Question

我正在尝试使用Mobilenet进行转学这是我的代码

from keras.applications.mobilenet import preprocess_input
from keras.applications.mobilenet import MobileNet
import keras.backend as K

x_train_final=preprocess_input(x_train)
x_test_final=preprocess_input(x_test)
pretrained_weights='imagenet'

#2
mobile=MobileNet(weights=pretrained_weights,include_top=False,input_shape=(416,416,3))
x=mobile.output
x=keras.layers.Flatten()(x)
x=keras.layers.Dense(512)(x)
x=keras.layers.Activation("relu")(x)
x=keras.layers.Dense(256)(x)
x=keras.layers.Activation("sigmoid")(x)
x=keras.layers.Dense(8)(x)
output=x
model=keras.models.Model(inputs=mobile.input,outputs=output)

def custom_loss(y_true, y_pred):

    loss = K.square(y_pred - y_true)  # (batch_size, 8)
    # summing both loss values along batch dimension
    loss = K.sum(loss, axis=0)        # (batch_size,)

    return loss

model.compile(optimizer = keras.optimizers.Adam(learning_rate=0.002), 
          loss = custom_loss,
          metrics = ['accuracy', 'mse'])

model.fit(x_train_final, y_train, epochs = 100)

但是我遇到一个错误。

Epoch 1/100
---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-37-55c4376c8a25> in <module>()
----> 1 model.fit(x_train_final, y_train, epochs = 100)

7 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     58     ctx.ensure_initialized()
     59     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60                                         inputs, attrs, num_outputs)
     61   except core._NotOkStatusException as e:
     62     if name is not None:

InvalidArgumentError:  Incompatible shapes: [32] vs. [8]
     [[node gradients_4/loss_4/dense_18_loss/custom_loss/weighted_loss/mul_grad/Mul_1 (defined at /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3009) ]] [Op:__inference_keras_scratch_graph_111168]

Function call stack:
keras_scratch_graph

“我的火车”数据集形状为（3066、416、416、3）

测试数据集的形状为（100，416，416，3）

我无法弄清错误。

Answer 1

我也面临同样的问题，发现我的池层存在问题。它给出了错误的输出。将maxpool2d更改为globalaevaragepool可解决此问题。如果要坚持使用maxpool，请更改其输出形状。

InvalidArgumentError：不兼容的形状：[32]与[8]-Keras转移学习

1 个答案: