I want to train a model for which the loss function can only be computed externally. So, I take the output of my last layer, compute some value externally and want to use this to update my network. Can I implement such a setup in tensorflow?
相关问题
- batch_dot with variable batch size in Keras
- How to use Reshape keras layer with two None dimen
- How to use Reshape keras layer with two None dimen
- CV2 Image Error: error: (-215:Assertion failed) !s
- Why keras use “call” instead of __call__?
相关文章
- tensorflow 神经网络 训练集准确度远高于验证集和测试集准确度?
- Tensorflow: device CUDA:0 not supported by XLA ser
- Numpy array to TFrecord
- conditional graph in tensorflow and for loop that
- How to downgrade to cuda 10.0 in arch linux?
- Apply TensorFlow Transform to transform/scale feat
- How to force tensorflow tensors to be symmetric?
- How to measure overfitting when train and validati
Yes you can, you have to define your minimised loss out of the graph, for example:
And then you just have to specify :
It should work