Stack Overflow
Stack Overflow

Questions tagged [edge-tpu]

33 questions
0
votes
0 answers

saved models for tflites to use Edge

Dear google mediapipe team Could you offer the quantized models related pose, face, iris and hand of mediapipe's tflie file I have used mediapipe's holistic at android with qualcomm device. I want to improve the performance by using qualcomm's snpe…
Hoyeon JANG
  • 1
0
votes
0 answers

Gstreamer pipeline error on Google Coral Dev Board Mini

I have the Google Coral Dev Board Mini with the Coral Camera attached. The camera demos work well. However, the Coral BodyPix demo produces the following Gstreamer error: (bodypix_gl_imx.py:1491): dconf-WARNING **: 01:11:30.405: Unable to open…
Andrew Brown
  • 333
  • 3
  • 12
0
votes
0 answers

How do I resolve the error: Attempting to use a delegate that only supports static-sized tensors with a graph that has dynamic-sized tensors?

I am trying to compile an image segmentation (U-net) model to run it on edge TPU (Coral Board). I have converted and quantized the model into .tflite and I am getting the following error when compiling with edgetpu compiler: Attempting to use a…
Rokngreat Spy
  • 1
  • 1
0
votes
1 answer

Facing such problem like no model name edge tpu found and no module name edgeTPU_cpp_wrapper

Traceback (most recent call last): File "/usr/local/lib/python3.9/dist-packages/edgetpu/swig/edgetpu_cpp_wrapper.py", line 18, in swig_import_helper fp, pathname, description = imp.find_module('_edgetpu_cpp_wrapper', [dirname(file)]) File…
Ares
  • 11
  • 1
0
votes
1 answer

"IndexError: index 10 is out of bounds for axis 0 with size 10" when running inference on Coral Dev Board

I'm trying to run a quantized and Edge-TPU-compiled Tensorflow object detection model on a Coral Dev Board. My Code: import time import os from PIL import Image from PIL import ImageDraw from pycoral.adapters import common from pycoral.adapters…
Linus Sorg
  • 31
  • 5
0
votes
0 answers

running inference on coral edgetpu generates IndexError: index 10 is out of bounds for axis 0 with size 10

I was trying to run post training int8 quantized detection model (generated through tflite and coral edgetpu compiler)using 'detect_image.py' example provided on their official website. python3 examples/detect_image.py --model…
Hasnain
  • 13
  • 3
0
votes
1 answer

Is it possible to bias the training of an object detection model towards classification in tensorflow ModelMaker?

I'm using Tensorflow 2 Model Maker to perform transfer training of EfficientDet-Lite (ultimately to run on a Coral EdgeTPU) and I care much more about the classification output and much less about the precision of the bounding boxes. Is there a way…
TvE
  • 1,016
  • 1
  • 11
  • 19
0
votes
1 answer

Image classification using tensorflow lite without Google Coral USB

I am trying to evaluate a Raspberry Pi performance with a Google Goral Edge TPU USB device and without it for an image classification task on a video file. I have managed to evaluate the peformance using the Edge TPU USB device already. However,…
user13861457
0
votes
1 answer

How to sleep and wake google coral development board for a given time

I'm new to stack overflow I needed help with my project on the Google coral dev board. I wanted to know how to make the board sleep for given time then run an operation and wake up. I really am stuck on this hope someone can help me. Thanks in…
Tejas Ashokkumar Awasarmol
  • 1
0
votes
0 answers

Convert SSD MobileNetV2 custom model to edgetpu model?

I'm trying to convert the mobilenetv2(ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8 ) model to EdgeTPU model for object detection. And ı'm using TF2. I tried many solution but still have "cpu operations" when i convert tflite model to edge tpu. how…
Cansel Oğuz
  • 88
  • 2
  • 8
0
votes
0 answers

Google Coral: Is there a limit to model size?

I was looking to use a relatively large model (~300 MB Tflite) but I'm concerned it may not be supported by Google Coral due to its size. That's where my questions come from. How exactly does it work? Is the model loaded into the Coral itself? Or…
Aloha
  • 864
  • 18
  • 40
0
votes
1 answer

How to solve Runtime Error: Empty min/max for tensor Cast while doing post-training quantization (fully quantized tflite model from saved_model)?

I try to create fully quantized tflite model to be able to run it on coral. I downloaded SSD MobileNet V2 FPNLite 640x640 from https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md I installed in…
Andrej Fogelton
  • 123
  • 11
0
votes
1 answer

ValueError: None is only supported in the 1st dimension. Tensor 'input_tensor' has invalid shape '[1, None, None, 3]'

I trained a custom MobileNetV2 SSD model for object detection. I saved the .pb file and now I want to convert it into a .tflite-file in order to use it with Coral edge-tpu. I use Tensorflow 2.2 on Windows 10 on CPU. The code I'm using: import…
Yannik
  • 1
0
votes
2 answers

Can You Mesh Network Google Coral TPUs

I believe it is possible to leverage the power of two USB Connected connected Google Coral TPUs in conjunction with one another (or at least side by side, running their own inferences each). However, is it possible to leverage two or more Google…
jstats
  • 596
  • 4
  • 17
0
votes
2 answers

Speed Up Multiple Model Inference on EDGE TPU

I have retrained a RESNET50 model for reidentification on EDGE TPU. However, it seems to be no way to fetch a batch of image to EDGE_TPU. I have come up with a solution of running multiple same model for images. However, is there anyway to speed up…
dtlam26
  • 1,410
  • 11
  • 19
1
2
3