Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile
Ibai Gorordo | Turing Inc.

@ibaigorordo

ibaigorordo.github.io

ID: 1292117840888119298

linkhttps://github.com/ibaiGorordo calendar_today08-08-2020 15:18:01

263 Tweet

699 Followers

356 Following

Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

ONNX-SAM2-Segment-Anything - Updated -Set multimask_output=False on the Pytorch model -> ONNX model will only return one mask per label -Add Bilinear interpolation inside the model for smoother results github.com/ibaiGorordo/ON…

Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

SAM2 (ONNX) - Add box selection - The accuracy is affected by how close the box fits the object - The behaviour with points is not very reliable Code: github.com/ibaiGorordo/ON… Video: youtu.be/gF2Ejq8IKsI

Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

One of the hardest parts of sharing GitHub examples is finding nice images and videos to show what the model can do. I used Flux.1 to generate an image and then ran object detection.

One of the hardest parts of sharing GitHub examples is finding nice images and videos to show what the model can do. 

I used Flux.1 to generate an image and then ran object detection.
Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

YOLOv10 Object Detection (ONNX) It is almost the same as my v9 repo but downloads the models from the official repository. Code: github.com/ibaiGorordo/ON… Video: youtu.be/hz9PYZF4ax4 YOLOv10: github.com/THU-MIG/yolov10

Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

NeuflowV2 - Optical Flow (ONNX) "Compared to other state-of-the-art methods, our model achieves a 10x-70x speedup" Added example with Object Detection to mask the detected objects' flow. Code:github.com/ibaiGorordo/ON… Video:youtu.be/S0RnlEHGNrc Neuflow: github.com/neufieldroboti…

Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

本日、tur.ing に入社しました!End-to-End自動運転AIのエンジニアとして挑戦していきます! Today I joined tur.ing as an engineer working on End-to-End autonomous driving! youtube.com/watch?v=wvZlbA…

本日、tur.ing に入社しました!End-to-End自動運転AIのエンジニアとして挑戦していきます!

Today I joined tur.ing as an engineer working on End-to-End autonomous driving!

youtube.com/watch?v=wvZlbA…
Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

入社したばかりですが、チューリング飯再開しました!社員みんな対応できるので、お気軽にどうぞ。一人あたり12,000円で、美味しいご飯と技術トークを楽しみたい方大歓迎!転職意欲は問いません。 少しでも興味あればぜひDMください!

入社したばかりですが、チューリング飯再開しました!社員みんな対応できるので、お気軽にどうぞ。一人あたり12,000円で、美味しいご飯と技術トークを楽しみたい方大歓迎!転職意欲は問いません。

少しでも興味あればぜひDMください!
Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

良さそうです。 neuflowのコードでテストしましたが、input_img = input_img / 255.0 の部分(github.com/ibaiGorordo/ON…)をコメントアウトするだけで問題なく動作しました。 SEA-RAFT ONNX Export Colab: colab.research.google.com/drive/1nmgLcAK…

良さそうです。

neuflowのコードでテストしましたが、input_img = input_img / 255.0 の部分(github.com/ibaiGorordo/ON…)をコメントアウトするだけで問題なく動作しました。

SEA-RAFT ONNX Export Colab: colab.research.google.com/drive/1nmgLcAK…
Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

Check out our model in action! Our model’s accuracy feels even more impressive when visualized with Rerun (It would be nice to have flat 3D lines, without using mesh🙏)

Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

Dust3r inference minimal (Pytorch) Minimal & easy-to-use inference code for Dust3r: - Simplified inference code - ONNX export - Limited to 2 images for simplicity Code: github.com/ibaiGorordo/du…

Dust3r inference minimal (Pytorch) 

Minimal & easy-to-use inference code for Dust3r:
 - Simplified inference code
- ONNX export
- Limited to 2 images for simplicity

Code: github.com/ibaiGorordo/du…
Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

DeDoDe v2 - Feature Detector, Descriptor and Matching (Pytorch) Code: github.com/ibaiGorordo/de… Video:youtu.be/cDHNvORTRjo?si… DeDoDe: github.com/Parskatt/DeDoDe

Ibai Gorordo | Turing Inc. (@ibaigorordo) 's Twitter Profile Photo

VGGT Pytorch Inference (WIP) A wrapper around the VGGT model to visualize outputs directly in Rerun. Turn images into point clouds, camera poses, depth maps, and intrinsic easily Code: github.com/ibaiGorordo/vg…