Skip to content

Latest commit

 

History

History
 
 

vehicle-detection

readme.md

Vehicle Detection

Models that are able to detect vehicles.

Model Name Complexity (GFLOPs) Size (Mp) AP @ [IoU=0.50:0.95] (%) Links GPU_NUM
vehicle-detection-0200 0.82 1.83 25.4 snapshot, model template 4
vehicle-detection-0201 1.84 1.83 32.3 snapshot, model template 4
vehicle-detection-0202 3.28 1.83 36.9 snapshot, model template 4
vehicle-detection-0203 112.34 24.11 43.8 snapshot, model template) 4
vehicle-detection-0204 190.32 34.15 47.3 snapshot, model template) 4

Average Precision (AP) is defined as an area under the precision/recall curve.

Training pipeline

0. Change a directory in your terminal to object_detection.

cd <training_extensions>/pytorch_toolkit/object_detection

If You have not created virtual environment yet:

./init_venv.sh

Else:

. venv/bin/activate

or if You use conda:

conda activate <environment_name>

1. Select a model template file and instantiate it in some directory.

export MODEL_TEMPLATE=`realpath ./model_templates/vehicle-detection/vehicle-detection-0200/template.yaml`
export WORK_DIR=/tmp/my_model
python ../tools/instantiate_template.py ${MODEL_TEMPLATE} ${WORK_DIR}

2. Collect dataset

Collect or download images with vehicles presented on them. One can download MS-COCO dataset and remain images with cars only.

export DATA_DIR=${WORK_DIR}/data
wget http://images.cocodataset.org/zips/val2017.zip -P ${DATA_DIR}/
wget http://images.cocodataset.org/zips/train2017.zip -P ${DATA_DIR}/
wget http://images.cocodataset.org/annotations/annotations_trainval2017.zip -P ${DATA_DIR}/
unzip ${DATA_DIR}/val2017.zip -d ${DATA_DIR}/
unzip ${DATA_DIR}/train2017.zip -d ${DATA_DIR}/
unzip ${DATA_DIR}/annotations_trainval2017.zip -d ${DATA_DIR}/
python ../../../external/mmdetection/tools/coco_filter.py ${DATA_DIR}/annotations/instances_train2017.json ${DATA_DIR}/annotations/instances_train2017car.json --filter car --remap
python ../../../external/mmdetection/tools/coco_filter.py ${DATA_DIR}/annotations/instances_val2017.json ${DATA_DIR}/annotations/instances_val2017car.json --filter car --remap
sed -i "s/car/vehicle/g" ${DATA_DIR}/annotations/instances_val2017car.json
sed -i "s/car/vehicle/g" ${DATA_DIR}/annotations/instances_train2017car.json

3. Prepare annotation

Annotate dataset and save annotation to MSCOCO format with vehicle as the only one class.

4. Change current directory to directory where the model template has been instantiated.

cd ${WORK_DIR}

5. Training and Fine-tuning

Try both following variants and select the best one:

  • Training from scratch or pre-trained weights. Only if you have a lot of data, let's say tens of thousands or even more images. This variant assumes long training process starting from big values of learning rate and eventually decreasing it according to a training schedule.

  • Fine-tuning from pre-trained weights. If the dataset is not big enough, then the model tends to overfit quickly, forgetting about the data that was used for pre-training and reducing the generalization ability of the final model. Hence, small starting learning rate and short training schedule are recommended.

  • If you would like to start training from pre-trained weights use --load-weights pararmeter.

    python train.py \
   --load-weights ${WORK_DIR}/snapshot.pth \
   --train-ann-files ${TRAIN_ANN_FILE} \
   --train-data-roots ${TRAIN_IMG_ROOT} \
   --val-ann-files ${VAL_ANN_FILE} \
   --val-data-roots ${VAL_IMG_ROOT} \
   --save-checkpoints-to ${WORK_DIR}/outputs

    Also you can use parameters such as --epochs, --batch-size, --gpu-num, --base-learning-rate, otherwise default values will be loaded from ${MODEL_TEMPLATE}.

  • If you would like to start fine-tuning from pre-trained weights use --resume-from parameter and value of --epochs have to exceed the value stored inside ${MODEL_TEMPLATE} file, otherwise training will be ended immediately. Here we add 5 additional epochs.

    export ADD_EPOCHS=5
export EPOCHS_NUM=$((`cat ${MODEL_TEMPLATE} | grep epochs | tr -dc '0-9'` + ${ADD_EPOCHS}))

python train.py \
   --resume-from ${WORK_DIR}/snapshot.pth \
   --train-ann-files ${TRAIN_ANN_FILE} \
   --train-data-roots ${TRAIN_IMG_ROOT} \
   --val-ann-files ${VAL_ANN_FILE} \
   --val-data-roots ${VAL_IMG_ROOT} \
   --save-checkpoints-to ${WORK_DIR}/outputs \
   --epochs ${EPOCHS_NUM}

6. Evaluation

Evaluation procedure allows us to get quality metrics values and complexity numbers such as number of parameters and FLOPs.

To compute MS-COCO metrics and save computed values to ${WORK_DIR}/metrics.yaml run:

python eval.py \
   --load-weights ${WORK_DIR}/outputs/latest.pth \
   --test-ann-files ${VAL_ANN_FILE} \
   --test-data-roots ${VAL_IMG_ROOT} \
   --save-metrics-to ${WORK_DIR}/metrics.yaml

You can also save images with predicted bounding boxes using --save-output-to parameter.

python eval.py \
   --load-weights ${WORK_DIR}/outputs/latest.pth \
   --test-ann-files ${VAL_ANN_FILE} \
   --test-data-roots ${VAL_IMG_ROOT} \
   --save-metrics-to ${WORK_DIR}/metrics.yaml \
   --save-output-to ${WORK_DIR}/output_images

7. Export PyTorch* model to the OpenVINO™ format

To convert PyTorch* model to the OpenVINO™ IR format run the export.py script:

python export.py \
   --load-weights ${WORK_DIR}/outputs/latest.pth \
   --save-model-to ${WORK_DIR}/export

This produces model model.xml and weights model.bin in single-precision floating-point format (FP32). The obtained model expects normalized image in planar BGR format.

For SSD networks an alternative OpenVINO™ representation is saved automatically to ${WORK_DIR}/export/alt_ssd_export folder. SSD model exported in such way will produce a bit different results (non-significant in most cases), but it also might be faster than the default one. As a rule SSD models in Open Model Zoo are exported using this option.

8. Validation of IR

Instead of passing snapshot.pth you need to pass path to model.bin (or model.xml).

python eval.py \
   --load-weights ${WORK_DIR}/export/model.bin \
   --test-ann-files ${VAL_ANN_FILE} \
   --test-data-roots ${VAL_IMG_ROOT} \
   --save-metrics-to ${WORK_DIR}/metrics.yaml