我最近已经更新到Tensorflow 2.3.1
的最新版本,并且在更新后我的模型不再起作用:
model = tf.keras.Sequential([
layers.Input(shape= input_shape), # input_shape: (1623, 105, 105, 3)
layers.experimental.preprocessing.Rescaling(1./255),
layers.Conv2D(32, 3, activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(32, 3, activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(32, 3, activation='relu'),
layers.MaxPooling2D(),
layers.Flatten(),
layers.Dense(128, activation='relu'),
layers.Dense(ds_info.features['label'].num_classes)
])
问题在于Input图层添加了一个新的batch_size
维度,这又导致了以下错误:
Input 0 of layer max_pooling2d_22 is incompatible with the layer: expected ndim=4, found ndim=5. Full shape received: [None, 1623, 103, 103, 32]
如何防止生成该错误或解决此问题。
答案 0 :(得分:1)
指定输入形状时,需要省略样本数。那是因为Keras可以接受任何数字。所以试试这个:
layers.Input(shape = input_shape[1:]),
这将指定输入形状为(rows, columns, channels)
,省略了样本数量。