automl
SynthDet
Our great sponsors
automl | SynthDet | |
---|---|---|
7 | 3 | |
6,154 | 350 | |
0.7% | 0.9% | |
5.0 | 2.9 | |
22 days ago | 10 months ago | |
Jupyter Notebook | C# | |
Apache License 2.0 | Apache License 2.0 |
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.
automl
- Slowdown / normalization on the Front Lines
- Lion, a new Optimizer from Google, provides 3-5x speedup compared to AdamW
-
How do I increase the accuracy of small objects when training an object detector?
I'm using Google Brain's EfficientDet repo to train an object detector. What hyperparameters should I choose to increase accuracy for small objects.
-
Android QR Code Detection with TensorFlow Lite
EfficientDet-D0 has comparable accuracy as YOLOv3.
-
[R] Google AI Introduces Two New Families of Neural Networks Called ‘EfficientNetV2’ and ‘CoAtNet’ For Image Recognition
Code for https://arxiv.org/abs/2104.00298 found: https://github.com/google/automl/efficientnetv2
-
Google AI Introduces Two New Families of Neural Networks Called ‘EfficientNetV2’ and ‘CoAtNet’ For Image Recognition
7 Min Read | Paper (CoAtNet) | Paper (EfficientNetV2) | Google blog | Code
-
[R] EfficientNetV2: Smaller Models and Faster Training
Abstract: This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. To develop this family of models, we use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed and parameter efficiency. The models were searched from the search space enriched with new ops such as Fused-MBConv. Our experiments show that EfficientNetV2 models train much faster than state-of- the-art models while being up to 6.8x smaller. > Our training can be further sped up by progressively increasing the image size during training, but it often causes a drop in accuracy. To compensate for this accuracy drop, we propose to adaptively adjust regularization (e.g., dropout and data augmentation) as well, such that we can achieve both fast training and good accuracy. > With progressive learning, our EfficientNetV2 significantly outperforms previous models on ImageNet and CIFAR/Cars/Flowers datasets. By pretraining on the same ImageNet21k, our EfficientNetV2 achieves 87.3% top-1 accuracy on ImageNet ILSVRC2012, outperforming the recent ViT by 2.0% accuracy while training 5x-11x faster using the same computing resources. Code will be available at this https URL.
SynthDet
-
Looking for 3D food packaging assets
Didn't try but Unity did a object recognition project with store products: https://github.com/Unity-Technologies/SynthDet. You can find the models and texture in the "Assets/Foreground Objects" folder. And you may need to check the license depending on your usage.
-
How to generate images and labels using unity (or other game engine) to train YOLO5 object detection model? (Synthetic Data generation using unity for neural network learning). Are there any existing solutions or guides?
This is probably what you're looking for . https://github.com/Unity-Technologies/SynthDet
-
Imported materials for objects can't edit.
So I'm working on Unity with this Project (SynthDet) https://github.com/Unity-Technologies/SynthDet and I'm working on imported objects (obj. ), trying to edit materials of those objects, but I can't. The materials are gredy out. Don't know what to do. Do you guys have any ideas what to do, to allow to edit imported materials?
What are some alternatives?
simple-faster-rcnn-pytorch - A simplified implemention of Faster R-CNN that replicate performance from origin paper
AI-basketball-analysis - :basketball::robot::basketball: AI web app and API to analyze basketball shots and shooting pose.
gpt-3 - GPT-3: Language Models are Few-Shot Learners
Deep-Learning-Push-Up-Counter - Deep Learning approach to count the number of repetitions in a video of push ups or pull ups.
FLAML - A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
yolov3-tf2 - YoloV3 Implemented in Tensorflow 2.0
TFLiteClassification - TensorFlow Lite Image Classification Python Implementation
machine-learning-for-trading - Code for Machine Learning for Algorithmic Trading, 2nd edition.
SipMask - SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)
Real-time-Object-Detection-for-Autonomous-Driving-using-Deep-Learning - My Computer Vision project from my Computer Vision Course (Fall 2020) at Goethe University Frankfurt, Germany. Performance comparison between state-of-the-art Object Detection algorithms YOLO and Faster R-CNN based on the Berkeley DeepDrive (BDD100K) Dataset.
efficientdet-pytorch - A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
make-sense - Free to use online tool for labelling photos. https://makesense.ai