diff options
Diffstat (limited to 'backend/microservice/api')
| -rw-r--r-- | backend/microservice/api/controller.py | 18 | ||||
| -rw-r--r-- | backend/microservice/api/newmlservice.py | 10 |
2 files changed, 19 insertions, 9 deletions
diff --git a/backend/microservice/api/controller.py b/backend/microservice/api/controller.py index 437690ee..f0f36907 100644 --- a/backend/microservice/api/controller.py +++ b/backend/microservice/api/controller.py @@ -1,4 +1,6 @@ +from cmath import log from dataclasses import dataclass +from distutils.command.upload import upload from gc import callbacks from xmlrpc.client import DateTime import flask @@ -31,16 +33,24 @@ class Predictor: class train_callback(tf.keras.callbacks.Callback): - def __init__(self, x_test, y_test): + def __init__(self, x_test, y_test,modelId): self.x_test = x_test self.y_test = y_test + self.modelId=modelId # def on_epoch_end(self, epoch, logs=None): - print(epoch) + #print('Evaluation: ', self.model.evaluate(self.x_test,self.y_test),"\n") + + #print(epoch) + + #print(logs) + #ml_socket.send(epoch) #file = request.files.get("file") url = config.api_url + "/Model/epoch" - requests.post(url, epoch).text + r=requests.post(url, json={"Stat":str(logs),"ModelId":str(self.modelId),"EpochNum":epoch}).text + + #print(r) #print('Evaluation: ', self.model.evaluate(self.x_test,self.y_test),"\n") #broj parametara zavisi od izabranih metrika loss je default @app.route('/train', methods = ['POST']) @@ -63,7 +73,7 @@ def train(): url = config.api_url + "/file/h5" files = {'file': open(filepath, 'rb')} - r=requests.post(url, files=files) + r=requests.post(url, files=files,data={"uploaderId":paramsExperiment['uploaderId']}) fileId=r.text predictor = Predictor( _id = "", diff --git a/backend/microservice/api/newmlservice.py b/backend/microservice/api/newmlservice.py index 585db480..a9bce3bb 100644 --- a/backend/microservice/api/newmlservice.py +++ b/backend/microservice/api/newmlservice.py @@ -252,7 +252,7 @@ def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback): opt=tf.keras.optimizers.RMSprop(learning_rate=params['learningRate']) ###REGULARIZACIJA - #regularisation={'kernelType':'l1 ili l2 ili l1_l2','krenelRate':default=0.01 ili jedna od vrednosti(0.0001,0.001,0.1,1,2,3) ili neka koju je korisnik zadao,'biasType':'','biasRate':'','activityType','activityRate'} + #regularisation={'kernelType':'l1 ili l2 ili l1_l2','kernelRate':default=0.01 ili jedna od vrednosti(0.0001,0.001,0.1,1,2,3) ili neka koju je korisnik zadao,'biasType':'','biasRate':'','activityType','activityRate'} reg=params['regularisation'] ###Kernel @@ -279,7 +279,7 @@ def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback): elif(reg['kernelType']=='l1l2'): activityreg=tf.keras.regularizers.l1_l2(l1=reg['activityRate'][0],l2=reg['activityRate'][1]) """ - filepath=os.path.join("temp/",paramsExperiment['_id']+"_"+paramsModel['_id']) + filepath=os.path.join("temp/",paramsExperiment['_id']+"_"+paramsModel['_id']+".h5") if(problem_type=='multi-klasifikacioni'): #print('multi') classifier=tf.keras.Sequential() @@ -294,7 +294,7 @@ def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback): classifier.compile(loss =paramsModel["lossFunction"] , optimizer = paramsModel['optimizer'] , metrics =paramsModel['metrics']) - history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=paramsModel['batchSize']) + history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=paramsModel['batchSize'],callbacks=callback(x_test, y_test,paramsModel['_id'])) hist=history.history #plt.plot(hist['accuracy']) @@ -326,7 +326,7 @@ def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback): classifier.compile(loss =paramsModel["lossFunction"] , optimizer = paramsModel['optimizer'] , metrics =paramsModel['metrics']) - history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=paramsModel['batchSize']) + history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=paramsModel['batchSize'],callbacks=callback(x_test, y_test,paramsModel['_id'])) hist=history.history y_pred=classifier.predict(x_test) y_pred=(y_pred>=0.5).astype('int') @@ -352,7 +352,7 @@ def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback): classifier.compile(loss =paramsModel["lossFunction"] , optimizer = paramsModel['optimizer'] , metrics =paramsModel['metrics']) - history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=paramsModel['batchSize']) + history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=paramsModel['batchSize'],callbacks=callback(x_test, y_test,paramsModel['_id'])) hist=history.history y_pred=classifier.predict(x_test) #print(classifier.evaluate(x_test, y_test)) |