diff --git a/exp/kerokero/prepare_data.py b/exp/kerokero/prepare_data.py
--- a/exp/kerokero/prepare_data.py
+++ b/exp/kerokero/prepare_data.py
@@ -113,6 +113,11 @@ def show(img,filename="x"):
 
 
 if __name__=="__main__":
-	root=sys.argv[1]
-	for d in traverseDirs(root):
-		harvestDir(d)
+	((trainImages,trainLabels),(testImages,testLabels))=loadDataset(sys.argv[1])
+	np.savez_compressed(
+		sys.argv[2],
+		trainImages=trainImages,
+		trainLabels=trainLabels,
+		testImages=testImages,
+		testLabels=testLabels
+	)
diff --git a/exp/kerokero/test.py b/exp/kerokero/test.py
--- a/exp/kerokero/test.py
+++ b/exp/kerokero/test.py
@@ -10,13 +10,17 @@ from analyzer.corners import Corners
 
 parser=argparse.ArgumentParser()
 parser.add_argument("model")
-parser.add_argument("data_dir")
+parser.add_argument("data")
 args=parser.parse_args()
 
 model=load_model(args.model)
 
 print("loading data...")
-((trainImages,trainLabels),(testImages,testLabels))=loadDataset(args.data_dir)
+with np.load(args.data) as data:
+	trainImages=data["trainImages"]
+	trainLabels=data["trainLabels"]
+	testImages=data["testImages"]
+	testLabels=data["testLabels"]
 print("done")
 
 for img in testImages:
diff --git a/exp/kerokero/train.py b/exp/kerokero/train.py
--- a/exp/kerokero/train.py
+++ b/exp/kerokero/train.py
@@ -1,13 +1,16 @@
 import argparse
+import logging as log
 
+import numpy as np
 from keras.layers import Conv2D,Dropout,Dense,Flatten,MaxPooling2D,BatchNormalization
 from keras.models import Sequential,load_model
 
-from prepare_data import loadDataset
+import ftp
 
+log.basicConfig(level=log.INFO,format="%(asctime)s %(levelname)s: %(message)s")
 
 parser=argparse.ArgumentParser()
-parser.add_argument("data_dir")
+parser.add_argument("data")
 parser.add_argument("--load_model")
 parser.add_argument("--save_model",default="/tmp/gogo-{0:03}.h5")
 parser.add_argument("--epochs",type=int,default=100)
@@ -55,10 +58,10 @@ def createCNN():
 	
 	model.add(Flatten())
 	
-	model.add(Dense(500, activation="relu"))
+	model.add(Dense(500,activation="relu"))
 	model.add(Dropout(0.1))
 	
-	model.add(Dense(128, activation="relu"))
+	model.add(Dense(128,activation="relu"))
 	model.add(Dropout(0.1))
 	
 	model.add(Dense(8))
@@ -71,11 +74,18 @@ model=createCNN()
 if args.load_model:
 	model=load_model(args.load_model)
 
-print("loading data...")
-((trainImages,trainLabels),(testImages,testLabels))=loadDataset(args.data_dir)
-print("done")
+log.info("loading data...")
+with np.load(args.data) as data:
+	trainImages=data["trainImages"]
+	trainLabels=data["trainLabels"]
+	testImages=data["testImages"]
+	testLabels=data["testLabels"]
+log.info("done")
 
 for i in range(args.initial_epoch,args.epochs//10):
 	model.fit(trainImages.reshape((-1,224,224,1)),trainLabels,epochs=(i+1)*10,initial_epoch=i*10,batch_size=128,validation_split=0.2)
-	model.save(args.save_model.format(i+1))
-print(model.evaluate(testImages,testLabels))
+	path=args.save_model.format(i+1)
+	log.info("saving model...")
+	model.save(path)
+	ftp.push(path)
+log.info(model.evaluate(testImages,testLabels))