How can I see the scores of every class after run the predict

I have a classified network for the MNIST dataset (csv) with 10 labels which are numbers (0,1,2,3,4,5,6,7,8,9) and after training the network, I run the predict_classes for test_data. I want to know for each of the data in test_set what is the score of every label(0,1,2,3,4,5,6,7,8,9) in y_pred. for example if predict_classes say that for first data the label is "7" what is the score of 7 and what is the scores of other labels such (0,1,2,3,4,5,6,8,9) How can I write its code?

from keras import models 
import numpy as np
from keras import layers
import tensorflow as  tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, LSTM, BatchNormalization
mnist = tf.keras.datasets.mnist
#Load dataset
(x_train, y_train), (x_test, y_test) = mnist.load_data()
#normalizing data
x_train = x_train / 255.0
x_test = x_test / 255.0

# bulid model
model = Sequential()
model.add(LSTM(15, input_shape=(x_train.shape[1:]), return_sequences=True, activation="tanh", unroll=True))
model.add(LSTM(15, dropout=0.2, activation="tanh", unroll=True))
#model.add(LSTM(1, activation='tanh'))
#model.add(LSTM(2, activation='tanh'))
model.add(Dense(5, activation='tanh' ))
model.add(Dense(10, activation='sigmoid'))
model.summary()
opt = tf.keras.optimizers.Adam(lr=1e-3, decay=1e-5)
model.compile(loss='sparse_categorical_crossentropy', optimizer=opt,
             metrics=['accuracy'])
model.fit(x_train, y_train, epochs=2, validation_data=(x_test, y_test))


y_pred = model.predict_classes(x_test)
print(y_pred)

CodePudding user response：

I think what you are looking for is a confusion matrix. This code can generate for you a confusion matrix and plot it with seaboarn.

from sklearn.metrics import confusion_matrix

#Get the confusion matrix
cf_matrix = confusion_matrix(y_test, y_pred)
print(cf_matrix)

# plot heat map of confusion matrix
import seaborn as sns
sns.heatmap(cf_matrix, annot=True)

CodePudding user response：

Instead of using model.predict_classes(), you can use model.predict() (https://www.tensorflow.org/api_docs/python/tf/keras/Model#predict).

This returns an array with the probability for all of the possible classes.