# voxl-tflite-server: "FATAL: Unsupported model provided!!"

Source: https://forum.modalai.com/topic/452/voxl-tflite-server-fatal-unsupported-model-provided
Category: General Questions (https://forum.modalai.com/category/2/general-questions)
Posted: 2021-09-20 22:09:17 UTC by colerose
Replies: 8 · Views: 1715

## colerose · 2021-09-20 22:09:17 UTC

I am trying to create a custom version of the voxl-tflite-server using a tflite file of the literature version of the yolo-v4-tiny model. However, when I change the code as well as the the voxl-tflite-server.conf file to include my new model I get the error "FATAL: Unsupported model provided!!" when trying to run the server. I can't find where this message is printed in the code. How can I turn this error off?

## Reply by Guest · 2021-09-20 23:00:57 UTC

This error is printed at line 78 of [threads.cpp](https://gitlab.com/voxl-public/modal-pipe-architecture/voxl-tflite-server/-/blob/master/server/threads.cpp#L78). If you would like to run your own model, it is much simpler to just change the 
```
tflite_settings->model_name
```
 and 
```
tflite_settings->labels_file_name 
```
parameters in [models.cpp](https://gitlab.com/voxl-public/modal-pipe-architecture/voxl-tflite-server/-/blob/master/server/models.cpp#L227) to match the absolute paths on voxl where these files are located (typically /usr/bin/dnn/ or in the /data/ partition if the file is larger).

## Reply by colerose · 2021-09-22 17:44:42 UTC

@Matt-Turi thanks Matt. I ended up getting a segfault with it. I believe it was too memory intensive because it wasn't supported by the GPU. Is there a chance that tiny-yolo could be supported by ModalAI anytime soon?

## Reply by Guest · 2021-09-22 20:24:23 UTC

We've done some testing with darknet and a few tflite converted yolo models, but saw extremely poor inference times and performance from both. Is there any reason you are looking to use the yolo architecture specifically over mobilenet or some other native tensorflow model?

## Reply by colerose · 2021-09-23 21:19:33 UTC

I have some yolo weights on some custom data that I collected for yolo that I wanted to test with voxl-tflite-server. Additionally, I noticed that in there are some classes missing in the coco_labels.txt file included with the code for voxl-tflite-server in master. Some classes such as 'desk' are replaced with question marks:

```
0  person
1  bicycle
2  car
3  motorcycle
4  airplane
5  bus
6  train
7  truck
8  boat
9  traffic light
10  fire hydrant
11  ???-11
12  stop sign
13  parking meter
14  bench
15  bird
16  cat
17  dog
18  horse
19  sheep
20  cow
21  elephant
22  bear
23  zebra
24  giraffe
25  ???
26  backpack
27  umbrella
28  ???-28
29  ???-29
30  handbag
31  tie
32  suitcase
33  frisbee
34  skis
35  snowboard
36  sports ball
37  kite
38  baseball bat
39  baseball glove
40  skateboard
41  surfboard
42  tennis racket
43  bottle
44  ???-44
45  wine glass
46  cup
47  fork
48  knife
49  spoon
50  bowl
51  banana
52  apple
53  sandwich
54  orange
55  broccoli
56  carrot
57  hot dog
58  pizza
59  donut
60  cake
61  chair
62  couch
63  potted plant
64  bed
65  ???-65
66  dining table
67  ???-67
68  ???-68
69  toilet
70  ???-70
71  tv
72  laptop
73  mouse
74  remote
75  keyboard
76  cell phone
77  microwave
78  oven
79  toaster
80  sink
81  refrigerator
82  ???-82
83  book
84  clock
85  vase
86  scissors
87  teddy bear
88  hair drier
89  toothbrush
```

## Reply by colerose · 2021-09-23 21:24:27 UTC

@Matt-Turi did you try the full fledged version of yolo or was it tiny-yolo?

## Reply by Guest · 2021-09-23 22:26:49 UTC

@colerose Looks like that labels file is a bit outdated - I will see to updating it. 

For your other question - in the past, I tried with regular and tiny yolo implementations. With a modified darknet framework (opencl backend instead of cuda), the inference times for tiny-yolo were around 30 seconds per image, and full yolo was upwards of a minute per image. I also tested with the tflite-converted models, but saw similar performance results as well as various inconsistencies / unsupported ops due to the conversion (likely why you are getting segfaults with your model). 

For reference, any of the object detection models from the [tf1 zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf1_detection_zoo.md) as well as a few from the [tf2 zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md) will integrate seamlessly and can support our gpu acceleration as seen with the mobilenetv2 model that is default.

## Reply by colerose · 2021-09-27 18:43:53 UTC

@Matt-Turi this is great to know, thanks Matt! :slightly_smiling_face:  Just curious, any reason why mobilenetv2 was chosen from the tf1/tf2 zoo when it seems that there are faster and more accurate models available?

## Reply by Guest · 2021-09-27 19:45:03 UTC

@colerose we selected mobilenetv2 because of its exceptional performance on embedded devices - currently, inference time in the voxl-tflite-server is  ~22ms per frame with very high precision. Also, the mobilenet family is fairly easy to retrain with a custom dataset!