IndexError: list index out of range

[christianbaun]

Hello. Thanks for this great tutorial. I was able to deploy tensorflow lite on the RasPi3+ and this here works well:

python3 TFLite_detection_webcam.py --modeldir=Sample_TFLite_model

But when I try to calculate an own model and use it the same way (with TFLite_detection_webcam.py) I get the IndexError: list index out of range error.

I created the own model in Debian Linux 9 with TF2.

$ pip3 list | grep tensorflow
tensorflow                   2.0.0     
tensorflow-estimator         2.0.1     
tensorflow-hub               0.7.0     

I created the model whis way:

$ make_image_classifier \
--image_dir ~/tensorflow/images_train/ \
--tfhub_module https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/4 \
--image_size 224 \
--saved_model_dir /tmp/mynewmodel \
--labels_output_file /tmp/mynewmodel/labelmap.txt \
--tflite_output_file /tmp/mynewmodel/detect.tflite

This is the output:

$ ls -lh /tmp/mynewmodel/
insgesamt 11M
drwxr-xr-x 2 bnc bnc 4,0K Jan 10 22:55 assets
-rw-r--r-- 1 bnc bnc 8,5M Jan 11 00:02 detect.tflite
-rw-r--r-- 1 bnc bnc   20 Jan 11 00:02 labelmap.txt
-rw-r--r-- 1 bnc bnc 2,0M Jan 11 00:02 saved_model.pb
drwxr-xr-x 2 bnc bnc 4,0K Jan 11 00:02 variables

When I try to use the self-generated tensorflow lite model on the RasPi 3+, I get this error message:

$ python3 TFLite_detection_webcam.py --modeldir=/home/pi/mynewmodel
INFO: Initialized TensorFlow Lite runtime.
Traceback (most recent call last):
  File "TFLite_detection_webcam.py", line 186, in <module>
    classes = interpreter.get_tensor(output_details[1]['index'])[0] # Class index of detected objects
IndexError: list index out of range

Every 1-2 hours, I get one of these lines as additional output:

Corrupt JPEG data: premature end of data segment

What can I do to fix this? Has anyone the same issue?

[beige]

I ran make_image_classifier on Windows 10 and got the same error when running TFLite_detection_webcam.py on an RPI 4 with the results.

My index file contains: daisy dandelion roses sunflowers tulips

This index appears to be correct if you don't add your own pictures and classes.

On Windows 10: make_image_classifier --image_dir my_image_tflt dir \ --tfhub_module https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/4 --image_size 224 --saved_model_dir my_dir_tflt\new_model_tflt --labels_output_file labelmap.txt --tflite_output_file new_mobile_model.tflite

On RPi4: (tflite1-env) pi@raspberrypi:~/tflite1 $ python3 TFLite_detection_webcam.py --modeldir=tflt_test_model1 INFO: Initialized TensorFlow Lite runtime. Traceback (most recent call last): File "TFLite_detection_webcam.py", line 186, in classes = interpreter.get_tensor(output_details[1]['index'])[0] # Class index of detected objects IndexError: list index out of range

(tflite1-env) pi@raspberrypi:~/tflite1 $ ls -l /home/pi/tflite1/tflt_test_model1 total 8696 -rw-r--r-- 1 pi pi 8900048 Feb 3 12:10 detect.tflite -rw-r--r-- 1 pi pi 40 Feb 3 12:10 labelmap.txt

Any help would be appreciated.

[lery600]

i get "list index is out of range" after running "python3 TFLite_detection_webcam.py --modeldir=TFLite_model". it works only about a few seconds or if it's dark. as soon as it starts seeing any picture it freezes. i followed this guide and i trained my own model with only one label. File "TFLite_detection_webcam.py", line 204, in object_name = labels[int(classes[i])] IndexError: list index out of range

[piyushy6]

classes = interpreter.get_tensor(output_details[1]['index'])[0] # Class index of detected objects IndexError: list index out of range

I am also trying to run my own model in Rpi. But the same issue is occurring. Any solution to this issue?

[hushki610]

i have the same problem.. did anyone came across a solution?

[EdjeElectronics]

Hi all, the "list index out of range" error is occurring because you are using an "image classification" model rather than an "object detection" model. Image classification models apply a single label to an image, while object detection models locate and label multiple objects in an image. This code is written for object detection models.

If you'd like to see how to use an image classification model on the Raspberry Pi, please see this example: https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/raspberry_pi

[sharmila-polamuri]

Hi @EdjeElectronics I built an object detection model and converted it to tflite model format. But I got IndexError: list index out of range error when I try to predict images/video using tflite formated model. Can you please help me to resolve this problem?

[seung-gu]

It's because there are missing classes in "labelmap.txt" file. Class number is up to 89, which was supposed to be 90 classes for total, but if you count it, it's actually 80 classes (10 classes are removed). Therefore, "object_name = labels[int(classes[i])]" this line doesn't work. What you need to do is to fill in the missing numbers with just garbage class names such as "??", and it will work if you just make the number of column of labelmap.txt file with 90 lines.

[PiotrG1996]

This should solve the problem. https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi/blob/master/Raspberry_Pi_Guide.md#5-indexerror-list-index-out-of-range

1. Download correct detect.tflite file for object detection.
2. Create file labelmap.txt and paste all objects in this way:

??? person bicycle car motorcycle airplane bus train truck boat traffic light fire hydrant ??? stop sign parking meter bench bird cat dog horse sheep cow elephant bear zebra giraffe ??? backpack umbrella ??? ??? handbag tie suitcase frisbee skis snowboard sports ball kite baseball bat baseball glove skateboard surfboard tennis racket bottle ??? wine glass cup fork knife spoon bowl banana apple sandwich orange broccoli carrot hot dog pizza donut cake chair couch potted plant bed ??? dining table ??? ??? toilet ??? tv laptop mouse remote keyboard cell phone microwave oven toaster sink refrigerator ??? book clock vase scissors teddy bear hair drier toothbrush

[AlexM1989]

Still no solution? I still have the same issue

File "TFLite_detection_webcam.py", line 186, in classes = interpreter.get_tensor(output_details[1]['index'])[0] # Class index of detected objects IndexError: list index out of range

[markfilan]

The way Python indexing works is that it starts at 0, so the first number of your list would be [0]. Index Error: List index out of range means you are trying to get an item in a list that doesn't exist. It means that you are referring to n-th element of the python list, while the length of the list is smaller than n. whenever you get this type of error please cross check with items that comes between/middle in range, and insure that their index is not last if you get output then you have made perfect error that mentioned.

An index in Python refers to a position within an ordered list . To retrieve an element of the list, you use the index operator ([]) . Using indexing you can easily get any element by its position.