from sklearn import preprocessing
min_max_scaler = preprocessing.MinMaxScaler()
data_scale = min_max_scaler.fit_transform(data)
from sklearn.model_selection import train_test_splitX_train, X_val, Y_train, Y_val = train_test_split(data_scale, output, test_size=0.09375)
from keras.models import Sequential
from keras.layers import Dense
model = Sequential([
Dense(20, activation='tanh', input_shape=(6,)),
Dense(1),
])
model.compile(optimizer='adam',
loss='mean_squared_error', metrics=['accuracy']
)
hist = model.fit(X_train, Y_train,
batch_size=29, epochs=100,
validation_data=(X_val, Y_val))
I am trying to create a model to predict an output using 6 types of input features. I have the data of 64 items, and I am using 58 for training and 6 for validation. The model that I am asked to prepare has to have one hidden layer of 20 units and activation tanh. But I am getting zero accuracy in every epoch.
Epoch 1/100
2/2 [==============================] - 1s 243ms/step - loss: 51811.7448 - accuracy: 0.0000e+00 - val_loss: 50574.0625 - val_accuracy: 0.0000e+00
Epoch 2/100
2/2 [==============================] - 0s 25ms/step - loss: 51643.5742 - accuracy: 0.0000e+00 - val_loss: 50551.1445 - val_accuracy: 0.0000e+00
Epoch 3/100
2/2 [==============================] - 0s 20ms/step - loss: 49723.1016 - accuracy: 0.0000e+00 - val_loss: 50528.1992 - val_accuracy: 0.0000e+00
Epoch 4/100
2/2 [==============================] - 0s 22ms/step - loss: 52539.8047 - accuracy: 0.0000e+00 - val_loss: 50505.1836 - val_accuracy: 0.0000e+00
Epoch 5/100
2/2 [==============================] - 0s 22ms/step - loss: 52482.2578 - accuracy: 0.0000e+00 - val_loss: 50482.1211 - val_accuracy: 0.0000e+00
Epoch 6/100
2/2 [==============================] - 0s 23ms/step - loss: 52004.6667 - accuracy: 0.0000e+00 - val_loss: 50459.0156 - val_accuracy: 0.0000e+00
Epoch 7/100
2/2 [==============================] - 0s 25ms/step - loss: 51018.6693 - accuracy: 0.0000e+00 - val_loss: 50435.8750 - val_accuracy: 0.0000e+00
Epoch 8/100
2/2 [==============================] - 0s 24ms/step - loss: 49717.7070 - accuracy: 0.0000e+00 - val_loss: 50412.6758 - val_accuracy: 0.0000e+00
Epoch 9/100
2/2 [==============================] - 0s 23ms/step - loss: 51335.4518 - accuracy: 0.0000e+00 - val_loss: 50389.3867 - val_accuracy: 0.0000e+00
Epoch 10/100
2/2 [==============================] - 0s 22ms/step - loss: 49924.4167 - accuracy: 0.0000e+00 - val_loss: 50366.0586 - val_accuracy: 0.0000e+00
Epoch 11/100
2/2 [==============================] - 0s 25ms/step - loss: 49802.1510 - accuracy: 0.0000e+00 - val_loss: 50342.6406 - val_accuracy: 0.0000e+00
Epoch 12/100
2/2 [==============================] - 0s 22ms/step - loss: 51098.2708 - accuracy: 0.0000e+00 - val_loss: 50319.1133 - val_accuracy: 0.0000e+00
Epoch 13/100
2/2 [==============================] - 0s 26ms/step - loss: 51471.4388 - accuracy: 0.0000e+00 - val_loss: 50295.5039 - val_accuracy: 0.0000e+00
Epoch 14/100
2/2 [==============================] - 0s 23ms/step - loss: 52146.4961 - accuracy: 0.0000e+00 - val_loss: 50271.7344 - val_accuracy: 0.0000e+00
Epoch 15/100
2/2 [==============================] - 0s 25ms/step - loss: 52312.6641 - accuracy: 0.0000e+00 - val_loss: 50247.8945 - val_accuracy: 0.0000e+00
Epoch 16/100
2/2 [==============================] - 0s 22ms/step - loss: 50880.9089 - accuracy: 0.0000e+00 - val_loss: 50223.9336 - val_accuracy: 0.0000e+00
Epoch 17/100
2/2 [==============================] - 0s 23ms/step - loss: 51607.6393 - accuracy: 0.0000e+00 - val_loss: 50199.8594 - val_accuracy: 0.0000e+00
Epoch 18/100
2/2 [==============================] - 0s 22ms/step - loss: 51863.2174 - accuracy: 0.0000e+00 - val_loss: 50175.6914 - val_accuracy: 0.0000e+00
Epoch 19/100
2/2 [==============================] - 0s 21ms/step - loss: 49922.4349 - accuracy: 0.0000e+00 - val_loss: 50151.3906 - val_accuracy: 0.0000e+00
Epoch 20/100
2/2 [==============================] - 0s 27ms/step - loss: 53367.2396 - accuracy: 0.0000e+00 - val_loss: 50126.8711 - val_accuracy: 0.0000e+00
Epoch 21/100
2/2 [==============================] - 0s 25ms/step - loss: 49393.4909 - accuracy: 0.0000e+00 - val_loss: 50102.3164 - val_accuracy: 0.0000e+00
Epoch 22/100
2/2 [==============================] - 0s 26ms/step - loss: 51564.7669 - accuracy: 0.0000e+00 - val_loss: 50077.5195 - val_accuracy: 0.0000e+00
Epoch 23/100
2/2 [==============================] - 0s 24ms/step - loss: 50011.7604 - accuracy: 0.0000e+00 - val_loss: 50052.6367 - val_accuracy: 0.0000e+00
Epoch 24/100
2/2 [==============================] - 0s 25ms/step - loss: 52412.6693 - accuracy: 0.0000e+00 - val_loss: 50027.5273 - val_accuracy: 0.0000e+00
Epoch 25/100
2/2 [==============================] - 0s 25ms/step - loss: 49858.7826 - accuracy: 0.0000e+00 - val_loss: 50002.3281 - val_accuracy: 0.0000e+00
Epoch 26/100
2/2 [==============================] - 0s 25ms/step - loss: 51710.6602 - accuracy: 0.0000e+00 - val_loss: 49976.9219 - val_accuracy: 0.0000e+00
Epoch 27/100
2/2 [==============================] - 0s 24ms/step - loss: 50573.8073 - accuracy: 0.0000e+00 - val_loss: 49951.3438 - val_accuracy: 0.0000e+00
Epoch 28/100
2/2 [==============================] - 0s 28ms/step - loss: 49282.0898 - accuracy: 0.0000e+00 - val_loss: 49925.6562 - val_accuracy: 0.0000e+00
Epoch 29/100
2/2 [==============================] - 0s 31ms/step - loss: 51581.7708 - accuracy: 0.0000e+00 - val_loss: 49899.7656 - val_accuracy: 0.0000e+00
Epoch 30/100
2/2 [==============================] - 0s 28ms/step - loss: 50463.7826 - accuracy: 0.0000e+00 - val_loss: 49873.7188 - val_accuracy: 0.0000e+00
Epoch 31/100
2/2 [==============================] - 0s 24ms/step - loss: 51371.1406 - accuracy: 0.0000e+00 - val_loss: 49847.5156 - val_accuracy: 0.0000e+00
Epoch 32/100
2/2 [==============================] - 0s 26ms/step - loss: 49800.9284 - accuracy: 0.0000e+00 - val_loss: 49821.1562 - val_accuracy: 0.0000e+00
Epoch 33/100
2/2 [==============================] - 0s 25ms/step - loss: 51305.6406 - accuracy: 0.0000e+00 - val_loss: 49794.5820 - val_accuracy: 0.0000e+00
Epoch 34/100
2/2 [==============================] - 0s 25ms/step - loss: 50867.6029 - accuracy: 0.0000e+00 - val_loss: 49767.8789 - val_accuracy: 0.0000e+00
Epoch 35/100
2/2 [==============================] - 0s 22ms/step - loss: 51187.8073 - accuracy: 0.0000e+00 - val_loss: 49740.9961 - val_accuracy: 0.0000e+00
Epoch 36/100
2/2 [==============================] - 0s 25ms/step - loss: 50952.5169 - accuracy: 0.0000e+00 - val_loss: 49713.9336 - val_accuracy: 0.0000e+00
Epoch 37/100
2/2 [==============================] - 0s 22ms/step - loss: 49043.2917 - accuracy: 0.0000e+00 - val_loss: 49686.7812 - val_accuracy: 0.0000e+00
Epoch 38/100
2/2 [==============================] - 0s 24ms/step - loss: 51361.7057 - accuracy: 0.0000e+00 - val_loss: 49659.3867 - val_accuracy: 0.0000e+00
Epoch 39/100
2/2 [==============================] - 0s 21ms/step - loss: 51550.3112 - accuracy: 0.0000e+00 - val_loss: 49631.8008 - val_accuracy: 0.0000e+00
Epoch 40/100
2/2 [==============================] - 0s 24ms/step - loss: 49792.8099 - accuracy: 0.0000e+00 - val_loss: 49604.0781 - val_accuracy: 0.0000e+00
Epoch 41/100
2/2 [==============================] - 0s 22ms/step - loss: 50967.6693 - accuracy: 0.0000e+00 - val_loss: 49576.1758 - val_accuracy: 0.0000e+00
Epoch 42/100
2/2 [==============================] - 0s 27ms/step - loss: 49447.2734 - accuracy: 0.0000e+00 - val_loss: 49548.1289 - val_accuracy: 0.0000e+00
Epoch 43/100
2/2 [==============================] - 0s 23ms/step - loss: 51130.9167 - accuracy: 0.0000e+00 - val_loss: 49519.8555 - val_accuracy: 0.0000e+00
Epoch 44/100
2/2 [==============================] - 0s 23ms/step - loss: 48933.1875 - accuracy: 0.0000e+00 - val_loss: 49491.4727 - val_accuracy: 0.0000e+00
Epoch 45/100
2/2 [==============================] - 0s 25ms/step - loss: 49759.7201 - accuracy: 0.0000e+00 - val_loss: 49462.8906 - val_accuracy: 0.0000e+00
Epoch 46/100
2/2 [==============================] - 0s 27ms/step - loss: 50660.8659 - accuracy: 0.0000e+00 - val_loss: 49434.0742 - val_accuracy: 0.0000e+00
Epoch 47/100
2/2 [==============================] - 0s 30ms/step - loss: 50524.8307 - accuracy: 0.0000e+00 - val_loss: 49405.1367 - val_accuracy: 0.0000e+00
Epoch 48/100
2/2 [==============================] - 0s 26ms/step - loss: 49962.2904 - accuracy: 0.0000e+00 - val_loss: 49375.9844 - val_accuracy: 0.0000e+00
Epoch 49/100
2/2 [==============================] - 0s 25ms/step - loss: 49227.0677 - accuracy: 0.0000e+00 - val_loss: 49346.7344 - val_accuracy: 0.0000e+00
Epoch 50/100
2/2 [==============================] - 0s 29ms/step - loss: 51078.3815 - accuracy: 0.0000e+00 - val_loss: 49317.1992 - val_accuracy: 0.0000e+00
Epoch 51/100
2/2 [==============================] - 0s 37ms/step - loss: 51424.3841 - accuracy: 0.0000e+00 - val_loss: 49287.4883 - val_accuracy: 0.0000e+00
Epoch 52/100
2/2 [==============================] - 0s 28ms/step - loss: 50354.8789 - accuracy: 0.0000e+00 - val_loss: 49257.6719 - val_accuracy: 0.0000e+00
Epoch 53/100
2/2 [==============================] - 0s 28ms/step - loss: 50108.2552 - accuracy: 0.0000e+00 - val_loss: 49227.6602 - val_accuracy: 0.0000e+00
Epoch 54/100
2/2 [==============================] - 0s 29ms/step - loss: 50449.8867 - accuracy: 0.0000e+00 - val_loss: 49197.5000 - val_accuracy: 0.0000e+00
Epoch 55/100
2/2 [==============================] - 0s 30ms/step - loss: 49881.0417 - accuracy: 0.0000e+00 - val_loss: 49167.1758 - val_accuracy: 0.0000e+00
Epoch 56/100
2/2 [==============================] - 0s 28ms/step - loss: 50056.2122 - accuracy: 0.0000e+00 - val_loss: 49136.6602 - val_accuracy: 0.0000e+00
Epoch 57/100
2/2 [==============================] - 0s 26ms/step - loss: 49487.7695 - accuracy: 0.0000e+00 - val_loss: 49105.9570 - val_accuracy: 0.0000e+00
Epoch 58/100
2/2 [==============================] - 0s 27ms/step - loss: 48665.1133 - accuracy: 0.0000e+00 - val_loss: 49075.0781 - val_accuracy: 0.0000e+00
Epoch 59/100
2/2 [==============================] - 0s 25ms/step - loss: 48959.0208 - accuracy: 0.0000e+00 - val_loss: 49044.0430 - val_accuracy: 0.0000e+00
Epoch 60/100
2/2 [==============================] - 0s 35ms/step - loss: 49726.4310 - accuracy: 0.0000e+00 - val_loss: 49012.7773 - val_accuracy: 0.0000e+00
Epoch 61/100
2/2 [==============================] - 0s 28ms/step - loss: 50568.7305 - accuracy: 0.0000e+00 - val_loss: 48981.3711 - val_accuracy: 0.0000e+00
Epoch 62/100
2/2 [==============================] - 0s 24ms/step - loss: 50870.2344 - accuracy: 0.0000e+00 - val_loss: 48949.7461 - val_accuracy: 0.0000e+00
Epoch 63/100
2/2 [==============================] - 0s 26ms/step - loss: 49693.0521 - accuracy: 0.0000e+00 - val_loss: 48918.0352 - val_accuracy: 0.0000e+00
Epoch 64/100
2/2 [==============================] - 0s 25ms/step - loss: 51050.4596 - accuracy: 0.0000e+00 - val_loss: 48886.1133 - val_accuracy: 0.0000e+00
Epoch 65/100
2/2 [==============================] - 0s 23ms/step - loss: 51286.4609 - accuracy: 0.0000e+00 - val_loss: 48854.0156 - val_accuracy: 0.0000e+00
Epoch 66/100
2/2 [==============================] - 0s 24ms/step - loss: 50518.3047 - accuracy: 0.0000e+00 - val_loss: 48821.7656 - val_accuracy: 0.0000e+00
Epoch 67/100
2/2 [==============================] - 0s 25ms/step - loss: 49936.2500 - accuracy: 0.0000e+00 - val_loss: 48789.4023 - val_accuracy: 0.0000e+00
Epoch 68/100
2/2 [==============================] - 0s 26ms/step - loss: 48336.5130 - accuracy: 0.0000e+00 - val_loss: 48756.8906 - val_accuracy: 0.0000e+00
Epoch 69/100
2/2 [==============================] - 0s 25ms/step - loss: 50585.8268 - accuracy: 0.0000e+00 - val_loss: 48724.1992 - val_accuracy: 0.0000e+00
Epoch 70/100
2/2 [==============================] - 0s 22ms/step - loss: 50887.9961 - accuracy: 0.0000e+00 - val_loss: 48691.3438 - val_accuracy: 0.0000e+00
Epoch 71/100
2/2 [==============================] - 0s 28ms/step - loss: 48245.7734 - accuracy: 0.0000e+00 - val_loss: 48658.4023 - val_accuracy: 0.0000e+00
Epoch 72/100
2/2 [==============================] - 0s 24ms/step - loss: 49855.4987 - accuracy: 0.0000e+00 - val_loss: 48625.2539 - val_accuracy: 0.0000e+00
Epoch 73/100
2/2 [==============================] - 0s 27ms/step - loss: 49838.8216 - accuracy: 0.0000e+00 - val_loss: 48591.9961 - val_accuracy: 0.0000e+00
Epoch 74/100
2/2 [==============================] - 0s 24ms/step - loss: 50452.5221 - accuracy: 0.0000e+00 - val_loss: 48558.6094 - val_accuracy: 0.0000e+00
Epoch 75/100
2/2 [==============================] - 0s 26ms/step - loss: 49913.4987 - accuracy: 0.0000e+00 - val_loss: 48525.0977 - val_accuracy: 0.0000e+00
Epoch 76/100
2/2 [==============================] - 0s 22ms/step - loss: 50415.0065 - accuracy: 0.0000e+00 - val_loss: 48491.4062 - val_accuracy: 0.0000e+00
Epoch 77/100
2/2 [==============================] - 0s 21ms/step - loss: 48946.9909 - accuracy: 0.0000e+00 - val_loss: 48457.6523 - val_accuracy: 0.0000e+00
Epoch 78/100
2/2 [==============================] - 0s 24ms/step - loss: 49364.7357 - accuracy: 0.0000e+00 - val_loss: 48423.7656 - val_accuracy: 0.0000e+00
Epoch 79/100
2/2 [==============================] - 0s 22ms/step - loss: 48923.9831 - accuracy: 0.0000e+00 - val_loss: 48389.7344 - val_accuracy: 0.0000e+00
Epoch 80/100
2/2 [==============================] - 0s 29ms/step - loss: 48342.6185 - accuracy: 0.0000e+00 - val_loss: 48355.6523 - val_accuracy: 0.0000e+00
Epoch 81/100
2/2 [==============================] - 0s 31ms/step - loss: 47624.0443 - accuracy: 0.0000e+00 - val_loss: 48321.4961 - val_accuracy: 0.0000e+00
Epoch 82/100
2/2 [==============================] - 0s 28ms/step - loss: 50017.1719 - accuracy: 0.0000e+00 - val_loss: 48287.1250 - val_accuracy: 0.0000e+00
Epoch 83/100
2/2 [==============================] - 0s 29ms/step - loss: 48870.0182 - accuracy: 0.0000e+00 - val_loss: 48252.7070 - val_accuracy: 0.0000e+00
Epoch 84/100
2/2 [==============================] - 0s 30ms/step - loss: 48225.5339 - accuracy: 0.0000e+00 - val_loss: 48218.1875 - val_accuracy: 0.0000e+00
Epoch 85/100
2/2 [==============================] - 0s 23ms/step - loss: 48875.5664 - accuracy: 0.0000e+00 - val_loss: 48183.5781 - val_accuracy: 0.0000e+00
Epoch 86/100
2/2 [==============================] - 0s 23ms/step - loss: 49319.9857 - accuracy: 0.0000e+00 - val_loss: 48148.8750 - val_accuracy: 0.0000e+00
Epoch 87/100
2/2 [==============================] - 0s 42ms/step - loss: 47941.7708 - accuracy: 0.0000e+00 - val_loss: 48114.1445 - val_accuracy: 0.0000e+00
Epoch 88/100
2/2 [==============================] - 0s 23ms/step - loss: 50075.6576 - accuracy: 0.0000e+00 - val_loss: 48079.2461 - val_accuracy: 0.0000e+00
Epoch 89/100
2/2 [==============================] - 0s 28ms/step - loss: 50083.3125 - accuracy: 0.0000e+00 - val_loss: 48044.2969 - val_accuracy: 0.0000e+00
Epoch 90/100
2/2 [==============================] - 0s 27ms/step - loss: 48913.2578 - accuracy: 0.0000e+00 - val_loss: 48009.3086 - val_accuracy: 0.0000e+00
Epoch 91/100
2/2 [==============================] - 0s 28ms/step - loss: 47684.0156 - accuracy: 0.0000e+00 - val_loss: 47974.3320 - val_accuracy: 0.0000e+00
Epoch 92/100
2/2 [==============================] - 0s 22ms/step - loss: 48293.5768 - accuracy: 0.0000e+00 - val_loss: 47939.2383 - val_accuracy: 0.0000e+00
Epoch 93/100
2/2 [==============================] - 0s 23ms/step - loss: 49457.4193 - accuracy: 0.0000e+00 - val_loss: 47904.0781 - val_accuracy: 0.0000e+00
Epoch 94/100
2/2 [==============================] - 0s 24ms/step - loss: 49460.8294 - accuracy: 0.0000e+00 - val_loss: 47868.8281 - val_accuracy: 0.0000e+00
Epoch 95/100
2/2 [==============================] - 0s 30ms/step - loss: 48577.9479 - accuracy: 0.0000e+00 - val_loss: 47833.6133 - val_accuracy: 0.0000e+00
Epoch 96/100
2/2 [==============================] - 0s 22ms/step - loss: 49447.5651 - accuracy: 0.0000e+00 - val_loss: 47798.3164 - val_accuracy: 0.0000e+00
Epoch 97/100
2/2 [==============================] - 0s 28ms/step - loss: 48044.7982 - accuracy: 0.0000e+00 - val_loss: 47763.0625 - val_accuracy: 0.0000e+00
Epoch 98/100
2/2 [==============================] - 0s 35ms/step - loss: 48426.7266 - accuracy: 0.0000e+00 - val_loss: 47727.7227 - val_accuracy: 0.0000e+00
Epoch 99/100
2/2 [==============================] - 0s 26ms/step - loss: 49340.5078 - accuracy: 0.0000e+00 - val_loss: 47692.3594 - val_accuracy: 0.0000e+00
Epoch 100/100
2/2 [==============================] - 0s 27ms/step - loss: 47890.7018 - accuracy: 0.0000e+00 - val_loss: 47657.0117 - val_accuracy: 0.0000e+00
