Tensorflow Custom TFLite java.lang.NullPointerException: Cannot allocate memory for the interpreter

Question

I have created a custom tensorflow lite model using retrain.py from https://github.com/tensorflow/hub/blob/master/examples/image_retraining/retrain.py using the following command

python retrain.py --image_dir newImageDirectory --tfhub_module https://tfhub.dev/google/imagenet/mobilenet_v2_100_224/feature_vector/1

Then I convert using toco the output_graph.pb file to a lite file. Using the below command:

bazel run tensorflow/contrib/lite/toco:toco -- --input_file=/tmp/output_graph.pb --output_file=/tmp/optimized.lite --input_format=TENSORFLOW_GRAPHDEF --output_format=TFLITE --inpute_shape=1,224,224,3 --input_array=input --output_array=final_result --inference_type=FLOAT --input_data_type=FLOAT

Then I take the new lite file and the labels.txt file and put them in tensorflow for poets 2 https://github.com/googlecodelabs/tensorflow-for-poets-2 to see if I can have it start to classify new categories. When the application launches I receive the following error:

Caused by: java.lang.NullPointerException: Can not allocate memory for the interpreter                                                                                            at org.tensorflow.lite.NativeInterpreterWrapper.createInterpreter(Native Method)
                                                                      at org.tensorflow.lite.NativeInterpreterWrapper.<init>(NativeInterpreterWrapper.java:63)
                                                                                        at org.tensorflow.lite.NativeInterpreterWrapper.<init>(NativeInterpreterWrapper.java:51)
                                                                                        at org.tensorflow.lite.Interpreter.<init>(Interpreter.java:90)
                                                                                        at com.example.android.tflitecamerademo.ImageClassifier.<init>(ImageClassifier.java:97)

I've been running into this issue when trying to use a retrained InceptionV3 model, I thought it was caused by the model size (about 80 MB), but it must be something else when this error occurs even with these smaller MobileNet models. — Colander
– Colander, Commented Jul 11, 2018 at 15:27
This problem has been reported here github.com/tensorflow/tensorflow/issues/19982 — Mirwise Khan
– Mirwise Khan, Commented Mar 4, 2021 at 18:09

Frank · Accepted Answer · 2021-03-04 22:00:28Z

1

This is due to the computer you are using, make sure you have enough ram to allocate for the program, or try increasing your swap file size?

answered Mar 4, 2021 at 22:00

Frank

313 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Tensorflow Custom TFLite java.lang.NullPointerException: Cannot allocate memory for the interpreter

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related