# Memory Error, out of fast Frame Buffer Stack - H7 **URL:** \ **Category:** OpenMV Boards\ **Created:** [March 16, 2020, 9:39pm UTC](https://forums.openmv.io/t/memory-error-out-of-fast-frame-buffer-stack-h7/1687 "2020-03-16T21:39:35Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![uraibeef](https://avatars.discourse-cdn.com/v4/letter/u/b3f665/32.png) [@uraibeef](https://forums.openmv.io/u/uraibeef)\ **Post date:** [March 16, 2020, 9:39pm UTC](https://forums.openmv.io/t/memory-error-out-of-fast-frame-buffer-stack-h7/1687/1 "2020-03-16T21:39:35Z")
i’m going to run machine learning example ’ TensorFlow Lite Mobilenet V1 Example ’ on OpenMV H7 and then it show up an error ‘MemoryError: Out of fast Frame Buffer Stack Memory! Please reduce the resolution of the image you are running this algorithm on to bypass this issue!’ but i’m not edit anything on this code? what should i do? thank you ---
**Author:** ![iabdalkader](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/iabdalkader/32/1169_2.png) [@iabdalkader](https://forums.openmv.io/u/iabdalkader)\ **Post date:** [March 17, 2020, 12:47am UTC](https://forums.openmv.io/t/memory-error-out-of-fast-frame-buffer-stack-h7/1687/2 "2020-03-17T00:47:45Z")
Hi, the mobilenet example loads the network to memory and only works on the H7-Plus (with external SDRAM). ---
**Author:** ![kwagyeman](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/kwagyeman/32/4_2.png) [@kwagyeman](https://forums.openmv.io/u/kwagyeman)\ **Post date:** [March 17, 2020, 2:04am UTC](https://forums.openmv.io/t/memory-error-out-of-fast-frame-buffer-stack-h7/1687/3 "2020-03-17T02:04:57Z")
It doesn’t even work on the H7 Plus anymore. Google broke Mobilenet support with their recent updates to TensorFlow. We are waiting for a fix. ---
**Author:** ![uraibeef](https://avatars.discourse-cdn.com/v4/letter/u/b3f665/32.png) [@uraibeef](https://forums.openmv.io/u/uraibeef)\ **Post date:** [March 17, 2020, 6:44am UTC](https://forums.openmv.io/t/memory-error-out-of-fast-frame-buffer-stack-h7/1687/4 "2020-03-17T06:44:29Z")
> [@](#): > > Hi, the mobilenet example loads the network to memory and only works on the H7-Plus (with external SDRAM). thank you, i’m missing to read the comment on top of the example code ---
**Author:** ![uraibeef](https://avatars.discourse-cdn.com/v4/letter/u/b3f665/32.png) [@uraibeef](https://forums.openmv.io/u/uraibeef)\ **Post date:** [March 17, 2020, 6:49am UTC](https://forums.openmv.io/t/memory-error-out-of-fast-frame-buffer-stack-h7/1687/5 "2020-03-17T06:49:03Z")
> [@](#): > > It doesn’t even work on the H7 Plus anymore. Google broke Mobilenet support with their recent updates to TensorFlow. We are waiting for a fix. omg… really? what should i do if i want to train a model, convert to .tflite and deploy on OpenMV. now i used this model [mobilenet\_v1 | Kaggle](https://tfhub.dev/google/imagenet/mobilenet_v1_025_224/feature_vector/4) and it error like this ’ OSError: Didn’t find op for builtin opcode ‘MUL’ version ‘2’ ’ if i can use the model from tfhub can you suggest me for a model that i can re-train for my dataset? thank you very much ---
**Author:** ![kwagyeman](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/kwagyeman/32/4_2.png) [@kwagyeman](https://forums.openmv.io/u/kwagyeman)\ **Post date:** [March 17, 2020, 4:28pm UTC](https://forums.openmv.io/t/memory-error-out-of-fast-frame-buffer-stack-h7/1687/6 "2020-03-17T16:28:39Z")
Hi, you need to install the latest firmware to run that model. Which… might not have been released yet. If you can compile the firmware for the H7 and install it you should be good to go. [https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/kernels/all\_ops\_resolver.cc#L21](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/kernels/all_ops_resolver.cc#L21) We added support for MUL versions 1 to 3. ---
**Author:** ![uraibeef](https://avatars.discourse-cdn.com/v4/letter/u/b3f665/32.png) [@uraibeef](https://forums.openmv.io/u/uraibeef)\ **Post date:** [March 25, 2020, 5:07pm UTC](https://forums.openmv.io/t/memory-error-out-of-fast-frame-buffer-stack-h7/1687/7 "2020-03-25T17:07:16Z")
> [@](#): > > Hi, you need to install the latest firmware to run that model. Which… might not have been released yet. If you can compile the firmware for the H7 and install it you should be good to go. > > [https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/kernels/all\_ops\_resolver.cc#L21](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/kernels/all_ops_resolver.cc#L21) > > We added support for MUL versions 1 to 3. i got an errro when i try to run make.py for build tensorflow-lib ‘’’ tensorflow/lite/micro/kernels/all\_ops\_resolver.cc: In constructor '‘tflite::ops::micro::AllOpsResolver::AllOpsResolver()’:tensorflow/lite/micro/kernels/all\_ops\_resolver.cc::68::35: error: ‘Register\_SUB’ was not declaerd in this scope AddBuiltIn(BuiltinOperator\_SUB, Register\_SUB(), 1, 2); tensorflow/lite/micro/kernels/all\_ops\_resolver.cc::68::35: note: suggested alternative: ‘Register\_SIN’ AddBuiltin(BuiltinOperator\_SUB, Register\_SUB(), 1, 2); what wrong? i don’t know how to solve it? and… if i can’t to do that, when the next release will come? thank you ---
**Author:** ![kwagyeman](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/kwagyeman/32/4_2.png) [@kwagyeman](https://forums.openmv.io/u/kwagyeman)\ **Post date:** [March 26, 2020, 3:21am UTC](https://forums.openmv.io/t/memory-error-out-of-fast-frame-buffer-stack-h7/1687/8 "2020-03-26T03:21:36Z")
Did you clone the repo correctly? If you pulled the latest tensorflow then I have no idea. Things break constantly upstream. You should just clone the repo and init submodules and then it should build okay. Also, try compiling more than once. TensorFlow fails to build the first time sometimes.