There is a bug in the memory allocation algorithm under multi branch PAD operation #109
Description
When there is a branch structure in the model as shown in the following figure, the input tensor of branch B should only be read before it is used by branch B.
As shown in the following figure, the tensor address of this branch is 49152. Branch A can use it correctly.
As shown in the figure below, the input tensor address of branch B is 0, which should be 49152. On the right side of the graph, it can be seen that the tensor at 49152 has been modified, which should not appear before branch B. In addition, the input tensor shape of branch B is also incorrect.
Here is my tflite file.
model.zip