如何将几个张量传递给 tensorflow.js 中的 model.predict

Question

I'm trying to use tensorflow.js to run a model that I created in python. This model has two inputs tensor, one of [1, 60] shape and another of [1, 60, 1]. I'm doing this:

    var array1 = new Array(60).fill(0);
    var tensor1 = tf.tensor(arr1, [1, 60);
    var array2 = new Array(60).fill(1);
    var tensor2 = tf.tensor(arr2, [1, 60, 1]);

    var tensorResult = model.predict([tensor1, tensor2]);

But it's giving me this message:

Error: Error when checking model : the Array of Tensors that you are passing to your model is not the size the the model expected. Expected to see 2 Tensor(s), but instead got 1 Tensors(s).

model.summary():

__________________________________________________________________________________________________
Layer (type)                    Output shape         Param #     Receives inputs                 
==================================================================================================
l_word (InputLayer)             [null,60]            0                                           
__________________________________________________________________________________________________
l_embWord (Embedding)           [null,60,300]        164395500   l_word[0][0]                    
__________________________________________________________________________________________________
l_company (InputLayer)          [null,60,1]          0                                         
__________________________________________________________________________________________________
l_concat (Concatenate)          [null,60,301]        0           l_embWord[0][0]                 
                                                                 l_company[0][0]                 
__________________________________________________________________________________________________
l_bLstm (Bidirectional)         [null,128]           187392      l_concat[0][0]                  
__________________________________________________________________________________________________
l_dense (Dense)                 [null,16]            2064        l_bLstm[0][0]                   
__________________________________________________________________________________________________
l_dropout (Dropout)             [null,16]            0           l_dense[0][0]                   
__________________________________________________________________________________________________
l_softmax (Dense)               [null,3]             51          l_dropout[0][0]                 
==================================================================================================
Total params: 164585007
Trainable params: 189507
Non-trainable params: 164395500
__________________________________________________________________________________________________

In python, the following works perfectly for me:

    model.predict([tensor1, tensor2])

I will appreciate any contribution.

Thank you!

Answer 1

The error says it all.

the Array of Tensors that you are passing to your model is not the size the the model expected.

The shape of the tensors passed as inputs to the models is not what the model expects