TFDeep' object has no attribute 'between_tensors

Question

I'm trying to run shap on my tensorflow (time series model) and getting error.

I built a simple example which I got the same error:

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Masking, LSTM, Dense

model = Sequential()
model.add(Masking(mask_value=0.0, input_shape=(90, 8)))
model.add(LSTM(100, return_sequences=True))
model.add(LSTM(70, return_sequences=True))
model.add(LSTM(70, return_sequences=False))  # Output shape (None, 70)
model.add(Dense(50, activation='relu'))
model.add(Dense(52, activation='relu'))

model.summary()



Model: "sequential_1"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 masking_1 (Masking)         (None, 90, 8)             0         
                                                                 
 lstm_3 (LSTM)               (None, 90, 100)           43600     
                                                                 
 lstm_4 (LSTM)               (None, 90, 70)            47880     
                                                                 
 lstm_5 (LSTM)               (None, 70)                39480     
                                                                 
 dense_2 (Dense)             (None, 50)                3550      
                                                                 
 dense_3 (Dense)             (None, 52)                2652      
                                                                 
=================================================================
Total params: 137,162
Trainable params: 137,162
Non-trainable params: 0

train the model:

import numpy as np
# Generate synthetic data
num_samples = 5000
input_shape = (num_samples, 90, 8)
output_shape = (num_samples, 52)

# Example input data (random values)
X_train = np.random.rand(*input_shape)

# Example target data (random values)
y_train = np.random.rand(*output_shape)



model.compile(optimizer='adam', loss='mean_squared_error', metrics=['accuracy'])
batch_size = 256
epochs = 10
model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.2)

run shap:

import shap
de = shap.DeepExplainer(model, data=X_train[:100])
shap_values = de.shap_values(X_train[101:102])

I'm getting error:

AttributeError: Exception encountered when calling layer "lstm_3" "                 f"(type LSTM).

'TFDeep' object has no attribute 'between_tensors'

Call arguments received by layer "lstm_3" "                 f"(type LSTM):
  • inputs=tf.Tensor(shape=(200, 90, 8), dtype=float32)
  • mask=tf.Tensor(shape=(200, 90), dtype=bool)
  • training=False
  • initial_state=None

versions:

shap.__version__ == 0.44.1
tf.__version__   == 2.10.0

1. What is wrong ?
2. how can I fix and run shap on my example ?