reslove : InvalidArgumentError: Graph execution error 怎么辦？

Question

大家好，我是計算機視覺和分類方面的專家，我正在嘗試使用帶有 tensorflow 和 keras 的 cnn 方法訓練模型，但我不斷收到此代碼下方的錯誤，任何人都可以幫助我或至少給我一個平靜的建議?

model = keras.models.Sequential([
    keras.layers.Conv2D(filters=16, kernel_size=(3,3), activation='relu',input_shape=(IMG_HEIGHT,IMG_WIDTH,channels)),
    keras.layers.Conv2D(filters=32, kernel_size=(3,3), activation='relu'),
    keras.layers.MaxPool2D(pool_size=(2,2)),
    keras.layers.BatchNormalization(axis=-1),

    keras.layers.Conv2D(filters=64, kernel_size=(3,3), activation='relu'),
    keras.layers.Conv2D(filters=128, kernel_size=(3,3), activation='relu'),
    keras.layers.MaxPool2D(pool_size=(2,2)),
    keras.layers.BatchNormalization(axis=-1),

    keras.layers.Flatten(),
    keras.layers.Dense(512,activation='relu'),
    keras.layers.BatchNormalization() ,
    keras.layers.Dropout(rate=0.5),

    keras.layers.Dense(3,activation='softmax')

])

learning_rate = 0.001
    epochs=30
    opt= Adam(learning_rate=learning_rate , decay=learning_rate/(epochs*0.5))
    model.compile(loss='sparse_categorical_crossentropy',optimizer=opt,metrics=['accuracy'])


aug = ImageDataGenerator(
          rotation_range=10,
          zoom_range=0.15,
          width_shift_range=0.1,
          height_shift_range=0.1,
          shear_range=0.15,
          horizontal_flip= False,
          vertical_flip= False,
          fill_mode="nearest"
          )
          
    
    history = model.fit(aug.flow(X_train, y_train,batch_size=32), epochs=epochs,validation_data=(X_val,y_val) )

InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-15-15df12cd6846> in <module>()
     11 
     12 
---> 13 history = model.fit(aug.flow(X_train, y_train,batch_size=32), epochs=epochs,validation_data=(X_val,y_val) )

1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     53     ctx.ensure_initialized()
     54     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 55                                         inputs, attrs, num_outputs)
     56   except core._NotOkStatusException as e:
     57     if name is not None:

InvalidArgumentError: Graph execution error:

Detected at node 'sparse_categorical_crossentropy/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits' defined at (most recent call last):
    File "/usr/lib/python3.7/runpy.py", line 193, in _run_module_as_main
      "__main__", mod_spec)

Answer 1

您只需確保您的標簽從 0 到 2 從零開始，因為您的輸出層有 3 個節點和一個softmax激活函數，並且您使用的是sparse_categorical_crossentropy 。 這是一個工作示例：

import tensorflow as tf

model = tf.keras.Sequential([
    tf.keras.layers.Conv2D(filters=16, kernel_size=(3,3), activation='relu',input_shape=(256, 256, 3)),
    tf.keras.layers.Conv2D(filters=32, kernel_size=(3,3), activation='relu'),
    tf.keras.layers.MaxPool2D(pool_size=(2,2)),
    tf.keras.layers.BatchNormalization(axis=-1),

    tf.keras.layers.Conv2D(filters=64, kernel_size=(3,3), activation='relu'),
    tf.keras.layers.Conv2D(filters=128, kernel_size=(3,3), activation='relu'),
    tf.keras.layers.MaxPool2D(pool_size=(2,2)),
    tf.keras.layers.BatchNormalization(axis=-1),

    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(512,activation='relu'),
    tf.keras.layers.BatchNormalization() ,
    tf.keras.layers.Dropout(rate=0.5),

    tf.keras.layers.Dense(3,activation='softmax')

])

learning_rate = 0.001
epochs=2
opt= tf.keras.optimizers.Adam(learning_rate=learning_rate , decay=learning_rate/(epochs*0.5))
model.compile(loss='sparse_categorical_crossentropy',optimizer=opt,metrics=['accuracy'])


aug = tf.keras.preprocessing.image.ImageDataGenerator(
          rotation_range=10,
          zoom_range=0.15,
          width_shift_range=0.1,
          height_shift_range=0.1,
          shear_range=0.15,
          horizontal_flip= False,
          vertical_flip= False,
          fill_mode="nearest"
          )
          

X_train = tf.random.normal((50, 256, 256, 3))
y_train = tf.random.uniform((50, ), maxval=3, dtype=tf.int32)
history = model.fit(aug.flow(X_train, y_train, batch_size=2), epochs=epochs)

使用虛擬數據作為真實數據的方向。

Answer 2

否則，如果您使用 Colab。 請通過選擇 Runtime -> Change run time type -> GPU 更改運行時間類型

Answer 3

同樣的問題發生在我身上，所以你需要確保它們都是相同的圖像縱橫比（例如：1:1、4:3、16:9 等）。