I have created the following toy dataset:
I am trying to predict the class with a neural net in keras:
model = Sequential()
model.add(Dense(units=2, activation='sigmoid', input_shape= (nr_feats,)))
model.add(Dense(units=nr_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
With nr_feats and nr_classes set to 2.
The neural net can only predict with 50 percent accuracy returning either all 1's or all 2's. Using Logistic Regression results in 100 percent accuracy.
I can not find what is going wrong here.
I have uploaded a notebook to github if you quickly want to try something.
EDIT 1
I drastically increased the number of epochs and accuracy finally starts to improve from 0.5 at epoch 72 and converges to 1.0 at epoch 98.
This still seems extremely slow for such a simple dataset.
I am aware it is better to use a single output neuron with sigmoid activation but it's more that I want to understand why it does not work with two output neurons and softmax activation.
I pre-process my dataframe as follows:
from sklearn.preprocessing import LabelEncoder
x_train = df_train.iloc[:,0:-1].values
y_train = df_train.iloc[:, -1]
nr_feats = x_train.shape[1]
nr_classes = y_train.nunique()
label_enc = LabelEncoder()
label_enc.fit(y_train)
y_train = keras.utils.to_categorical(label_enc.transform(y_train), nr_classes)
Training and evaluation:
model.fit(x_train, y_train, epochs=500, batch_size=32, verbose=True)
accuracy_score(model.predict_classes(x_train), df_train.iloc[:, -1].values)
EDIT 2
After changing the output layer to a single neuron with sigmoid activation and using binary_crossentropy loss as modesitt suggested, accuracy still remains at 0.5 for 200 epochs and converges to 1.0 100 epochs later.
Note: Read the "Update" section at the end of my answer if you want the true reason. In this scenario, the other two reasons I have mentioned are only valid when the learning rate is set to a low value (less than 1e-3).
I put together some code. It is very similar to yours but I just cleaned it a little bit and made it simpler for myself. As you can see, I use a dense layer with one unit with a sigmoid activation function for the last layer and just change the optimizer from adam to rmsprop (it is not important that much, you can use adam if you like):
import numpy as np
import random
# generate random data with two features
n_samples = 200
n_feats = 2
cls0 = np.random.uniform(low=0.2, high=0.4, size=(n_samples,n_feats))
cls1 = np.random.uniform(low=0.5, high=0.7, size=(n_samples,n_feats))
x_train = np.concatenate((cls0, cls1))
y_train = np.concatenate((np.zeros((n_samples,)), np.ones((n_samples,))))
# shuffle data because all negatives (i.e. class "0") are first
# and then all positives (i.e. class "1")
indices = np.arange(x_train.shape[0])
np.random.shuffle(indices)
x_train = x_train[indices]
y_train = y_train[indices]
from keras.models import Sequential
from keras.layers import Dense
model = Sequential()
model.add(Dense(2, activation='sigmoid', input_shape=(n_feats,)))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
model.summary()
model.fit(x_train, y_train, epochs=5, batch_size=32, verbose=True)
Here is the output:
Layer (type) Output Shape Param #
=================================================================
dense_25 (Dense) (None, 2) 6
_________________________________________________________________
dense_26 (Dense) (None, 1) 3
=================================================================
Total params: 9
Trainable params: 9
Non-trainable params: 0
_________________________________________________________________
Epoch 1/5
400/400 [==============================] - 0s 966us/step - loss: 0.7013 - acc: 0.5000
Epoch 2/5
400/400 [==============================] - 0s 143us/step - loss: 0.6998 - acc: 0.5000
Epoch 3/5
400/400 [==============================] - 0s 137us/step - loss: 0.6986 - acc: 0.5000
Epoch 4/5
400/400 [==============================] - 0s 149us/step - loss: 0.6975 - acc: 0.5000
Epoch 5/5
400/400 [==============================] - 0s 132us/step - loss: 0.6966 - acc: 0.5000
As you can see the accuracy never increases from 50%. What if you increase the number of epochs to say 50:
Layer (type) Output Shape Param #
=================================================================
dense_35 (Dense) (None, 2) 6
_________________________________________________________________
dense_36 (Dense) (None, 1) 3
=================================================================
Total params: 9
Trainable params: 9
Non-trainable params: 0
_________________________________________________________________
Epoch 1/50
400/400 [==============================] - 0s 1ms/step - loss: 0.6925 - acc: 0.5000
Epoch 2/50
400/400 [==============================] - 0s 136us/step - loss: 0.6902 - acc: 0.5000
Epoch 3/50
400/400 [==============================] - 0s 133us/step - loss: 0.6884 - acc: 0.5000
Epoch 4/50
400/400 [==============================] - 0s 160us/step - loss: 0.6866 - acc: 0.5000
Epoch 5/50
400/400 [==============================] - 0s 140us/step - loss: 0.6848 - acc: 0.5000
Epoch 6/50
400/400 [==============================] - 0s 168us/step - loss: 0.6832 - acc: 0.5000
Epoch 7/50
400/400 [==============================] - 0s 154us/step - loss: 0.6817 - acc: 0.5000
Epoch 8/50
400/400 [==============================] - 0s 146us/step - loss: 0.6802 - acc: 0.5000
Epoch 9/50
400/400 [==============================] - 0s 161us/step - loss: 0.6789 - acc: 0.5000
Epoch 10/50
400/400 [==============================] - 0s 140us/step - loss: 0.6778 - acc: 0.5000
Epoch 11/50
400/400 [==============================] - 0s 177us/step - loss: 0.6766 - acc: 0.5000
Epoch 12/50
400/400 [==============================] - 0s 180us/step - loss: 0.6755 - acc: 0.5000
Epoch 13/50
400/400 [==============================] - 0s 165us/step - loss: 0.6746 - acc: 0.5000
Epoch 14/50
400/400 [==============================] - 0s 128us/step - loss: 0.6736 - acc: 0.5000
Epoch 15/50
400/400 [==============================] - 0s 125us/step - loss: 0.6728 - acc: 0.5000
Epoch 16/50
400/400 [==============================] - 0s 165us/step - loss: 0.6718 - acc: 0.5000
Epoch 17/50
400/400 [==============================] - 0s 161us/step - loss: 0.6710 - acc: 0.5000
Epoch 18/50
400/400 [==============================] - 0s 170us/step - loss: 0.6702 - acc: 0.5000
Epoch 19/50
400/400 [==============================] - 0s 122us/step - loss: 0.6694 - acc: 0.5000
Epoch 20/50
400/400 [==============================] - 0s 110us/step - loss: 0.6686 - acc: 0.5000
Epoch 21/50
400/400 [==============================] - 0s 142us/step - loss: 0.6676 - acc: 0.5000
Epoch 22/50
400/400 [==============================] - 0s 142us/step - loss: 0.6667 - acc: 0.5000
Epoch 23/50
400/400 [==============================] - 0s 149us/step - loss: 0.6659 - acc: 0.5000
Epoch 24/50
400/400 [==============================] - 0s 125us/step - loss: 0.6651 - acc: 0.5000
Epoch 25/50
400/400 [==============================] - 0s 134us/step - loss: 0.6643 - acc: 0.5000
Epoch 26/50
400/400 [==============================] - 0s 143us/step - loss: 0.6634 - acc: 0.5000
Epoch 27/50
400/400 [==============================] - 0s 137us/step - loss: 0.6625 - acc: 0.5000
Epoch 28/50
400/400 [==============================] - 0s 131us/step - loss: 0.6616 - acc: 0.5025
Epoch 29/50
400/400 [==============================] - 0s 119us/step - loss: 0.6608 - acc: 0.5100
Epoch 30/50
400/400 [==============================] - 0s 143us/step - loss: 0.6601 - acc: 0.5025
Epoch 31/50
400/400 [==============================] - 0s 148us/step - loss: 0.6593 - acc: 0.5350
Epoch 32/50
400/400 [==============================] - 0s 161us/step - loss: 0.6584 - acc: 0.5325
Epoch 33/50
400/400 [==============================] - 0s 152us/step - loss: 0.6576 - acc: 0.5700
Epoch 34/50
400/400 [==============================] - 0s 128us/step - loss: 0.6568 - acc: 0.5850
Epoch 35/50
400/400 [==============================] - 0s 155us/step - loss: 0.6560 - acc: 0.5975
Epoch 36/50
400/400 [==============================] - 0s 136us/step - loss: 0.6552 - acc: 0.6425
Epoch 37/50
400/400 [==============================] - 0s 140us/step - loss: 0.6544 - acc: 0.6150
Epoch 38/50
400/400 [==============================] - 0s 120us/step - loss: 0.6538 - acc: 0.6375
Epoch 39/50
400/400 [==============================] - 0s 140us/step - loss: 0.6531 - acc: 0.6725
Epoch 40/50
400/400 [==============================] - 0s 135us/step - loss: 0.6523 - acc: 0.6750
Epoch 41/50
400/400 [==============================] - 0s 136us/step - loss: 0.6515 - acc: 0.7300
Epoch 42/50
400/400 [==============================] - 0s 126us/step - loss: 0.6505 - acc: 0.7450
Epoch 43/50
400/400 [==============================] - 0s 141us/step - loss: 0.6496 - acc: 0.7425
Epoch 44/50
400/400 [==============================] - 0s 162us/step - loss: 0.6489 - acc: 0.7675
Epoch 45/50
400/400 [==============================] - 0s 161us/step - loss: 0.6480 - acc: 0.7775
Epoch 46/50
400/400 [==============================] - 0s 126us/step - loss: 0.6473 - acc: 0.7575
Epoch 47/50
400/400 [==============================] - 0s 124us/step - loss: 0.6464 - acc: 0.7625
Epoch 48/50
400/400 [==============================] - 0s 130us/step - loss: 0.6455 - acc: 0.7950
Epoch 49/50
400/400 [==============================] - 0s 191us/step - loss: 0.6445 - acc: 0.8100
Epoch 50/50
400/400 [==============================] - 0s 163us/step - loss: 0.6435 - acc: 0.8625
The accuracy starts to increase (Note that if you train this model multiple times, each time it may take different number of epochs to reach an acceptable accuracy, anything from 10 to 100 epochs).
Also, in my experiments I noticed that increasing the number of units in the first dense layer, for example to 5 or 10 units, causes the model to be trained faster (i.e. quickly converge).
Why so many epochs needed?
I think it is because of these two reasons (combined):
1) Despite the fact that the two classes are easily separable, your data is made up of random samples, and
2) The number of data points compared to the size of neural net (i.e. number of trainable parameters, which is 9 in example code above) is relatively large.
Therefore, it takes more epochs for the model to learn the weights. It is as though the model is very restricted and needs more and more experience to correctly find the appropriate weights. As an evidence, just try to increase the number of units in the first dense layer. You are almost guaranteed to reach an accuracy of +90% with less than 10 epochs each time you attempt to train this model. Here you increase the capacity and therefore the model converges (i.e. trains) much faster (it should be noted that it starts to overfit if the capacity is too high or you train the model for too many epochs. You should have a validation scheme to monitor this issue).
Side note:
Don't set the high argument to a number less than the low argument in numpy.random.uniform since, according to the documentation, the results will be "officially undefined" in this case.
Update:
One more important thing here (maybe the most important thing in this scenario) is the learning rate of the optimizer. If the learning rate is too low, the model converges slowly. Try increasing the learning rate, and you can see you reach an accuracy of 100% with less than 5 epochs:
from keras import optimizers
model.compile(loss='binary_crossentropy',
optimizer=optimizers.RMSprop(lr=1e-1),
metrics=['accuracy'])
# or you may use adam
model.compile(loss='binary_crossentropy',
optimizer=optimizers.Adam(lr=1e-1),
metrics=['accuracy'])
The issue is that your labels are 1 and 2 instead of 0 and 1. Keras will not raise an error when it sees 2, but it is not capable of predicting 2.
Subtract 1 from all your y values. As a side note, it is common in deep learning to use 1 neuron with sigmoid for binary classification (0 or 1) vs 2 classes with softmax. Finally, use binary_crossentropy for the loss for binary classification problems.
Related
I built an algorithm in Python for data sets classification with Keras. It's a very simple LSTM network with 1 input layer, 1 hidden layer (LSTM) and 1 dense output layer.
My data consists of some analog measurements: 63 sets for training and 36 sets for testing, each set having 3 channels with 19200 samples each channel, so (following what I understood reading the documentation) the input shape I needed was x = (63,19200,3) and y = (36,19200,3). (If you want some additional information about the type of data, I can explain more.)
My code is as follows:
import numpy as np
import matplotlib.pyplot as plt
from sklearn.utils import shuffle
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Input
from keras.layers import Dropout
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
from keras import initializers
from keras import optimizers
# Fix random seed for reproducibility.
np.random.seed(1)
# Loading data (shapes: X_test (36,19200,3), y_test (36,3), X_train (63,19200,3), y_train (63,3))
(X_test, y_test), (X_train, y_train) = np.load('path.npy',allow_pickle=True)
data = [(X_test, y_test), (X_train, y_train)]
# Manually separating the validation data.
x_val = X_train[-10:]
y_val = y_train[-10:]
X_train = X_train[:-10]
y_train = y_train[:-10]
# Creating model.
model = Sequential()
model.add(Input(shape=(19200,3)))
model.add(LSTM(50, name = 'LSTM', activation='tanh',recurrent_activation='tanh', kernel_initializer=initializers.RandomNormal(mean=0.0, stddev=0.05, seed=1), bias_initializer=initializers.zeros()))
model.add(Dense(1, name = 'Saida', activation='sigmoid', kernel_initializer=initializers.RandomNormal(mean=0.0, stddev=0.05, seed=1), bias_initializer=initializers.zeros()))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
history = model.fit(X_train, y_train, epochs=20, batch_size=12, shuffle=True, validation_data=(x_val, y_val))
# Final evaluation of the model.
scores = model.evaluate(X_test, y_test, verbose=1)
print("Accuracy: %.2f%%" % (scores[1]*100))
Very simple, but not that organized, still working on that.
And for this run, the results are:
Model: "sequential_8"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
LSTM (LSTM) (None, 50) 10800
_________________________________________________________________
Saida (Dense) (None, 1) 51
=================================================================
Total params: 10,851
Trainable params: 10,851
Non-trainable params: 0
_________________________________________________________________
None
Epoch 1/20
5/5 [==============================] - 17s 3s/step - loss: 0.6866 - accuracy: 0.6792 - val_loss: 0.6956 - val_accuracy: 0.0000e+00
Epoch 2/20
5/5 [==============================] - 20s 4s/step - loss: 0.6814 - accuracy: 0.8113 - val_loss: 0.6979 - val_accuracy: 0.0000e+00
Epoch 3/20
5/5 [==============================] - 21s 4s/step - loss: 0.6915 - accuracy: 0.7925 - val_loss: 0.7002 - val_accuracy: 0.0000e+00
Epoch 4/20
5/5 [==============================] - 24s 5s/step - loss: 0.6810 - accuracy: 0.7925 - val_loss: 0.7025 - val_accuracy: 0.0000e+00
Epoch 5/20
5/5 [==============================] - 25s 5s/step - loss: 0.6828 - accuracy: 0.7925 - val_loss: 0.7048 - val_accuracy: 0.0000e+00
Epoch 6/20
5/5 [==============================] - 24s 5s/step - loss: 0.6703 - accuracy: 0.8302 - val_loss: 0.7072 - val_accuracy: 0.0000e+00
Epoch 7/20
5/5 [==============================] - 24s 5s/step - loss: 0.6787 - accuracy: 0.7925 - val_loss: 0.7095 - val_accuracy: 0.0000e+00
Epoch 8/20
5/5 [==============================] - 26s 5s/step - loss: 0.6963 - accuracy: 0.7547 - val_loss: 0.7117 - val_accuracy: 0.0000e+00
Epoch 9/20
5/5 [==============================] - 25s 5s/step - loss: 0.6776 - accuracy: 0.7925 - val_loss: 0.7141 - val_accuracy: 0.0000e+00
Epoch 10/20
5/5 [==============================] - 25s 5s/step - loss: 0.6640 - accuracy: 0.8302 - val_loss: 0.7164 - val_accuracy: 0.0000e+00
Epoch 11/20
5/5 [==============================] - 24s 5s/step - loss: 0.6626 - accuracy: 0.8491 - val_loss: 0.7187 - val_accuracy: 0.0000e+00
Epoch 12/20
5/5 [==============================] - 24s 5s/step - loss: 0.6504 - accuracy: 0.8491 - val_loss: 0.7210 - val_accuracy: 0.0000e+00
Epoch 13/20
5/5 [==============================] - 24s 5s/step - loss: 0.6729 - accuracy: 0.7925 - val_loss: 0.7233 - val_accuracy: 0.0000e+00
Epoch 14/20
5/5 [==============================] - 24s 5s/step - loss: 0.6602 - accuracy: 0.8302 - val_loss: 0.7257 - val_accuracy: 0.0000e+00
Epoch 15/20
5/5 [==============================] - 25s 5s/step - loss: 0.6857 - accuracy: 0.7547 - val_loss: 0.7281 - val_accuracy: 0.0000e+00
Epoch 16/20
5/5 [==============================] - 23s 5s/step - loss: 0.6630 - accuracy: 0.8113 - val_loss: 0.7305 - val_accuracy: 0.0000e+00
Epoch 17/20
5/5 [==============================] - 25s 5s/step - loss: 0.6633 - accuracy: 0.7925 - val_loss: 0.7328 - val_accuracy: 0.0000e+00
Epoch 18/20
5/5 [==============================] - 24s 5s/step - loss: 0.6600 - accuracy: 0.8302 - val_loss: 0.7352 - val_accuracy: 0.0000e+00
Epoch 19/20
5/5 [==============================] - 25s 5s/step - loss: 0.6670 - accuracy: 0.8113 - val_loss: 0.7374 - val_accuracy: 0.0000e+00
Epoch 20/20
5/5 [==============================] - 24s 5s/step - loss: 0.6534 - accuracy: 0.8302 - val_loss: 0.7399 - val_accuracy: 0.0000e+00
2/2 [==============================] - 1s 314ms/step - loss: 0.7171 - accuracy: 0.4167
Accuracy: 41.67%
Summarizing: High loss, but decrease very slowly. Accuracy is varying, but in the end it stabilizes at the same value (usually 0,7925 or 0,8113). And my accuracy for the validation set don't even respond to any changes that occur with the other metrics.
My main concern is the validation data is not behaving as it should. I already tried changing the optimizers, activation functions of every layer, weight initializers, number of epochs (went till 100 several times but nothing changed), batch size, shuffling the data using Keras function and Python built-in method, and so on.
The only thing I did not tried was to change the input shapes, but, as I mentioned earlier, this was the only way I got the 3D array to be accepted in the Input Layer.
If you guys have any tips to what can be changed to achieve more consistent results, I would be very grateful.
Any additional commentary will be happily accepted.
This is my first question here and I am not a native english speaker, so sorry if any information was not very clear.
Cheers, Matheus Zimmermann.
I think you can apply to_categorical method or One hot encoding approach to the
y_train , y_val and y_test variables.
Hope than after applying it ,you will find your validation accuracy perfectly.
I faced this type of same problem before.
# We have 2 inputs, 1 for each picture
left_input = Input(img_size)
right_input = Input(img_size)
# We will use 2 instances of 1 network for this task
convnet = MobileNetV2(weights='imagenet', include_top=False, input_shape=img_size,input_tensor=None)
convnet.trainable=True
x=convnet.output
x=tf.keras.layers.GlobalAveragePooling2D()(x)
x=Dense(320,activation='relu')(x)
x=Dropout(0.2)(x)
preds = Dense(101, activation='sigmoid')(x) # Apply sigmoid
convnet = Model(inputs=convnet.input, outputs=preds)
# Connect each 'leg' of the network to each input
# Remember, they have the same weights
encoded_l = convnet(left_input)
encoded_r = convnet(right_input)
# Getting the L1 Distance between the 2 encodings
L1_layer = Lambda(lambda tensor:K.abs(tensor[0] - tensor[1]))
# Add the distance function to the network
L1_distance = L1_layer([encoded_l, encoded_r])
prediction = Dense(1,activation='sigmoid')(L1_distance)
siamese_net = Model(inputs=[left_input,right_input],outputs=prediction)
optimizer = Adam(lr, decay=2.5e-4)
#//TODO: get layerwise learning rates and momentum annealing scheme described in paperworking
siamese_net.compile(loss=keras.losses.binary_crossentropy,optimizer=optimizer,metrics=['accuracy'])
siamese_net.summary()
and the result of training is as follows
Epoch 1/10
126/126 [==============================] - 169s 1s/step - loss: 0.5683 - accuracy: 0.6840 - val_loss: 0.4644 - val_accuracy: 0.8044
Epoch 2/10
126/126 [==============================] - 163s 1s/step - loss: 0.2032 - accuracy: 0.9795 - val_loss: 0.2117 - val_accuracy: 0.9681
Epoch 3/10
126/126 [==============================] - 163s 1s/step - loss: 0.1110 - accuracy: 0.9925 - val_loss: 0.1448 - val_accuracy: 0.9840
Epoch 4/10
126/126 [==============================] - 164s 1s/step - loss: 0.0844 - accuracy: 0.9950 - val_loss: 0.1384 - val_accuracy: 0.9820
Epoch 5/10
126/126 [==============================] - 163s 1s/step - loss: 0.0634 - accuracy: 0.9990 - val_loss: 0.0829 - val_accuracy: 1.0000
Epoch 6/10
126/126 [==============================] - 165s 1s/step - loss: 0.0526 - accuracy: 0.9995 - val_loss: 0.0729 - val_accuracy: 1.0000
Epoch 7/10
126/126 [==============================] - 164s 1s/step - loss: 0.0465 - accuracy: 0.9995 - val_loss: 0.0641 - val_accuracy: 1.0000
Epoch 8/10
126/126 [==============================] - 163s 1s/step - loss: 0.0463 - accuracy: 0.9985 - val_loss: 0.0595 - val_accuracy: 1.0000
The model is predicting with good accuracy, when i am comparing two dissimilar images. Further it is predicting really good with same class of images.
But when I am comparing Image1 with image1 itself, it is predicting that they are similar only with the probability of 0.5.
in other case if I compare image1 with image2, then it is predicting correctly with a probability of 0.8.(here image1 and image2 belongs to same class)
when I am comparing individual images, it is predicting correctly, I have tried different alternatives did not workout.
May I know what might be the error?
The L1 distance between two equal vectors is always zero.
When you pass the same image, the encodings generated are equal (encoded_l is equal to encoded_r). Hence, the input to your final sigmoid layer is a zero vector.
And, sigmoid(0) = 0.5.
This is the reason providing identical inputs to your model gives 0.5 as the output.
I am trying to build a deep learning model on Keras for a test and I am not very good at this. I have a scaled dataset with 128 features and these correspond to 6 different classes.
I have already tried adding/deleting layers or using regularisation like dropout/l1/l2, My model learns and accuracy goes up so high. But accuracy on test set is around 15%.
from tensorflow.keras.layers import Dense, Dropout
model = Sequential()
model.add(Dense(128, activation='tanh', input_shape=(128,)))
model.add(Dropout(0.5))
model.add(Dense(60, activation='tanh'))
model.add(Dropout(0.5))
model.add(Dense(20, activation='tanh'))
model.add(Dropout(0.5))
model.add(Dense(6, activation='sigmoid'))
model.compile(loss='categorical_crossentropy', optimizer='Nadam', metrics=['accuracy'])
model.fit(train_X, train_y, epochs=20, batch_size=32, verbose=1)
6955/6955 [==============================] - 1s 109us/sample - loss: 1.5805 - acc: 0.3865
Epoch 2/20
6955/6955 [==============================] - 0s 71us/sample - loss: 1.1512 - acc: 0.6505
Epoch 3/20
6955/6955 [==============================] - 0s 71us/sample - loss: 0.9191 - acc: 0.7307
Epoch 4/20
6955/6955 [==============================] - 0s 67us/sample - loss: 0.7819 - acc: 0.7639
Epoch 5/20
6955/6955 [==============================] - 0s 66us/sample - loss: 0.6939 - acc: 0.7882
Epoch 6/20
6955/6955 [==============================] - 0s 69us/sample - loss: 0.6284 - acc: 0.8099
Epoch 7/20
6955/6955 [==============================] - 0s 70us/sample - loss: 0.5822 - acc: 0.8240
Epoch 8/20
6955/6955 [==============================] - 1s 73us/sample - loss: 0.5305 - acc: 0.8367
Epoch 9/20
6955/6955 [==============================] - 1s 75us/sample - loss: 0.5130 - acc: 0.8441
Epoch 10/20
6955/6955 [==============================] - 1s 75us/sample - loss: 0.4703 - acc: 0.8591
Epoch 11/20
6955/6955 [==============================] - 1s 73us/sample - loss: 0.4679 - acc: 0.8650
Epoch 12/20
6955/6955 [==============================] - 1s 77us/sample - loss: 0.4399 - acc: 0.8705
Epoch 13/20
6955/6955 [==============================] - 1s 80us/sample - loss: 0.4055 - acc: 0.8904
Epoch 14/20
6955/6955 [==============================] - 1s 77us/sample - loss: 0.3965 - acc: 0.8874
Epoch 15/20
6955/6955 [==============================] - 1s 77us/sample - loss: 0.3964 - acc: 0.8877
Epoch 16/20
6955/6955 [==============================] - 1s 77us/sample - loss: 0.3564 - acc: 0.9048
Epoch 17/20
6955/6955 [==============================] - 1s 80us/sample - loss: 0.3517 - acc: 0.9087
Epoch 18/20
6955/6955 [==============================] - 1s 78us/sample - loss: 0.3254 - acc: 0.9133
Epoch 19/20
6955/6955 [==============================] - 1s 78us/sample - loss: 0.3367 - acc: 0.9116
Epoch 20/20
6955/6955 [==============================] - 1s 76us/sample - loss: 0.3165 - acc: 0.9192
The result I am recieving 39% With other models like GBM or XGB I can reach upto 85%
What am I doing wrong? Any suggestions?
I tried to code a neural network which is trained on the California housing dataset, which I got from Aurelion Geron's GitHup.
But when I run the code, the net does not get trained and loss = nan.
Can someone explain what I did wrong?
Best regards, Robin
Link for the csv file: https://github.com/ageron/handson-ml/tree/master/datasets/housing
My Code:
import numpy
import pandas as pd
from keras.models import Sequential
from keras.layers import Dense
# load dataset
df = pd.read_csv("housing.csv", delimiter=",", header=0)
# split into input (X) and output (Y) variables
Y = df["median_house_value"].values
X = df.drop("median_house_value", axis=1)
# Inland / Not Inland -> True / False = 1 / 0
X["ocean_proximity"] = X["ocean_proximity"]== "INLAND"
X=X.values
X= X.astype(float)
Y= Y.astype(float)
model = Sequential()
model.add(Dense(100, activation="relu", input_dim=9))
model.add(Dense(1, activation="linear"))
# Compile model
model.compile(loss="mean_squared_error", optimizer="adam")
model.fit(X, Y, epochs=50, batch_size=1000, verbose=1)
I found the error, there was a missing value in the "total_bedrooms" column
You need to drop NaN values from you data.
After having a quick look at data, you also need to normalize your data (as everytime with Neural Nets, to help convergence).
To do this you can use Standard Scaler, Min-Max Scaler etc..
nan values in your DataFrame are causing this behavior. Drop rows with the nan values and normalize your data:
df = df[~df.isnull().any(axis=1)]
df.iloc[:,:-1]=((df.iloc[:,:-1]-df.iloc[:,:-1].min())/(df.iloc[:,:-1].max()-df.iloc[:,:-1].min()))
And you will get:
Epoch 1/50
1000/20433 [>.............................] - ETA: 3s - loss: 0.1732
20433/20433 [==============================] - 0s 11us/step - loss: 0.1001
Epoch 2/50
1000/20433 [>.............................] - ETA: 0s - loss: 0.0527
20433/20433 [==============================] - 0s 3us/step - loss: 0.0430
Epoch 3/50
1000/20433 [>.............................] - ETA: 0s - loss: 0.0388
20433/20433 [==============================] - 0s 2us/step - loss: 0.0338
Epoch 4/50
1000/20433 [>.............................] - ETA: 0s - loss: 0.0301
20433/20433 [==============================] - 0s 2us/step - loss: 0.0288
Epoch 5/50
1000/20433 [>.............................] - ETA: 0s - loss: 0.0300
20433/20433 [==============================] - 0s 2us/step - loss: 0.0259
Epoch 6/50
1000/20433 [>.............................] - ETA: 0s - loss: 0.0235
20433/20433 [==============================] - 0s 3us/step - loss: 0.0238
Epoch 7/50
1000/20433 [>.............................] - ETA: 0s - loss: 0.0242
20433/20433 [==============================] - 0s 2us/step - loss: 0.0225
Epoch 8/50
1000/20433 [>.............................] - ETA: 0s - loss: 0.0213
20433/20433 [==============================] - 0s 2us/step - loss: 0.0218
Epoch 9/50
1000/20433 [>.............................] - ETA: 0s - loss: 0.0228
20433/20433 [==============================] - 0s 2us/step - loss: 0.0214
Epoch 10/50
1000/20433 [>.............................] - ETA: 0s - loss: 0.0206
20433/20433 [==============================] - 0s 2us/step - loss: 0.0211
I have a question about my NN model. I am using keras from python. My training consists of 1000 samples, each with 4320 features. There are 10 categories, and my Y contains numpy arrays of 10 elements with 0 on all the positions except one.
However, my NN doesn't learn from the first epoch and I probably have my model wrong, it's my first attempt of building a NN model and I must have got wrong a couple of things.
Epoch 1/150
1000/1000 [==============================] - 40s 40ms/step - loss: 6.7110 - acc: 0.5796
Epoch 2/150
1000/1000 [==============================] - 39s 39ms/step - loss: 6.7063 - acc: 0.5800
Epoch 3/150
1000/1000 [==============================] - 38s 38ms/step - loss: 6.7063 - acc: 0.5800
Epoch 4/150
1000/1000 [==============================] - 39s 39ms/step - loss: 6.7063 - acc: 0.5800
Epoch 5/150
1000/1000 [==============================] - 38s 38ms/step - loss: 6.7063 - acc: 0.5800
Epoch 6/150
1000/1000 [==============================] - 38s 38ms/step - loss: 6.7063 - acc: 0.5800
Epoch 7/150
1000/1000 [==============================] - 40s 40ms/step - loss: 6.7063 - acc: 0.5800
Epoch 8/150
1000/1000 [==============================] - 39s 39ms/step - loss: 6.7063 - acc: 0.5800
Epoch 9/150
1000/1000 [==============================] - 40s 40ms/step - loss: 6.7063 - acc: 0.5800
And this is part of my NN code:
model = Sequential()
model.add(Dense(4320, input_dim=4320, activation='relu'))
model.add(Dense(50, activation='relu'))
model.add(Dense(10, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X, Y, epochs=150, batch_size=10)
So, my X is a numpy array of length 1000 that contains other numpy arrays of 4320 elements. My Y is a numpy array of length 1000 that contains other numpy arrays of 10 elements (categories).
Am I doing something wrong or it just can't learn based on this training set? (On 1NN with manhattan distance I'm getting ~80% accuracy on this training set)
L.E.: After I've normalized the data, this is the output of my first 10 epochs:
Epoch 1/150
1000/1000 [==============================] - 41s 41ms/step - loss: 7.9834 - acc: 0.4360
Epoch 2/150
1000/1000 [==============================] - 41s 41ms/step - loss: 7.2943 - acc: 0.5080
Epoch 3/150
1000/1000 [==============================] - 39s 39ms/step - loss: 9.0326 - acc: 0.4070
Epoch 4/150
1000/1000 [==============================] - 39s 39ms/step - loss: 8.7106 - acc: 0.4320
Epoch 5/150
1000/1000 [==============================] - 40s 40ms/step - loss: 7.7547 - acc: 0.4900
Epoch 6/150
1000/1000 [==============================] - 44s 44ms/step - loss: 7.2591 - acc: 0.5270
Epoch 7/150
1000/1000 [==============================] - 42s 42ms/step - loss: 8.5002 - acc: 0.4560
Epoch 8/150
1000/1000 [==============================] - 41s 41ms/step - loss: 9.9525 - acc: 0.3720
Epoch 9/150
1000/1000 [==============================] - 40s 40ms/step - loss: 9.7160 - acc: 0.3920
Epoch 10/150
1000/1000 [==============================] - 39s 39ms/step - loss: 9.3523 - acc: 0.4140
Looks like it starts fluctuating so that seems to be good
It seems like your categories, classes are mutually exclusive since your target arrays are one-hot encoded (ie you never have to predict 2 classes at the same time). In that case, you should use softmax on your last layer to produce a distribution and train using categorical_crossentropy. If fact you can just set your targets as Y = [2,4,0,1] as your category indices and train with sparse_categorical_crossentropy which will save you the time of creating a 2 array of shape (samples, 10).
It seems like you have a lot of features, most likely the performance of your network will depend on how you pre-process your data. For continuous inputs, it's wise to normalise it and for discrete input encode it as one-hot to help the learning.