[英]Tf.keras model.predict() returns class probabilities that are higher than 1?
我試圖在 CNN 的 tf.keras 中調用 model.predict() 來預測單個圖像的 class。 出於某種原因,class 的概率返回高於 1,這是荒謬的。 我不確定為什么會發生這種情況。 以下是我訓練 CNN 的方法:
class_names = ['Angry','Disgust','Fear','Happy','Sad','Surprise','Neutral']
model = models.Sequential()
model.add(layers.Conv2D(64, (3, 3), activation='relu', input_shape=(48, 48, 1), kernel_regularizer=tf.keras.regularizers.l1(0.01)))
model.add(layers.Conv2D(128, (3, 3), padding='same', activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(tf.keras.layers.Dropout(0.5))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(tf.keras.layers.Dropout(0.5))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.summary()
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(7))
#model.summary()
model.compile(optimizer='adam',loss=tf.keras.losses.CategoricalCrossentropy(from_logits=True),metrics=['accuracy'])
lr_reducer = tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.9, patience=3) #monitors the validation loss for signs of a plateau and then alter the learning rate by the specified factor if a plateau is detected
early_stopper = tf.keras.callbacks.EarlyStopping(monitor='val_accuracy', min_delta=0, patience=6, mode='auto') #This will monitor and stop the model training if it is not further converging
checkpointer = tf.keras.callbacks.ModelCheckpoint('C:\\Users\\rtlum\\Documents\\DataSci_Projects\\PythonTensorFlowProjects\\Datasets\\FER2013_Model_Weights\\Model\\weights.hd5', monitor='val_loss', verbose=1, save_best_only=True) #This allows checkpoints to be saved each epoch just in case the model stops training
epochs = 100
batch_size = 64
learning_rate = 0.001
model.fit(
train_data,
train_labels,
epochs = epochs,
batch_size = batch_size,
validation_split = 0.2,
shuffle = True,
callbacks=[lr_reducer, checkpointer, early_stopper]
)
下面是我如何調用 model.predict() 並傳入單個圖像進行預測:
model = tf.keras.models.load_model('Model\\weights.hd5')
img = Image.open(test_image).convert('L')
img = img.resize([48, 48])
image_data = np.asarray(img, dtype=np.uint8)
#image_data = np.resize(img,3072)
image_data = image_data / 255
image_data_test = image_data.reshape((1, 48, 48, 1))
class_names = ['Angry','Disgust','Fear','Happy','Sad','Surprise','Neutral']
x = model.predict(image_data_test)
app.logger.info(x)
image_pred = np.argmax(x)
y = round(x[0][np.argmax(x)], 2)
confidence = y * 100
print(class_names[image_pred], confidence)
最后,下面是我從 model.predict() 收到的 class 概率:
>>> x = model.predict(image_data_test)
>>> x
array([[ 1.0593076 , -3.5140653 , 0.7505076 , 2.1341033 , 0.02394461,
-0.08749148, 0.6640976 ]], dtype=float32)
您的最后一層model.add(layers.Dense(7))
正在使用線性激活 function。 要獲得 7 個類別的概率,您應該使用softmax
激活。
將最后一層更改為
model.add(layers.Dense(7 , activation='softmax'))
添加激活層以將您的 output 值轉換為 [0,1] 的值
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.