| [ |
| { |
| "url": "https://github.com/onnx/tensorflow-onnx/blob/master/tutorials/efficientnet-lite.ipynb", |
| "name": "tensorflow-onnx/tutorials/efficientnet-lite.ipynb at main - GitHub", |
| "snippet": "This tutorial shows how to convert them to ONNX. To start, we setup a few environment variables and download the pre-trained model.", |
| "host_name": "github.com", |
| "rank": 0, |
| "date": "", |
| "favicon": "" |
| }, |
| { |
| "url": "https://huggingface.co/onnxmodelzoo/efficientnet-lite4-11", |
| "name": "onnxmodelzoo/efficientnet-lite4-11 - Hugging Face", |
| "snippet": "EfficientNet-Lite4 is an image classification model that achieves state-of-the-art accuracy. It is designed to run on mobile CPU, GPU, and ...", |
| "host_name": "huggingface.co", |
| "rank": 1, |
| "date": "", |
| "favicon": "" |
| }, |
| { |
| "url": "https://developers.google.com/edge/mediapipe/solutions/vision/image_embedder", |
| "name": "Image embedding task guide | Google AI Edge", |
| "snippet": "The MediaPipe Image Embedder task lets you create a numeric representation of an image, which is useful in accomplishing various ML-based ...", |
| "host_name": "developers.google.com", |
| "rank": 2, |
| "date": "", |
| "favicon": "" |
| }, |
| { |
| "url": "https://debuggercafe.com/person-segmentation-with-efficientnet-lite", |
| "name": "Person Segmentation with EfficientNet Lite Based - DebuggerCafe", |
| "snippet": "Person segmentation using a EfficientNet Lite based encoder and FCN32s decoder with the PyTorch Deep Learning framework.", |
| "host_name": "debuggercafe.com", |
| "rank": 3, |
| "date": "", |
| "favicon": "" |
| }, |
| { |
| "url": "https://www.youtube.com/watch?v=nVTropZJC88", |
| "name": "Local Image Embeddings in .NET | CLIP + ONNX Multimodal AI", |
| "snippet": "... image embeddings locally using ONNX Runtime - Build a simple image search scenario - Connect it to a lightweight RAG-style chat - Discuss ...", |
| "host_name": "www.youtube.com", |
| "rank": 4, |
| "date": "", |
| "favicon": "" |
| }, |
| { |
| "url": "https://blog.tensorflow.org/2020/03/higher-accuracy-on-vision-models-with-efficientnet-lite.html", |
| "name": "Higher accuracy on vision models with EfficientNet-Lite", |
| "snippet": "We are excited to announce EfficientNet-Lite (GitHub, TFHub), which runs on TensorFlow Lite and designed for performance on mobile CPU, GPU, and EdgeTPU.", |
| "host_name": "blog.tensorflow.org", |
| "rank": 5, |
| "date": "", |
| "favicon": "" |
| }, |
| { |
| "url": "https://www.edgecortix.com/en/blog/connecting-edge-ai-software-with-pytorch-tensorflow-lite-onnx-models", |
| "name": "Connecting Edge AI Software with PyTorch, TensorFlow Lite, and", |
| "snippet": "Edge AI software workflows can start with PyTorch, TensorFlow, or ONNX models, and MERA automatically converts them to code for EdgeCortix DNA IP.", |
| "host_name": "www.edgecortix.com", |
| "rank": 6, |
| "date": "", |
| "favicon": "" |
| }, |
| { |
| "url": "https://medium.com/data-science/bye-bye-mobilenet-hello-efficientnet-9b8ec2cc1a9c", |
| "name": "Bye-bye MobileNet. Hello EfficientNet! | by Vardan Agarwal - Medium", |
| "snippet": "MobileNet was the go-to model for an app and edge deployment. Now it is dethroned by the family of EfficientNet Lite models.", |
| "host_name": "medium.com", |
| "rank": 7, |
| "date": "", |
| "favicon": "" |
| }, |
| { |
| "url": "https://docs.oracle.com/en/database/oracle/machine-learning/oml4py/2-23ai/mlpug/onnx-pipeline-models-image-embedding.html", |
| "name": "ONNX Pipeline Models: Image Embedding - Oracle Help Center", |
| "snippet": "ONNX pipeline models provides image embedding models that accepts image as an input and produces embeddings as output.", |
| "host_name": "docs.oracle.com", |
| "rank": 8, |
| "date": "", |
| "favicon": "" |
| }, |
| { |
| "url": "https://www.researchgate.net/publication/397017514_An_Enhanced_MobileNet-Based_Lightweight_Image_Classification_Model_for_Environments_with_Limited_Resources", |
| "name": "An Enhanced MobileNet-Based Lightweight Image Classification", |
| "snippet": "Using the ImageNet-10 dataset, the model is compared against industry-leading lightweight architectures such as MobileNetV2 and EfficientNet.", |
| "host_name": "www.researchgate.net", |
| "rank": 9, |
| "date": "", |
| "favicon": "" |
| } |
| ] |
