Hi, I am hoping to run an object detection model on the OpenMV Cam H7 Plus. I am trying to use SSD mobilenet v2 fpnlite 320. After training this model, it is 11.5 MB as .tflite but by quantizing it I can reduce the size to 3.7 MB. This is smaller than the 4.2 MB available on the heap for the H7 Plu…

Load your model here: Netron And then cross check the ops used and make sure they are in: openmv/src/lib/tflm/tflm_backend.cc at master · openmv/openmv

All of the ops are supported except for the output layer which uses TFLite_Detection_PostProcess. It looks like this function is commented out in tlfm_backend.cc. Do you know of any workarounds for this? [image]

Hi, since you are compiling the firmware just enable it: openmv/src/lib/tflm/tflm_backend.cc at master · openmv/openmv Otherwise you to want to shave that operator off the network and do it in Python code like this: openmv/scripts/libraries/ml/ml/postprocessing.py at master · openmv/openmv

Thanks. By recompiling the firmware, and using load_to_fb=True I was able to successfully load the model. However, I have one more question for you. When I try to feed an image into the network I get ValueEror: unexpected tensor shape. I am unsure what the issue is, because when I print the input te…

Can you just print() the model itself and post that info here. This will list the tensors. Note that we support up to 4D tensors. Preprocessing for the image input is here: openmv/scripts/libraries/ml/ml/preprocessing.py at master · openmv/openmv We handle the RGB565 to RGB888 conversion. That er…

Here is the model printed from the H7 Plus: { model_size: 3741072, model_addr: 0xc1c6ea6c, ram_size: 3566032, ram_addr: 0xc0017780, input_shape: ((1, 320, 320, 3),), input_scale: (0.00392157,), input_zero_point: (0,), input_dtype: ('B',), output_shape: ((), (), (), ()), output_scale: (1.0, 1.0, 1.0…

Hmmm, our library isn’t able to handle that output at all. However, it may be something I can easily parse. It appears to be a 4 tensor output. The library should have handled that though, so, there’s something we can improve in our code. Okay, I need this from you: An input image to test with. B…

Here are the output tensors: output_tensor_1 = [[0.99609375 0.0078125 0.00390625 0.00390625 0.00390625 0.00390625 0.00390625 0.00390625 0.00390625 0.00390625]] output_tensor_2 = [[[ 0.23265359 0.41437462 0.83452284 0.58187926] [ 0.3753295 0.26537663 0.5947138 0.64145315] [-0.0136128…

Hi, I’ve made an issue tracker to work on this: Update tensorflow to handle post-processed model · Issue #2543 · openmv/openmv However, I will not be able to get to it for a while. If you want to try to make the changes to the firmware yourself to make it work this would be appreciated and then I c…

Quantized model on OpenMV Cam H7 Plus

OpenMV Boards

Joe100A December 5, 2024, 11:41am 9

Did you check this? Heads up custom Tflite models with Latest versions of Tensorflow

Topic		Replies	Views
Loading a tflite model into SDRAM instead of SRAM - H7 Plus OpenMV Boards	31	1628	June 15, 2023
Can't use Tensorflow-Lite for OpenMV OpenMV Boards	50	11042	June 9, 2020
Process for building custom a model, training it, and deploying it to the OpenMV Cam H7 OpenMV Boards	22	13015	November 23, 2019
OpenMV Firmware v4.5.6 and up TensorFlow Porting Guide OpenMV Boards tensorflow , tf , ml	32	2340	July 25, 2025
OpenMV Cam H7 Plus running Unoptimized (float32) model OpenMV Boards ml	3	73	July 15, 2025

Quantized model on OpenMV Cam H7 Plus

Related topics