ValueError: No gradients provided for any variable: ['embedding_2/embeddings:0', 'bidirectional_4/forward_lstm_4/lstm_cell_13/kernel:0', 'bidirectional_4/forward_lstm_4/lstm_cell_13/recurrent_kernel:0', 'bidirectional_4/forward_lstm_4/lstm_cell_13/bias:0', 'bidirectional_4/backward_lstm_4/lstm_cell_14/kernel:0', 'bidirectional_4/backward_lstm_4/lstm_cell_14/recurrent_kernel:0', 'bidirectional_4/backward_lstm_4/lstm_cell_14/bias:0', 'bidirectional_5/forward_lstm_5/lstm_cell_16/kernel:0', 'bidirectional_5/forward_lstm_5/lstm_cell_16/recurrent_kernel:0', 'bidirectional_5/forward_lstm_5/lstm_cell_16/bias:0', 'bidirectional_5/backward_lstm_5/lstm_cell_17/kernel:0', 'bidirectional_5/backward_lstm_5/lstm_cell_17/recurrent_kernel:0', 'bidirectional_5/backward_lstm_5/lstm_cell_17/bias:0', 'dense_2/kernel:0', 'dense_2/bias:0']. #43258
Labels
comp:keras
Keras related issues
type:others
issues not falling in bug, perfromance, support, build and install or feature
I am training model in colab. The model I'm trying to build is siamese network for text similarity.
the loss function which I used finds internally the negative sample.
Explaination of loss function::
kindly, watch this two small videos where the lecturer explains about the loss function I used::
https://www.coursera.org/lecture/sequence-models-in-nlp/computing-the-cost-i-T4Ylj
https://www.coursera.org/lecture/sequence-models-in-nlp/computing-the-cost-ii-qXOjN
the dataset can be found here::
https://www.kaggle.com/c/quora-question-pairs/data
my colab notebook::
https://colab.research.google.com/drive/1NCUxSS9fiuLpPd2hOSxKv5QKH2IUuhX2?usp=sharing
the loss function used is
and the training loop is
the error is ::
The text was updated successfully, but these errors were encountered: