edgetpu
PINTO_model_zoo
Our great sponsors
edgetpu | PINTO_model_zoo | |
---|---|---|
34 | 5 | |
382 | 3,220 | |
0.0% | - | |
2.7 | 9.8 | |
over 2 years ago | 21 days ago | |
C++ | Python | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
edgetpu
-
Chromebook Plus: more performance and AI capabilities
I know the tensor power pixelbook was shutdown and I never heard the actual reason just a bunch of speculation about costs/profitability which is probably true.
It's a shame that there isn't more competition and development in the neural asic world to harness the power of llms/generative AI on a low power, cheap hardware platform like the pixelbook line. For someone that invented the TPU they have done a not so great job of ensuring it's commercialization and support. Both on the hardware and software side.
The coral edge tpu seemed to be the right high level idea but without proper execution.
-
Show HN: RISC-V core written in 600 lines of C89
> even in the 80s I wanted an FPGA accelerators in every machine
Mostly unrelated, but I recently discovered that you can buy TPUs, right now, as a consumer product, from https://coral.ai.
The stock firmware already allows you to run these things so hard they overheat, which is amazing.
But yes, I also want FPGA accelerators.
-
Sony backs Raspberry Pi with fresh funding, access to A.I. chips
Chips optimized to perform the type of calculations used for NN inference at high parallelism. A good example would be the google spinoff https://coral.ai/ (though their usecase is highly limited by sub-par software constraints)
-
How can I speed up predictions [RPI, TFLite]?
https://coral.ai, and it looks really neat, but the USB accelerator has a wait time of 81 weeks and the PCIe modules have a wait time of around 14-50 weeks. A wait time that long isn't really an option, are there any alternatives?
-
YOLOv6: Redefine state-of-the-art for object detection
Is this available for https://coral.ai/ somehow? Would it be difficult to convert it?
-
ZMEventNotification Failure when running install.sh
if [ "${INSTALL_CORAL_EDGETPU}" == "yes" ] then # Coral files #echo #echo "Installing pycoral libs, if needed..." #${PY_SUDO} apt-get install libedgetpu1-std -qq #${PY_SUDO} ${INSTALLER} install python3-pycoral -qq echo 'Checking for Google Coral Edge TPU data files...' targets=('coco_indexed.names' 'ssd_mobilenet_v2_coco_quant_postprocess_edgetpu.tflite' 'ssdlite_mobiledet_coco_qat_postprocess_edgetpu.tflite' 'ssd_mobilenet_v2_face_quant_postprocess_edgetpu.tflite') sources=('https://dl.google.com/coral/canned_models/coco_labels.txt' 'https://github.com/google-coral/edgetpu/raw/master/test_data/ssd_mobilenet_v2_coco_quant_postprocess_edgetpu.tflite' 'https://github.com/google-coral/test_data/raw/master/ssdlite_mobiledet_coco_qat_postprocess_edgetpu.tflite' 'https://github.com/google-coral/test_data/raw/master/ssd_mobilenet_v2_face_quant_postprocess_edgetpu.tflite') for ((i=0;i<${#targets[@]};++i)) do if [ ! -f "${TARGET_DATA}/models/coral_edgetpu/${targets[i]}" ] then ${WGET} "${sources[i]}" -O"${TARGET_DATA}/models/coral_edgetpu/${targets[i]}" else echo "${targets[i]} exists, no need to download" fi done fi
-
NUC 10 BXNUC10i7FNH Core i7: how to expand it?
I am a happy owner of a NUC 10 Core i7! so far it has been amazing! now I need run frigate and to optimize this I need to add Google Coral TPU
- Adding PCIe "Bifurcation" to an old Dell R720XD
-
Building a rackmount server in the EU
FYI the dual edge coral TPU m.2 module needs a very unique pic-e interface as they’re each brought to a single PCI-e lane but in a single interface (so it’s 2x1X PCIe lanes not a 1x2X)… subtle difference but very few m.2 e interfaces support it (read about it on the github page)
-
[Request/suggestions] DIY mini PC / low power consumption
Also, the 720/920 tinys also have a m.2 e key slot for wifi; I'm intending to try out a https://coral.ai/products/m2-accelerator-dual-edgetpu/ accelerator in this slot for frigate once the card actually becomes available.
PINTO_model_zoo
-
YOLOv7 object detection in Ruby in 10 minutes
Download the ONNX model from this project: 307_YOLOv7
-
stereodemo: compare several recent stereo depth estimation methods in the wild
Hope it might be useful to more people, and thanks to PINTO0309 and ibaiGorordo for converting several pre-trained models to ONNX!
-
Loading Saved Models for transfer learning
Check it out https://github.com/PINTO0309/PINTO_model_zoo
-
[R][P]MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis
Someone reported, that he converted MobileStyleGAN to tfjs (https://github.com/PINTO0309/PINTO_model_zoo), but i didn't check it
What are some alternatives?
yolov7 - Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
YOLOX - YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
RobustVideoMatting - Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
scrypted - Scrypted is a high performance home video integration and automation platform
frigate - NVR with realtime local object detection for IP cameras
deepsparse - Sparsity-aware deep learning inference runtime for CPUs
yolov7_d2 - 🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥
tensorflow-onnx - Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX
TensorFlow-object-detection-tutorial - The purpose of this tutorial is to learn how to install and prepare TensorFlow framework to train your own convolutional neural network object detection classifier for multiple objects, starting from scratch
Dual-Edge-TPU-Adapter - Dual Edge TPU Adapter to use it on a system with single PCIe port on m.2 A/B/E/M slot
CREStereo - Official MegEngine implementation of CREStereo(CVPR 2022 Oral).
homebridge-wyze-connected-home-op - Wyze Connected Home plugin for Homebridge with support for the Wyze Outdoor Plug