Tensorflow tf.data.Dataset的Efficientnet inputshape错误
将tf.data.Dataset馈送到train EfficientnetB0模型时,我得到以下错误:Tensorflow tf.data.Dataset的Efficientnet inputshape错误,tensorflow,keras,efficientnet,Tensorflow,Keras,Efficientnet,将tf.data.Dataset馈送到train EfficientnetB0模型时,我得到以下错误: ValueError: in converted code: C:\Users\fconrad\AppData\Local\Continuum\anaconda3\envs\venv_spielereien\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py:677 map_fn b
ValueError: in converted code:
C:\Users\fconrad\AppData\Local\Continuum\anaconda3\envs\venv_spielereien\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py:677 map_fn
batch_size=None)
C:\Users\fconrad\AppData\Local\Continuum\anaconda3\envs\venv_spielereien\lib\site-packages\tensorflow_core\python\keras\engine\training.py:2410 _standardize_tensors
exception_prefix='input')
C:\Users\fconrad\AppData\Local\Continuum\anaconda3\envs\venv_spielereien\lib\site-packages\tensorflow_core\python\keras\engine\training_utils.py:573 standardize_input_data
'with shape ' + str(data_shape))
ValueError: Error when checking input: expected efficientnet-b0_input to have 4 dimensions, but got array with shape (224, 224, 3)
我真想知道为什么会发生这种情况,因为当我从数据集创建批时:
train_generator = (tf.data.Dataset
.from_tensor_slices((train_imgs, train_labels))
.map(read_img)
.map(flip_img)
.map(brightness)
.map(blur)
.map(noise)
.map(rotate_90)
.repeat()
.shuffle(512)
.batch(BATCH_SIZE)
.prefetch(True))
validation_generator = (tf.data.Dataset
.from_tensor_slices((validation_imgs, validation_labels))
.map(read_img)
)
print(train_generator.__iter__().__next__()[0].shape)
我得到了预期的结果(642242243)
但在创建模型后,当我开始培训时,上面的错误会出现:
effn = tfkeras.EfficientNetB0(include_top=False, input_shape=img_shape, classes=4)
effn_model = tf.keras.Sequential()
effn_model.add(effn)
effn_model.add(tf.keras.layers.GlobalAveragePooling2D())
effn_model.add(tf.keras.layers.Dense(4, 'softmax'))
effn_model.compile(optimizer= 'adam', loss='categorical_crossentropy', metrics= ['categorical_accuracy'])
effn_model.fit(train_generator,
epochs=20,
steps_per_epoch=train_imgs.shape[0] // BATCH_SIZE,
validation_data= validation_generator)
有人知道为什么数据集中的切片具有形状(64224,3),但模型无法识别批次维度吗?当我尝试训练keras.application模型时,一切都很好。
我使用tensorflow 2.1和efficientnet的pip安装。正如这里所解释的,谢谢
input\u shape
:可选的形状元组,仅在include\u top为False时指定它应该正好有3个输入通道。
因此,请尝试此->
from tensorflow.keras.applications.efficientnet import EfficientNetB0, EfficientNetB5
mm = EfficientNetB0(include_top=True, weights=None, input_tensor=None, input_shape=(128, 128, 3), pooling=None, classes=2, classifier_activation="sigmoid")
mm.summary()
注意输入\u shape=(128,128,3)
它有3个通道。如本文所述
input\u shape
:可选的形状元组,仅在include\u top为False时指定它应该正好有3个输入通道。
因此,请尝试此->
from tensorflow.keras.applications.efficientnet import EfficientNetB0, EfficientNetB5
mm = EfficientNetB0(include_top=True, weights=None, input_tensor=None, input_shape=(128, 128, 3), pooling=None, classes=2, classifier_activation="sigmoid")
mm.summary()
注意,input\u shape=(128,128,3)
它有3个通道