I have seen many questions of this problem online, but there are no definitive solutions and my case might be different, as it is with time series data and a LSTM architecture.
model = Sequential()
model.add(LSTM(50, activation='relu', return_sequences=True, input_shape=(n_steps, n_features)))
model.add(LSTM(50, activation='relu'))
model.add(Dense(1, activation = 'sigmoid'))
model.compile(optimizer='adam', loss='binary_crossentropy',metrics=['accuracy'])
Logs:
Train on 290 samples, validate on 190 samples
Epoch 1/4000
- 1s - loss: 0.6896 - accuracy: 0.5586 - val_loss: 0.6846 - val_accuracy: 0.6105
Epoch 2/4000
- 0s - loss: 0.6890 - accuracy: 0.5586 - val_loss: 0.6843 - val_accuracy: 0.6105
Epoch 3/4000
- 0s - loss: 0.6889 - accuracy: 0.5586 - val_loss: 0.6829 - val_accuracy: 0.6105
Epoch 4/4000
- 0s - loss: 0.6884 - accuracy: 0.5586 - val_loss: 0.6827 - val_accuracy: 0.6105
Epoch 5/4000
- 0s - loss: 0.6883 - accuracy: 0.5586 - val_loss: 0.6825 - val_accuracy: 0.6105
Epoch 6/4000
- 0s - loss: 0.6882 - accuracy: 0.5586 - val_loss: 0.6822 - val_accuracy: 0.6105
Epoch 7/4000
- 0s - loss: 0.6882 - accuracy: 0.5586 - val_loss: 0.6820 - val_accuracy: 0.6105
Epoch 8/4000
- 0s - loss: 0.6880 - accuracy: 0.5586 - val_loss: 0.6818 - val_accuracy: 0.6105
Epoch 9/4000
- 0s - loss: 0.6880 - accuracy: 0.5586 - val_loss: 0.6806 - val_accuracy: 0.6105
Epoch 10/4000
- 0s - loss: 0.6876 - accuracy: 0.5586 - val_loss: 0.6795 - val_accuracy: 0.6105
Couple of things to try:
Decrease the learning rate.
Is the dataset imbalanced? If it is then the model has learned to predict only one class (Which I think is the cause here).
Try giving the imbalanced class more weight check this.
Try to reset the model, tf.keras.backend.clear_session.
Try ensembling, weak learners.
Better yet, try a basic time series regression model like ARMA for baseline results.
Related
I'm a newbie with deep learning and I try to create a model and I don't really understand the model. add(layers). I m sure that the input shape (it's for recognition). I think the problem is in the Dropout, but I don't understand the value.
Can someone explains to me the
model = models.Sequential()
model.add(layers.Conv2D(32, (3,3), activation = 'relu', input_shape = (128,128,3)))
model.add(layers.MaxPooling2D((2,2)))
model.add(layers.Conv2D(64, (3,3), activation = 'relu'))
model.add(layers.MaxPooling2D((2,2)))
model.add(layers.Flatten())
model.add(layers.Dropout(0.5))
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dense(6, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer=optimizers.Adam(lr=1e-4), metrics=['acc'])
-------------------------------------------------------
history = model.fit(
train_data,
train_labels,
epochs=30,
validation_data=(test_data, test_labels),
)
and here is the result :
Epoch 15/30
5/5 [==============================] - 0s 34ms/step - loss: 0.3987 - acc: 0.8536 - val_loss: 0.7021 - val_acc: 0.7143
Epoch 16/30
5/5 [==============================] - 0s 31ms/step - loss: 0.3223 - acc: 0.8891 - val_loss: 0.6393 - val_acc: 0.7778
Epoch 17/30
5/5 [==============================] - 0s 32ms/step - loss: 0.3321 - acc: 0.9082 - val_loss: 0.6229 - val_acc: 0.7460
Epoch 18/30
5/5 [==============================] - 0s 31ms/step - loss: 0.2615 - acc: 0.9409 - val_loss: 0.6591 - val_acc: 0.8095
Epoch 19/30
5/5 [==============================] - 0s 32ms/step - loss: 0.2161 - acc: 0.9857 - val_loss: 0.6368 - val_acc: 0.7143
Epoch 20/30
5/5 [==============================] - 0s 33ms/step - loss: 0.1773 - acc: 0.9857 - val_loss: 0.5644 - val_acc: 0.7778
Epoch 21/30
5/5 [==============================] - 0s 32ms/step - loss: 0.1650 - acc: 0.9782 - val_loss: 0.5459 - val_acc: 0.8413
Epoch 22/30
5/5 [==============================] - 0s 31ms/step - loss: 0.1534 - acc: 0.9789 - val_loss: 0.5738 - val_acc: 0.7460
Epoch 23/30
5/5 [==============================] - 0s 32ms/step - loss: 0.1205 - acc: 0.9921 - val_loss: 0.5351 - val_acc: 0.8095
Epoch 24/30
5/5 [==============================] - 0s 32ms/step - loss: 0.0967 - acc: 1.0000 - val_loss: 0.5256 - val_acc: 0.8413
Epoch 25/30
5/5 [==============================] - 0s 32ms/step - loss: 0.0736 - acc: 1.0000 - val_loss: 0.5493 - val_acc: 0.7937
Epoch 26/30
5/5 [==============================] - 0s 32ms/step - loss: 0.0826 - acc: 1.0000 - val_loss: 0.5342 - val_acc: 0.8254
Epoch 27/30
5/5 [==============================] - 0s 32ms/step - loss: 0.0687 - acc: 1.0000 - val_loss: 0.5452 - val_acc: 0.8254
Epoch 28/30
5/5 [==============================] - 0s 32ms/step - loss: 0.0571 - acc: 1.0000 - val_loss: 0.5176 - val_acc: 0.7937
Epoch 29/30
5/5 [==============================] - 0s 32ms/step - loss: 0.0549 - acc: 1.0000 - val_loss: 0.5142 - val_acc: 0.8095
Epoch 30/30
5/5 [==============================] - 0s 32ms/step - loss: 0.0479 - acc: 1.0000 - val_loss: 0.5243 - val_acc: 0.8095
I never depassed the 70% average but on this i have 80% but i think i'm on overfitting.. I evidemently searched on differents docs but i'm lost
Have you try following into your training:
Data Augmentation
Pre-trained Model
Looking at the execution time per epoch, it looks like your data set is pretty small. Also, it's not clear whether there is any class imbalance in your dataset. You probably should try stratified CV training and analysis on the folds results. It won't prevent overfit but it will eventually give you more insight into your model, which generally can help to reduce overfitting. However, preventing overfitting is a general topic, search online to get resources. You can also try this
model.compile(loss='categorical_crossentropy',
optimizer='adam, metrics=['acc'])
-------------------------------------------------------
# src: https://keras.io/api/callbacks/reduce_lr_on_plateau/
# reduce learning rate by a factor of 0.2 if val_loss -
# won't improve within 5 epoch.
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2,
patience=5, min_lr=0.00001)
# src: https://keras.io/api/callbacks/early_stopping/
# stop training if val_loss don't improve within 15 epoch.
early_stop = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=15)
history = model.fit(
train_data,
train_labels,
epochs=30,
validation_data=(test_data, test_labels),
callbacks=[reduce_lr, early_stop]
)
You may also find it useful of using ModelCheckpoint or LearningRateScheduler. This doesn't guarantee of no overfit but some approach for that to adopt.
I am fairly new to deep learning and right now am trying to predict consumer choices based on EEG data. The total dataset consists of 1045 EEG recordings each with a corresponding label, indicating Like or Dislike for a product. Classes are distributed as follows (44% Likes and 56% Dislikes). I read that Convolutional Neural Networks are suitable to work with raw EEG data so I tried to implement a network based on keras with the following structure:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(full_data, target, test_size=0.20, random_state=42)
y_train = np.asarray(y_train).astype('float32').reshape((-1,1))
y_test = np.asarray(y_test).astype('float32').reshape((-1,1))
# X_train.shape = ((836, 512, 14))
# y_train.shape = ((836, 1))
from keras.optimizers import Adam
from keras.optimizers import SGD
from keras.layers import MaxPooling1D
model = Sequential()
model.add(Conv1D(16, kernel_size=3, activation="relu", input_shape=(512,14)))
model.add(MaxPooling1D())
model.add(Conv1D(8, kernel_size=3, activation="relu"))
model.add(MaxPooling1D())
model.add(Flatten())
model.add(Dense(1, activation="sigmoid"))
model.compile(optimizer=Adam(lr = 0.001), loss='binary_crossentropy', metrics=['accuracy'])
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=20, batch_size = 64)
When I fit the model however the validation accuracy does not change at all with the following output:
Epoch 1/20
14/14 [==============================] - 0s 32ms/step - loss: 292.6353 - accuracy: 0.5383 - val_loss: 0.7884 - val_accuracy: 0.5407
Epoch 2/20
14/14 [==============================] - 0s 7ms/step - loss: 1.3748 - accuracy: 0.5598 - val_loss: 0.8860 - val_accuracy: 0.5502
Epoch 3/20
14/14 [==============================] - 0s 6ms/step - loss: 1.0537 - accuracy: 0.5598 - val_loss: 0.7629 - val_accuracy: 0.5455
Epoch 4/20
14/14 [==============================] - 0s 6ms/step - loss: 0.8827 - accuracy: 0.5598 - val_loss: 0.7010 - val_accuracy: 0.5455
Epoch 5/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7988 - accuracy: 0.5598 - val_loss: 0.8689 - val_accuracy: 0.5407
Epoch 6/20
14/14 [==============================] - 0s 6ms/step - loss: 1.0221 - accuracy: 0.5610 - val_loss: 0.6961 - val_accuracy: 0.5455
Epoch 7/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7415 - accuracy: 0.5598 - val_loss: 0.6945 - val_accuracy: 0.5455
Epoch 8/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7381 - accuracy: 0.5574 - val_loss: 0.7761 - val_accuracy: 0.5455
Epoch 9/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7326 - accuracy: 0.5598 - val_loss: 0.6926 - val_accuracy: 0.5455
Epoch 10/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7338 - accuracy: 0.5598 - val_loss: 0.6917 - val_accuracy: 0.5455
Epoch 11/20
14/14 [==============================] - 0s 7ms/step - loss: 0.7203 - accuracy: 0.5610 - val_loss: 0.6916 - val_accuracy: 0.5455
Epoch 12/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7192 - accuracy: 0.5610 - val_loss: 0.6914 - val_accuracy: 0.5455
Epoch 13/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7174 - accuracy: 0.5610 - val_loss: 0.6912 - val_accuracy: 0.5455
Epoch 14/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7155 - accuracy: 0.5610 - val_loss: 0.6911 - val_accuracy: 0.5455
Epoch 15/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7143 - accuracy: 0.5610 - val_loss: 0.6910 - val_accuracy: 0.5455
Epoch 16/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7129 - accuracy: 0.5610 - val_loss: 0.6909 - val_accuracy: 0.5455
Epoch 17/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7114 - accuracy: 0.5610 - val_loss: 0.6907 - val_accuracy: 0.5455
Epoch 18/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7103 - accuracy: 0.5610 - val_loss: 0.6906 - val_accuracy: 0.5455
Epoch 19/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7088 - accuracy: 0.5610 - val_loss: 0.6906 - val_accuracy: 0.5455
Epoch 20/20
14/14 [==============================] - 0s 6ms/step - loss: 0.7075 - accuracy: 0.5610 - val_loss: 0.6905 - val_accuracy: 0.5455
Thanks in advance for any insights!
The phenomenon you run into is called underfitting. This happens when the amount our quality of your training data is insufficient, or your network architecture is too small and not capable to learn the problem.
Try normalizing your input data and experiment with different network architectures, learning rates and activation functions.
As #Muhammad Shahzad stated in his comment, adding some Dense Layers after flatting would be a concrete architecture adaption you should try.
You can also increase the epoch and must increase the data set. And you also can use-
train_datagen= ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True,
vertical_flip = True,
channel_shift_range=0.2,
fill_mode='nearest'
)
for feeding the model more data and I hope you can increase the validation_accuracy.
I'm new to Keras and I'm using it to build a normal Neural Network to classify number MNIST dataset.
Beforehand I have already split the data into 3 parts: 55000 to train, 5000 to evaluate and 10000 to test, and I have scaled the pixel density down (by dividing it by 255.0)
My model looks like this:
model = keras.models.Sequential()
model.add(keras.layers.Flatten(input_shape=[28,28]))
model.add(keras.layers.Dense(100, activation='relu'))
model.add(keras.layers.Dense(10, activation='softmax'))
And here is the compile:
model.compile(loss='sparse_categorical_crossentropy',
optimizer = 'Adam',
metrics=['accuracy'])
I train the model:
his = model.fit(xTrain, yTrain, epochs = 20, validation_data=(xValid, yValid))
At first the val_loss decreases, then it increases although the accuracy is increasing.
Train on 55000 samples, validate on 5000 samples
Epoch 1/20
55000/55000 [==============================] - 5s 91us/sample - loss: 0.2822 - accuracy: 0.9199 - val_loss: 0.1471 - val_accuracy: 0.9588
Epoch 2/20
55000/55000 [==============================] - 5s 82us/sample - loss: 0.1274 - accuracy: 0.9626 - val_loss: 0.1011 - val_accuracy: 0.9710
Epoch 3/20
55000/55000 [==============================] - 5s 83us/sample - loss: 0.0899 - accuracy: 0.9734 - val_loss: 0.0939 - val_accuracy: 0.9742
Epoch 4/20
55000/55000 [==============================] - 5s 84us/sample - loss: 0.0674 - accuracy: 0.9796 - val_loss: 0.0760 - val_accuracy: 0.9770
Epoch 5/20
55000/55000 [==============================] - 5s 94us/sample - loss: 0.0541 - accuracy: 0.9836 - val_loss: 0.0842 - val_accuracy: 0.9742
Epoch 15/20
55000/55000 [==============================] - 4s 82us/sample - loss: 0.0103 - accuracy: 0.9967 - val_loss: 0.0963 - val_accuracy: 0.9788
Epoch 16/20
55000/55000 [==============================] - 5s 84us/sample - loss: 0.0092 - accuracy: 0.9973 - val_loss: 0.0956 - val_accuracy: 0.9774
Epoch 17/20
55000/55000 [==============================] - 5s 82us/sample - loss: 0.0081 - accuracy: 0.9977 - val_loss: 0.0977 - val_accuracy: 0.9770
Epoch 18/20
55000/55000 [==============================] - 5s 85us/sample - loss: 0.0076 - accuracy: 0.9977 - val_loss: 0.1057 - val_accuracy: 0.9760
Epoch 19/20
55000/55000 [==============================] - 5s 83us/sample - loss: 0.0063 - accuracy: 0.9980 - val_loss: 0.1108 - val_accuracy: 0.9774
Epoch 20/20
55000/55000 [==============================] - 5s 85us/sample - loss: 0.0066 - accuracy: 0.9980 - val_loss: 0.1056 - val_accuracy: 0.9768
And when I evaluate the loss is too high:
model.evaluate(xTest, yTest)
Result:
10000/10000 [==============================] - 0s 41us/sample - loss: 25.7150 - accuracy: 0.9740
[25.714989705941953, 0.974]
Is this ok, or is it a sign of overfitting? Should I do something to improve it? Thanks in advance.
Usually, it is not Ok. You want the loss rate to be as small as possible. Your result is typical for overfitting. Your Network 'knows' its training data, but isn't capable of analysing new Images. You may want to add some layers. Maybe Convolutional Layers, Dropout Layer... another idea would be to augment your training images. The ImageDataGenerator-Class provided by Keras might help you out here
Another thing to look at could be your hyperparameters. Why do you use 100 nodes in the first dense layer? maybe something like 784 (28*28) seems more interesting if you want to start with a dense layer. I would suggest some combination of Convolutional-Dropout-Dense. Then your dense -layer maybe doesn't need that many nodes...
I am using a neural network for a binary classification problem but I am running into some trouble. Sometimes when running my model, my validation accuracy doesn't change at all and sometimes it works just fine. My dataset has 1200 samples with 28 features and I have a class imbalance (200 class a 1000 class b).All my features are normalized and are between 1 and 0. As I stated before this problem doesn't always happen but I want to know why and fix it
I have tried changing the optimisation function and the activation function but that did me no good. I have also noticed that when I increased the number of neurons in my network this problem occurs less often but it wasn't fixed.I also tried increasing the number of epochs but the problem keeps occuring sometimes
model = Sequential()
model.add(Dense(28, input_dim=28,kernel_initializer='normal', activation='sigmoid'))
model.add(Dense(200, kernel_initializer='normal',activation='sigmoid'))
model.add(Dropout(0.5))
model.add(Dense(300, kernel_initializer='normal',activation='sigmoid'))
model.add(Dropout(0.5))
model.add(Dense(300, kernel_initializer='normal',activation='sigmoid'))
model.add(Dropout(0.5))
model.add(Dense(150, kernel_initializer='normal',activation='sigmoid'))
model.add(Dropout(0.4))
model.add(Dense(1,kernel_initializer='normal'))
model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
history = model.fit(X_train, y_train,
epochs=34,
batch_size=32,
validation_data=(X_val, y_val),
verbose=1)
This is the result I get sometimes from training my model
Epoch 1/34
788/788 [==============================] - 1s 2ms/step - loss: 1.5705 - acc: 0.6865 - val_loss: 0.6346 - val_acc: 0.7783
Epoch 2/34
788/788 [==============================] - 0s 211us/step - loss: 1.0262 - acc: 0.6231 - val_loss: 0.5310 - val_acc: 0.7783
Epoch 3/34
788/788 [==============================] - 0s 194us/step - loss: 1.7575 - acc: 0.7221 - val_loss: 0.5431 - val_acc: 0.7783
Epoch 4/34
788/788 [==============================] - 0s 218us/step - loss: 0.9113 - acc: 0.5774 - val_loss: 0.5685 - val_acc: 0.7783
Epoch 5/34
788/788 [==============================] - 0s 199us/step - loss: 1.0987 - acc: 0.6688 - val_loss: 0.6435 - val_acc: 0.7783
Epoch 6/34
788/788 [==============================] - 0s 201us/step - loss: 0.9777 - acc: 0.5343 - val_loss: 0.5643 - val_acc: 0.7783
Epoch 7/34
788/788 [==============================] - 0s 204us/step - loss: 1.0603 - acc: 0.5914 - val_loss: 0.6266 - val_acc: 0.7783
Epoch 8/34
788/788 [==============================] - 0s 197us/step - loss: 0.7580 - acc: 0.5939 - val_loss: 0.6615 - val_acc: 0.7783
Epoch 9/34
788/788 [==============================] - 0s 206us/step - loss: 0.8950 - acc: 0.6650 - val_loss: 0.5291 - val_acc: 0.7783
Epoch 10/34
788/788 [==============================] - 0s 230us/step - loss: 0.8114 - acc: 0.6701 - val_loss: 0.5428 - val_acc: 0.7783
Epoch 11/34
788/788 [==============================] - 0s 281us/step - loss: 0.7235 - acc: 0.6624 - val_loss: 0.5275 - val_acc: 0.7783
Epoch 12/34
788/788 [==============================] - 0s 264us/step - loss: 0.7237 - acc: 0.6485 - val_loss: 0.5473 - val_acc: 0.7783
Epoch 13/34
788/788 [==============================] - 0s 213us/step - loss: 0.6902 - acc: 0.7056 - val_loss: 0.5265 - val_acc: 0.7783
Epoch 14/34
788/788 [==============================] - 0s 217us/step - loss: 0.6726 - acc: 0.7145 - val_loss: 0.5285 - val_acc: 0.7783
Epoch 15/34
788/788 [==============================] - 0s 197us/step - loss: 0.6656 - acc: 0.7132 - val_loss: 0.5354 - val_acc: 0.7783
Epoch 16/34
788/788 [==============================] - 0s 216us/step - loss: 0.6083 - acc: 0.7259 - val_loss: 0.5262 - val_acc: 0.7783
Epoch 17/34
788/788 [==============================] - 0s 218us/step - loss: 0.6188 - acc: 0.7310 - val_loss: 0.5271 - val_acc: 0.7783
Epoch 18/34
788/788 [==============================] - 0s 210us/step - loss: 0.6642 - acc: 0.6142 - val_loss: 0.5676 - val_acc: 0.7783
Epoch 19/34
788/788 [==============================] - 0s 200us/step - loss: 0.6017 - acc: 0.7221 - val_loss: 0.5256 - val_acc: 0.7783
Epoch 20/34
788/788 [==============================] - 0s 209us/step - loss: 0.6188 - acc: 0.7157 - val_loss: 0.8090 - val_acc: 0.2217
Epoch 21/34
788/788 [==============================] - 0s 201us/step - loss: 1.1724 - acc: 0.4061 - val_loss: 0.5448 - val_acc: 0.7783
Epoch 22/34
788/788 [==============================] - 0s 205us/step - loss: 0.5724 - acc: 0.7424 - val_loss: 0.5293 - val_acc: 0.7783
Epoch 23/34
788/788 [==============================] - 0s 234us/step - loss: 0.5829 - acc: 0.7538 - val_loss: 0.5274 - val_acc: 0.7783
Epoch 24/34
788/788 [==============================] - 0s 209us/step - loss: 0.5815 - acc: 0.7525 - val_loss: 0.5274 - val_acc: 0.7783
Epoch 25/34
788/788 [==============================] - 0s 220us/step - loss: 0.5688 - acc: 0.7576 - val_loss: 0.5274 - val_acc: 0.7783
Epoch 26/34
788/788 [==============================] - 0s 210us/step - loss: 0.5715 - acc: 0.7525 - val_loss: 0.5273 - val_acc: 0.7783
Epoch 27/34
788/788 [==============================] - 0s 206us/step - loss: 0.5584 - acc: 0.7576 - val_loss: 0.5274 - val_acc: 0.7783
Epoch 28/34
788/788 [==============================] - 0s 215us/step - loss: 0.5728 - acc: 0.7563 - val_loss: 0.5272 - val_acc: 0.7783
Epoch 29/34
788/788 [==============================] - 0s 281us/step - loss: 0.5735 - acc: 0.7576 - val_loss: 0.5275 - val_acc: 0.7783
Epoch 30/34
788/788 [==============================] - 0s 272us/step - loss: 0.5773 - acc: 0.7614 - val_loss: 0.5272 - val_acc: 0.7783
Epoch 31/34
788/788 [==============================] - 0s 225us/step - loss: 0.5847 - acc: 0.7525 - val_loss: 0.5272 - val_acc: 0.7783
Epoch 32/34
788/788 [==============================] - 0s 239us/step - loss: 0.5739 - acc: 0.7551 - val_loss: 0.5272 - val_acc: 0.7783
Epoch 33/34
788/788 [==============================] - 0s 216us/step - loss: 0.5632 - acc: 0.7525 - val_loss: 0.5269 - val_acc: 0.7783
Epoch 34/34
788/788 [==============================] - 0s 240us/step - loss: 0.5672 - acc: 0.7576 - val_loss: 0.5267 - val_acc: 0.7783
Given your reported class imbalance, your model does not seem to learn anything (the reported accuracy seems consistent with just predicting everything as the majority class). Nevertheless, there are issues with your code; for starters:
Replace all activation functions except for the output layer to activation = 'relu'.
Add a sigmoid activation function to your last layer activation='sigmoid'; as is, yours is a regression network (default linear output in the last layer) and not a classification one.
Remove all kernel_initializer='normal' arguments from all your layers, i.e. leave it to the default one kernel_initializer='glorot_uniform', which is known to achieve (much) better performance.
Also, not clear why you go for an input dense layer of 28 units - no. of units here has nothing to do with the input dimension; please see Keras Sequential model input layer.
Dropout should not go into the network by default - try first without it and then add if necessary.
All in all, here is how your model should look for starters:
model = Sequential()
model.add(Dense(200, input_dim=28, activation='relu'))
# model.add(Dropout(0.5))
model.add(Dense(300, activation='relu'))
# model.add(Dropout(0.5))
model.add(Dense(300, activation='relu'))
# model.add(Dropout(0.5))
model.add(Dense(150, activation='relu'))
# model.add(Dropout(0.4))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
and, as said, uncomment/adjust the dropout layers depending on your experimental results.
I am learning to write CNNs in Keras on Kaggle using one of the datasets I found there.
The link to my notebook is
https://www.kaggle.com/vj6978/brain-tumor-vimal?scriptVersionId=16814133
The code, the dataset and the ROC curve are available at the link. The ROC curve itself looks as if the model is simply making guesses rather than a learned prediction.
The testing accuracy also seems to peak at around 60% to 70% only which is quiet low. Any help would be appreciated.
Thanks
Vimal James
I believe your last activation should be sigmoid instead of softmax.
UPDATE :
Just forked your kernel on Kaggle and modifying as follows gives better results :
model = Sequential()
model.add(Conv2D(128, (3,3), input_shape = data_set.shape[1:]))
model.add(Activation("relu"))
model.add(AveragePooling2D(pool_size = (2,2)))
model.add(Conv2D(128, (3,3)))
model.add(Activation("relu"))
model.add(AveragePooling2D(pool_size = (2,2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Dense(1))
model.add(Activation("sigmoid")) # Last activation should be sigmoid for binary classification
model.compile(optimizer = "adam", loss = "binary_crossentropy", metrics = ['accuracy'])
This gave the following results :
rain on 204 samples, validate on 23 samples
Epoch 1/15
204/204 [==============================] - 2s 11ms/step - loss: 2.8873 - acc: 0.6373 - val_loss: 0.8000 - val_acc: 0.8261
Epoch 2/15
204/204 [==============================] - 1s 3ms/step - loss: 0.7292 - acc: 0.7206 - val_loss: 0.6363 - val_acc: 0.7391
Epoch 3/15
204/204 [==============================] - 1s 3ms/step - loss: 0.4731 - acc: 0.8088 - val_loss: 0.5417 - val_acc: 0.8261
Epoch 4/15
204/204 [==============================] - 1s 3ms/step - loss: 0.3605 - acc: 0.8775 - val_loss: 0.6820 - val_acc: 0.8696
Epoch 5/15
204/204 [==============================] - 1s 3ms/step - loss: 0.2986 - acc: 0.8529 - val_loss: 0.8356 - val_acc: 0.8696
Epoch 6/15
204/204 [==============================] - 1s 3ms/step - loss: 0.2151 - acc: 0.9020 - val_loss: 0.7592 - val_acc: 0.8696
Epoch 7/15
204/204 [==============================] - 1s 3ms/step - loss: 0.1305 - acc: 0.9657 - val_loss: 1.2486 - val_acc: 0.8696
Epoch 8/15
204/204 [==============================] - 1s 3ms/step - loss: 0.0565 - acc: 0.9853 - val_loss: 1.2668 - val_acc: 0.8696
Epoch 9/15
204/204 [==============================] - 1s 3ms/step - loss: 0.0426 - acc: 0.9853 - val_loss: 1.4674 - val_acc: 0.8696
Epoch 10/15
204/204 [==============================] - 1s 3ms/step - loss: 0.0141 - acc: 1.0000 - val_loss: 1.7379 - val_acc: 0.8696
Epoch 11/15
204/204 [==============================] - 1s 3ms/step - loss: 0.0063 - acc: 1.0000 - val_loss: 1.7232 - val_acc: 0.8696
Epoch 12/15
204/204 [==============================] - 1s 3ms/step - loss: 0.0023 - acc: 1.0000 - val_loss: 1.8291 - val_acc: 0.8696
Epoch 13/15
204/204 [==============================] - 1s 3ms/step - loss: 0.0014 - acc: 1.0000 - val_loss: 1.9164 - val_acc: 0.8696
Epoch 14/15
204/204 [==============================] - 1s 3ms/step - loss: 8.6263e-04 - acc: 1.0000 - val_loss: 1.8946 - val_acc: 0.8696
Epoch 15/15
204/204 [==============================] - 1s 3ms/step - loss: 6.8785e-04 - acc: 1.0000 - val_loss: 1.9596 - val_acc: 0.8696
Test loss: 3.079359292984009
Test accuracy: 0.807692289352417
You are using a softmax activation with a single neuron, this will always produce constant 1.0 output, due to the normalization used in softmax, so it makes no sense. For binary classification you have to use the sigmoid activation with a single output neuron.