损失为 NaN，使用激活 softmax 和损失 function categorical_crossentropy

Question

I'm trying to make this model work. Initially x.shape is (6703, 56) and y.shape is a binary column having shape (6703, ). Then I run

y = y.to_numpy()
y = y.astype("float32")
y = tf.keras.utils.to_categorical(y, 2)

and now y.shape is (6703, 2). I run

X_train, X_test, Y_train, Y_test = train_test_split(x, y, test_size=0.2, random_state=42)

and now

• X_train shape is (5362, 56)
• Y_train shape is (5362, 2)
• X_test shape is (1341, 56)
• Y_test shape is (1341, 2)

Then I build the model:

model = tf.keras.models.Sequential(name="3layers")

model.add(keras.layers.Dense(N_HIDDEN,
                             input_shape=(len(X_train[0]),),
                             name="dense1",
                             activation="relu"))

model.add(keras.layers.Dropout(DROPOUT))
    
model.add(keras.layers.Dense(N_HIDDEN,
                             name="dense2",
                             activation="relu"))

model.add(keras.layers.Dropout(DROPOUT))

model.add(keras.layers.Dense(NB_CLASSES,
                             name="dense3",
                             activation="softmax"))
    
model.summary()

model.compile(optimizer="SGD",  #SGD  adam
              loss="categorical_crossentropy",
              metrics=["accuracy"])
    
model.fit(X_train, Y_train,
          batch_size=BATCH_SIZE,
          epochs=EPOCHS,
          verbose=VERBOSE,
          validation_split=VALIDATION_SPLIT)
    
test_loss, test_acc = model.evaluate(X_test, Y_test)

The summary is what I expect:

dense1 (Dense)              (None, 64)                3648      
dropout_18 (Dropout)        (None, 64)                0         
dense2 (Dense)              (None, 64)                4160      
dropout_19 (Dropout)        (None, 64)                0         
dense3 (Dense)              (None, 2)                 130    

but the output is

Epoch 1/5
 > 429/429 [==============================] - 1s 1ms/step - loss: nan - accuracy: 0.5141 - val_loss: nan - val_accuracy: 0.4884
Epoch 2/5
 > 429/429 [==============================] - 0s 1ms/step - loss: nan - accuracy: 0.5143 - val_loss: nan - val_accuracy: 0.4884
Epoch 3/5
 > 429/429 [==============================] - 0s 987us/step - loss: nan - accuracy: 0.5143 - val_loss: nan - val_accuracy: 0.4884

I've tried changing many parameters, I'm stuck.

Answer 1

I found what it was. There were some "None" values in the x matrix that caused the problem. Removing them it started evaluating a numeric loss. Very poor accuracy, but this will be another problem to solve.