in json
| Name | Type |
|---|---|
| learning_rate | float |
| batch_size | int |
| train_steps | int |
| eval_steps | int |
This command would export trained model in quantized graph that can be used for prediction. You need to specify one of the trained checkpoints from experiment directory that you want to use for prediction with -c command as follows:
# For cpusudo docker run -v `pwd`/data:/data docker.nanonets.com/pi_training -m export -a ssd_mobilenet_v1_coco -e ssd_mobilenet_v1_coco_0 -c /data/0/model.ckpt-8998# For gpusudo nvidia-docker run -v `pwd`/data:/data docker.nanonets.com/pi_training:gpu -m export -a ssd_mobilenet_v1_coco -e ssd_mobilenet_v1_coco_0 -c /data/0/model.ckpt-8998Once your done training the model and have exported it you can move this onto a client device like the Raspberry Pi.For details of how to use on the Raspberry Pi click seehttps://github.com/NanoNets/TF-OD-Pi-Test
About
Object Detection using TensorFlow on a Raspberry Pi
Topics
Resources
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Releases
Packages0
Contributors2
Uh oh!
There was an error while loading.Please reload this page.