TensorFlow Lite的iOS例子 已编译通过，可以在iphone正常运行

# EfficientDet [](https://arxiv.org/abs/1911.09070) [](https://colab.sandbox.google.com/github/google/automl/blob/master/efficientdet/tutorial.ipynb) [](https://tfhub.dev/s?network-architecture=efficientdet) [1] Mingxing Tan, Ruoming Pang, Quoc V. Le. EfficientDet: Scalable and Efficient Object Detection. CVPR 2020. Arxiv link: https://arxiv.org/abs/1911.09070 Updates: - May10/2021: Added EfficientDet-lite checkpoints (by Yuqi and TFLite team) - Mar25/2021: Added [Det-AdvProp](https://arxiv.org/abs/2103.13886) model checkpoints ([see this page](./Det-AdvProp.md)). - Jul20/2020: Added keras/TF2 and new SOTA D7x: 55.1mAP with 153ms. - Apr22/2020: Sped up end-to-end latency: D0 has up to >200 FPS throughput on Tesla V100. * A great collaboration with [@fsx950223](https://github.com/fsx950223). - Apr1/2020: Updated results for test-dev and added EfficientDet-D7. - Mar26/2020: Fixed a few bugs and updated all checkpoints/results. - Mar24/2020: Added tutorial with visualization and coco eval. - Mar13/2020: Released the initial code and models. **Quick start tutorial: [tutorial.ipynb](tutorial.ipynb)** **Quick install dependencies: ```pip install -r requirements.txt```** ## 1. About EfficientDet Models EfficientDets are a family of object detection models, which achieve state-of-the-art 55.1mAP on COCO test-dev, yet being 4x - 9x smaller and using 13x - 42x fewer FLOPs than previous detectors. Our models also run 2x - 4x faster on GPU, and 5x - 11x faster on CPU than other detectors. EfficientDets are developed based on the advanced backbone, a new BiFPN, and a new scaling technique: <p align="center"> <img src="./g3doc/network.png" width="800" /> </p> * **Backbone**: we employ [EfficientNets](https://arxiv.org/abs/1905.11946) as our backbone networks. * **BiFPN**: we propose BiFPN, a bi-directional feature network enhanced with fast normalization, which enables easy and fast feature fusion. * **Scaling**: we use a single compound scaling factor to govern the depth, width, and resolution for all backbone, feature & prediction networks. Our model family starts from EfficientDet-D0, which has comparable accuracy as [YOLOv3](https://arxiv.org/abs/1804.02767). Then we scale up this baseline model using our compound scaling method to obtain a list of detection models EfficientDet-D1 to D6, with different trade-offs between accuracy and model complexity. <table border="0"> <tr> <td> <img src="./g3doc/flops.png" width="100%" /> </td> <td> <img src="./g3doc/params.png", width="100%" /> </td> </tr> </table> ** For simplicity, we compare the whole detectors here. For more comparison on FPN/NAS-FPN/BiFPN, please see Table 4 of our [paper](https://arxiv.org/abs/1911.09070). ## 2. Pretrained EfficientDet Checkpoints We have provided a list of EfficientDet checkpoints and results as follows: | Model | AP^test | AP₅₀ | AP₇₅ |AP_S | AP_M | AP_L | AP^val | | #params | #FLOPs | |---------- |------ |------ |------ | -------- | ------| ------| ------ |------ |------ | :------: | | EfficientDet-D0 ([h5](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d0.h5), [ckpt](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d0.tar.gz), [val](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/val/d0_coco_val.txt), [test-dev](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/testdev/d0_coco_test-dev2017.txt)) | 34.6 | 53.0 | 37.1 | 12.4 | 39.0 | 52.7 | 34.3 | | 3.9M | 2.54B | | EfficientDet-D1 ([h5](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d1.h5), [ckpt](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d1.tar.gz), [val](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/val/d1_coco_val.txt), [test-dev](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/testdev/d1_coco_test-dev2017.txt)) | 40.5 | 59.1 | 43.7 | 18.3 | 45.0 | 57.5 | 40.2 | | 6.6M | 6.10B | | EfficientDet-D2 ([h5](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d2.h5), [ckpt](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d2.tar.gz), [val](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/val/d2_coco_val.txt), [test-dev](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/testdev/d2_coco_test-dev2017.txt)) | 43.9 | 62.7 | 47.6 | 22.9 | 48.1 | 59.5 | 43.5 | | 8.1M | 11.0B | | EfficientDet-D3 ([h5](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d3.h5), [ckpt](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d3.tar.gz), [val](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/val/d3_coco_val.txt), [test-dev](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/testdev/d3_coco_test-dev2017.txt)) | 47.2 | 65.9 | 51.2 | 27.2 | 51.0 | 62.1 | 46.8 | | 12.0M | 24.9B | | EfficientDet-D4 ([h5](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d4.h5), [ckpt](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d4.tar.gz), [val](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/val/d4_coco_val.txt), [test-dev](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/testdev/d4_coco_test-dev2017.txt)) | 49.7 | 68.4 | 53.9 | 30.7 | 53.2 | 63.2 | 49.3 | | 20.7M | 55.2B | | EfficientDet-D5 ([h5](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d5.h5), [ckpt](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d5.tar.gz), [val](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/val/d5_coco_val.txt), [test-dev](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/testdev/d5_coco_test-dev2017.txt)) | 51.5 | 70.5 | 56.1 | 33.9 | 54.7 | 64.1 | 51.2 | | 33.7M | 130B | | EfficientDet-D6 ([h5](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d6.h5), [ckpt](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d6.tar.gz), [val](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/val/d6_coco_val.txt), [test-dev](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/testdev/d6_coco_test-dev2017.txt)) | 52.6 | 71.5 | 57.2 | 34.9 | 56.0 | 65.4 | 52.1 | | 51.9M | 226B | | EfficientDet-D7 ([h5](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d7.h5), [ckpt](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d7.tar.gz), [val](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/val/d7_coco_val.txt), [test-dev](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/testdev/d7_coco_test-dev2017.txt)) | 53.7 | 72.4 | 58.4 | 35.8 | 57.0 | 66.3 | 53.4 | | 51.9M | 325B | | EfficientDet-D7x ([h5](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d7x.h5), [ckpt](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/efficientdet-d7x.tar.gz), [val](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/val/d7x_coco_val.txt), [test-dev](https://storage.googleapis.com/cloud-tpu-checkpoints/efficientdet/coco2/testdev/d7x_coco_test-dev2017.txt)) | 55.1 |