Skip to main content
Cross Validated

Return to Question

Post Reopened by Sycorax♦, whuber♦
Post Closed as "Not suitable for this site" by Michael R. Chernick, Sycorax♦, Peter Flom
Adjusted some spelling in text and added the figures.
Source Link
edit approved Dec 17, 2019 at 11:07
horseoftheyear
edit approved Dec 17, 2019 at 11:07
horseoftheyear
  • 508
  • 6
  • 12

I'm strugglestruggling with a problem OF class probabilities (binary,: 0 and 1). DontI don't know why but after 100 epochesepochs the probabilities became 0 or 1 (like the class to predict). Maybe something is not working with the code or I missing something?

Train data is 20.000 rows (more or less),; test data is 2000 rows. Each Each row is a match where 0 is lost and 1 is won.

theThe probabilities of the class are 1 or 0 and not a value between 1 and 0. This happen after 100 epoches.

A data test with prediction after 100 epoches is like this:

Model loss

Model accuracy

I'm struggle with a problem OF class probabilities (binary, 0 and 1). Dont know why but after 100 epoches the probabilities became 0 or 1 (like the class to predict). Maybe something is not working with the code or I missing something?

Train data is 20.000 rows (more or less), test data is 2000 rows. Each row is a match where 0 is lost and 1 is won.

the probabilities of the class are 1 or 0 and not a value between 1 and 0. This happen after 100 epoches.

data test with prediction after 100 epoches is like this:

I'm struggling with a problem OF class probabilities (binary: 0 and 1). I don't know why but after 100 epochs the probabilities became 0 or 1 (like the class to predict). Maybe something is not working with the code or I missing something?

Train data is 20.000 rows (more or less); test data is 2000 rows. Each row is a match where 0 is lost and 1 is won.

The probabilities of the class are 1 or 0 and not a value between 1 and 0. A data test with prediction after 100 epoches is like this:

Model loss

Model accuracy

added 837 characters in body
Source Link
Mirko Piccolo
Mirko Piccolo
  • 133
  • 5

the probabilities of the class are 1 or 0 and not a value between 1 and 0. This happen after 100 epoches.

data test with prediction after 100 epoches is like this:

**RESULT**   VALUE_A     VALUE_B     VALUE_C    **PRED_0    PRED_1**
   0           4          5          3           1          0
   0           7          4          5           0          1
   1           6          7          6           0          1
   1           2          3          4           0          1

What I'm looking for:

**RESULT**   VALUE_A     VALUE_B     VALUE_C    **PRED_0    PRED_1**
   0           4          5          3           0.65          0.35
   0           7          4          5           0.25          0.75
   1           6          7          6           0.20          0.80
   1           2          3          4           0.30          0.70

Plus, someone could please give me some advice looking at accuracy and loss graph?

Plus, someone could please give me some advice looking at accuracy and loss graph?

the probabilities of the class are 1 or 0 and not a value between 1 and 0. This happen after 100 epoches.

data test with prediction after 100 epoches is like this:

**RESULT**   VALUE_A     VALUE_B     VALUE_C    **PRED_0    PRED_1**
   0           4          5          3           1          0
   0           7          4          5           0          1
   1           6          7          6           0          1
   1           2          3          4           0          1

What I'm looking for:

**RESULT**   VALUE_A     VALUE_B     VALUE_C    **PRED_0    PRED_1**
   0           4          5          3           0.65          0.35
   0           7          4          5           0.25          0.75
   1           6          7          6           0.20          0.80
   1           2          3          4           0.30          0.70

Plus, someone could please give me some advice looking at accuracy and loss graph?

Source Link
Mirko Piccolo
Mirko Piccolo
  • 133
  • 5

Probabilities in keras (python in R markdown)

I'm struggle with a problem OF class probabilities (binary, 0 and 1). Dont know why but after 100 epoches the probabilities became 0 or 1 (like the class to predict). Maybe something is not working with the code or I missing something?

Train data is 20.000 rows (more or less), test data is 2000 rows. Each row is a match where 0 is lost and 1 is won.

y_train_binary = keras.utils.to_categorical(Y, 2)
y_test_binary = keras.utils.to_categorical(t_Y, 2)
model = Sequential()
model.add(Dense(40, input_dim=45, activation='relu'))
model.add(Dropout(0.05))
model.add(BatchNormalization())
model.add(Dense(30, activation='relu'))
model.add(Dropout(0.05))
model.add(BatchNormalization())
model.add(Dense(20, activation='relu'))
model.add(Dropout(0.05))
model.add(BatchNormalization())
model.add(Dense(10, activation='relu'))
model.add(Dropout(0.05))
model.add(BatchNormalization())
model.add(Dense(2, activation='softmax'))
keras.optimizers.Adam(lr=0.5, beta_1=0.9, beta_2=0.999, epsilon=0.3)
model.compile(loss='categorical_crossentropy', optimizer='Adam', metrics=['accuracy']) 
model.fit(X, y_train_binary, epochs=300, validation_split=0.2, batch_size=10, verbose=0)
prediction_classes = model.predict_proba(t_X)
numpy.savetxt("C:/Users/Megaport/Desktop/foo.csv", prediction_classes, delimiter=",")

I've tried so many parameters (learning rate, epochs, batch size, epsilon, add layer, less layer, different value of dropout) but the problem is the same: probs are not working.

Plus, someone could please give me some advice looking at accuracy and loss graph?