if i try to convert T2 model to TFLITE
it throws error.
I tried also tried TFlite converter with SELECT_TF_OPS but it failed saying inputs are Dynamic
( as both inputs and input_lengths have None as dim).
any work done on this ?
Some of the operators in the model are not supported by the standard TensorFlow Lite runtime. If those are native TensorFlow operators, you might be able to use the extended runtime by passing --enable_select_tf_ops, or by setting target_ops=TFLITE_BUILTINS,SELECT_TF_OPS when calling tf.lite.TFLiteConverter(). Otherwise, if you have a custom implementation for them you can disable this error with --allow_custom_ops, or by setting allow_custom_ops=True when calling tf.lite.TFLiteConverter(). Here is a list of builtin operators you are using: ADD, CAST, CONCATENATION, CONV_2D, DIV, EXPAND_DIMS, FILL, FLOOR, FULLY_CONNECTED, GATHER, GREATER_EQUAL, LESS, LOGICAL_AND, LOGICAL_NOT, LOGICAL_OR, LOGISTIC, MAXIMUM, MINIMUM, MUL, PACK, RANGE, REDUCE_ANY, REDUCE_MAX, RESHAPE, SELECT, SHAPE, SOFTMAX, SPLIT, SQUEEZE, STRIDED_SLICE, SUM, TANH, TILE, TRANSPOSE. Here is a list of operators for which you will need custom implementations: All, BatchMatMul, Enter, Exit, LoopCond, Merge, RandomUniform, ReverseSequence, Round, Switch, TensorArrayGatherV3, TensorArrayReadV3, TensorArrayScatterV3, TensorArraySizeV3, TensorArrayV3, TensorArrayWriteV3.
if i try to convert T2 model to TFLITE it throws error. I tried also tried TFlite converter with SELECT_TF_OPS but it failed saying inputs are Dynamic ( as both inputs and input_lengths have None as dim). any work done on this ?