fixed earlystop

python/w2v_cnn_gen_hdf5.py

@@ -28,7 +28,7 @@ num_rows = 4.8E6
 batchSize = 2048
 steps = num_rows/batchSize
 #early stop
-earlystop = keras.callbacks.EarlyStopping(monitor='sparse_categorical_accuracy',patience=10,verbose=False,restore_best_weights=True)
+earlystop = keras.callbacks.EarlyStopping(monitor='val_sparse_categorical_accuracy',patience=5,verbose=False,restore_best_weights=True)
 cbList = [earlystop]
 
 trainData = hdf5Generator(path + "w2vCNN.hdf5", batchSize, "Train")

python/w2v_sentence_mean gen.py

@@ -72,7 +72,7 @@ modelNN.compile(optimizer='adam',loss='categorical_crossentropy',metrics=["spars
 
 # %% fit
 #early stop
-earlystop = keras.callbacks.EarlyStopping(monitor='sparse_categorical_accuracy',patience=10,verbose=False,restore_best_weights=True)
+earlystop = keras.callbacks.EarlyStopping(monitor='val_sparse_categorical_accuracy',patience=10,verbose=False,restore_best_weights=True)
 cbList = [earlystop]
 
 train = generate_arrays_from_file('./train.json',batchSize)

python/w2v_sentence_mean.py

@@ -64,7 +64,7 @@ modelNN.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=
 
 # %% fit
 #early stop
-earlystop = keras.callbacks.EarlyStopping(monitor='sparse_categorical_accuracy',patience=5,verbose=False,restore_best_weights=True)
+earlystop = keras.callbacks.EarlyStopping(monitor='val_sparse_categorical_accuracy',patience=5,verbose=False,restore_best_weights=True)
 cbList = [earlystop]
 count = np.unique(Y_train,return_counts=True)[1]
 cWeight = 1/(count/Y_train.size)