Search results
-
M
Some success with a coral tpu (m.2) with CPAI and BI
If I'm reading that correctly, that's ~700 frames analyzed (motion triggers) over 6 hours, for around 1 frame every 30 seconds? How many frames does a motion trigger cause to be analyzed? -
M
Some success with a coral tpu (m.2) with CPAI and BI
Good to know. What sort of video stream load are you putting on it? (Average FPS?) -
M
Some success with a coral tpu (m.2) with CPAI and BI
Sorry to hear that. I hope it’s better in the next version. -
M
Some success with a coral tpu (m.2) with CPAI and BI
That would be an API change between BI and CPAI, I’d guess. BI would need to send the info to CPAI in order for it to appear in anything on the CPAI side, and I don’t think it does. I’m not familiar with the details of the API, but I haven’t seen anything like that in there. -
M
Sharing setups with CodeProject AI on Coral hardware (Spring 2024)
The most important part of my calculus ended up being power consumption, which is pretty hard to measure. Running a GPU on a steady stream of video for a year is going to cost a bit. For me, for example, I calculated out that if the card ended up using an extra ~40 watts, I'd spend $100-$200 per... -
M
Sharing setups with CodeProject AI on Coral hardware (Spring 2024)
I’m hoping that the guy finishes this board: https://github.com/magic-blue-smoke/Dual-Edge-TPU-Adapter/blob/main/PCIex4_2xDualTPU_s.jpeg And then we can drop a few duals into a single slot. -
M
Sharing setups with CodeProject AI on Coral hardware (Spring 2024)
I do not have experience. It was something I looked into and it seemed interesting until I learned I needed bifurcation and didn’t have it. With that one in particular you may need 4-way bifurcation, which is even more rare, but as I understand it if you only have 2-way that just means that only... -
M
Sharing setups with CodeProject AI on Coral hardware (Spring 2024)
There is also this one, but your motherboard has to be compatible with bifurcation. https://a.co/d/cEtN1G7 -
M
How to train a custom YOLOv5 model using CodeProject.AI Training for YoloV5 6.2 module
For the original models: https://coral.ai/models/object-detection/ There are really two models (MobileNet & EfficentDet) in your comment in different sizes and variations. Mainly think of the different sizes. Then, for models that don't fit well on one TPU, I've been playing with segmenting... -
M
Some success with a coral tpu (m.2) with CPAI and BI
Here's a feature branch to base any USB work off of that will make it much easier to keep things in sync: https://github.com/seth-planet/CodeProject.AI-Server/tree/usb_debug I wonder if the training set from that link can be adapted to train a YOLOv8 model? You should look into the docs here... -
M
How to train a custom YOLOv5 model using CodeProject.AI Training for YoloV5 6.2 module
If you’re starting from ‘scratch’ with an existing .tflite file, the first step would be to instal the TPU compiler and converting to that format: https://coral.ai/docs/edgetpu/compiler/ I think the YOLOv8 export takes care of that for you, but it may still be needed if you find your own... -
M
YOLO v8 issue with Coral TPU
Possibly. I found it has a CPU-only instruction midway through the model so it doesn’t run as well as you’d think it should. Everything after that instruction ends up also being CPU-only. (Unless you’re running multi-TPUs, because then you can run the remaining instructions on the next TPU segment.) -
M
How to train a custom YOLOv5 model using CodeProject.AI Training for YoloV5 6.2 module
Most models can be used on a Coral TPU but require some extra steps to get them exported as the appropriate .tflite file and then more steps to get them segmented across multiple TPUs. YOLOv8 is relatively easy to export since they have the settings built into their export feature, but it’s not... -
M
Some success with a coral tpu (m.2) with CPAI and BI
Also, the original module code mixed different models under the label of MobileNet, so one thing to check is what the model is that is actually being loaded. -
M
Some success with a coral tpu (m.2) with CPAI and BI
The funny thing about accuracy measurements is there are so many false positives to get rid of also, and everyone has different opinions about the cost of false positives. It also just occurred to me that if anyone is setting up a system for development, it should be based off of a GitHub... -
M
Some success with a coral tpu (m.2) with CPAI and BI
I didn’t write that code, but we are trying to use CPAI model configurations in a way that it hadn’t been originally intended. Both because we are wrapping up a number of different sizes and types of models in the Coral module and because we are trying to only download the models on demand. So... -
M
Some success with a coral tpu (m.2) with CPAI and BI
lol. Once you have kids (two under two until recently!) you lose control of time you didn’t even know you had and in ways you were were able to lose. I swear I’ve lost twenty IQ points on top of everything else. Feel free to use whatever os/install is most useful for you. After all I’ll be... -
M
Some success with a coral tpu (m.2) with CPAI and BI
I still have all the time limitations of two young daughters, but maybe I should take you up on that offer. Next time there’s a release of CPAI and you’re feeling like you have the time to get everything installed and set up on your end, we could look into it. I’d probably need a walk through of... -
M
Some success with a coral tpu (m.2) with CPAI and BI
That's part of my debugging problem, I'm not running CPAI or have it setup right now. I'm just running the core TPU code outside of CPAI to work on and test the performance. For example, the two next things I'm planning on looking at are a reorg of the internals to reduce context switching... -
M
Some success with a coral tpu (m.2) with CPAI and BI
Part of the problem is that I suspect the logs are enough. There tends not to be enough logged, so someone needs to get in there and start printing out all of the intermediate values. And the unstable parts are even harder. I've tried to put everything together in such a way that the system can... -
M
Some success with a coral tpu (m.2) with CPAI and BI
Yeah, I believe you. “It works on my machine.” Sounds like a poor excuse, but really does make it hard to debug and fix issues. And, like I said, all my TPUs are busy right now working on other things and haven’t actually been running CPAI in a real-world way for months. -
M
Some success with a coral tpu (m.2) with CPAI and BI
Yeah. Something like that should work in theory, but I don’t have a USB one to test with. I’m sure I made an assumption somewhere but don’t know where. Seems silly to spend > $60 on flakey and slow hardware just to see how it breaks. But I may do it anyway just to make it happen. -
M
Some success with a coral tpu (m.2) with CPAI and BI
Alright. I know there are a number of issues kicking around that I may not be able to debug anytime soon since I’m not in a position to do so. I’ve been only in the core of the code and even then I’ve been testing with particular load patterns and lack of driver/hardware failures. -
M
Some success with a coral tpu (m.2) with CPAI and BI
Honestly, I don’t really understand what would cause you to have to reinstall to change the model size, but I haven’t been running that part of the code so I can’t speak to it. It’s an area we’ve actively been working on, however, to try to reduce the CPAI bandwidth cost. So if you’re feeling... -
M
CodeProject.AI Version 2.5
Only the IPcam-general is ready to be used in that repo. Ive sent it along to be included in the next version of CPAI, but I don’t know when that will be or how it’ll be handled. Unfortunately it also doesn’t run that great on one TPU because the compiler says there is a CPU-only operation... -
M
Some success with a coral tpu (m.2) with CPAI and BI
Yeah, it’s a little overzealous in shutting down the TPUs when not used, but they should come back online pretty quickly. The next version should both wait longer before shutting them down and bring them back up faster. -
M
CodeProject.AI Version 2.5
It should really never fall back to CPU and it’s something that only happens on a failed instantiation, so there is something wrong with your installation. (I personally think it’s a confusing design choice and it should fail 100% instead of falling back to CPU.) -
M
CodeProject.AI Version 2.5
Do the failed inferences leave any messages in the log file? -
M
CodeProject.AI Version 2.5
Nothing wrong with finding trains in your yard. My toddler would love that! ;) Same with elephants…. The biggest problem these days with the Coral module is that my Linux machine is rock solid so I can’t test, improve, and recover from the crashes folks are seeing. I need to start running the... -
M
CodeProject.AI Version 2.5
Well there was another bug in the code where it saved out the thumbnail and then used the thumbnail in the next iteration for resizing. I thought it was suspiciously fast. But still looks like OpenCV easily takes the speed crown here using a 4k image. $ python test_img_timing.py cv2: 4.9.0...