MobilenetV2 tflite model trained on cifar10 dataset is expecting input image of shape 1x32x32x3(Because during training their was batch flag used) but in order to dump model into Mobile I get 32x32x3 shape images from camera so now not able to feed data into tflite.interpreter.......any Suggestion
Asked
Active
Viewed 231 times
1 Answers
0
A 1x32x32x3 matrix has the same number of elements as a 32x32x3 matrix, so you can feed the data from the image to the input tensor of the tflite interpreter without causing any error.

daverim
- 101
- 3
-
Tq... the problem was with the dimensions of byte buffers created – Akash Bhogar Dec 10 '19 at 13:05