- Source-codes about ETRI KSB framework.
- 2nd Prize!
- Predict public bicycle demand
- Learn random forest model using Tashu 2013-2015 dataset
- Model using R.F. based on tashu history
./random_forest_train_local/random_forest_init.py --input ./data/history --model ./model/ --checkpoint ./checkpoint/local
$ saved_model_cli show --dir ./model/1/ --all
MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:
signature_def['predict']:
The given SavedModel SignatureDef contains the following input(s):
inputs['x'] tensor_info:
dtype: DT_FLOAT
shape: (-1, 8)
name: Placeholder:0
The given SavedModel SignatureDef contains the following output(s):
outputs['y'] tensor_info:
dtype: DT_FLOAT
shape: (-1, -1)
name: probabilities:0
Method name is: tensorflow/serving/predict
docker run --rm -p 8501:8501 -v MODELPATH:MODELPATHINDOCKER -e MODEL_NAME=tashu tensorflow/serving
curl -i -d '{"signature_name": "predict", "instances": [[1,0.0,0.0,0.0,0.0,0.0,0.0,0.0]]}' http://IPADDRESS:PORT/v1/models/default:predict