[lite] Add check for bias_size is zero to avoid division by zero. This shouldn't happen for properly converted models. Just safety check

karimnosseir · tensorflower-gardener · commit 8c6f391a2282 · 2021-12-14T13:45:48.000-08:00
PiperOrigin-RevId: 416383645
Change-Id: If8e508bf696ae8ecfb927e69c139a8ccf7fe60cb
diff --git a/tensorflow/lite/kernels/internal/common.h b/tensorflow/lite/kernels/internal/common.h
@@ -75,6 +75,7 @@ float ActivationFunction(float x) {
 inline void BiasAndClamp(float clamp_min, float clamp_max, int bias_size,
                          const float* bias_data, int array_size,
                          float* array_data) {
+  if (bias_size == 0) return;
   // Note: see b/132215220: in May 2019 we thought it would be OK to replace
   // this with the Eigen one-liner:
   //   return (array.colwise() + bias).cwiseMin(clamp_max).cwiseMin(clamp_max).
