tensorflow-serving-yolov3
tensorflow-serving-yolov3 copied to clipboard
Byronnar
本项目主要对原tensorflow-yolov3版本做了许多细节上的改进,增加了TensorFlow-Serving工程部署,训练了多个数据集，包括Visdrone2019, 安全帽等, 安全帽mAP在98%左右, 推理速度1080上608的尺寸大概25fps.
目前使用了docker+nvidia-docker2+tensorRT+TensorFlow-Serving环境对savemodel模型进行了部署，通过客户端-服务器模式测试，时间大概4秒左右，这个性能是无法满足在线应用的。（服务器是tesla T4 16g） 想请教下，各位大神有什么更好的解决方案吗？或者调用模型的方式，本地化部署等等。谢谢
Bumps [numpy](https://github.com/numpy/numpy) from 1.16 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [tensorflow-gpu](https://github.com/tensorflow/tensorflow) from 1.11.0 to 2.7.2. Release notes Sourced from tensorflow-gpu's releases. TensorFlow 2.7.2 Release 2.7.2 This releases introduces several vulnerability fixes: Fixes a code injection in saved_model_cli (CVE-2022-29216) Fixes...
Bumps [pillow](https://github.com/python-pillow/Pillow) from 6.2.0 to 9.0.1. Release notes Sourced from pillow's releases. 9.0.1 https://pillow.readthedocs.io/en/stable/releasenotes/9.0.1.html Changes In show_file, use os.remove to remove temporary images. CVE-2022-24303 #6010 [@radarhere, @hugovk] Restrict builtins within...
使用的转模型的方式是加了一句代码 estimator.export_savemodel(FLAGS.save_dir, input_receiver_fn, strip_default_attrs=True,as_text=False) 相比ckpt 模型的预测结果 转化完的pb模型的预测结果精度降低了0.5% 想问问为什么会有这种情况发生
Bumps [opencv-python](https://github.com/skvark/opencv-python) from 3.4.2.17 to 4.2.0.32. Release notes Sourced from opencv-python's releases. 4.2.0.32 opencv-python: https://pypi.org/project/opencv-python/ opencv-contrib-python: https://pypi.org/project/opencv-contrib-python/ opencv-python-headless: https://pypi.org/project/opencv-python-headless/ opencv-contrib-python-headless: https://pypi.org/project/opencv-contrib-python-headless/ OpenCV version 4.2.0. Changes: macOS environment updated from xcode8.3...
Bumps [opencv-contrib-python](https://github.com/skvark/opencv-python) from 3.4.2.17 to 4.2.0.32. Release notes Sourced from opencv-contrib-python's releases. 4.2.0.32 opencv-python: https://pypi.org/project/opencv-python/ opencv-contrib-python: https://pypi.org/project/opencv-contrib-python/ opencv-python-headless: https://pypi.org/project/opencv-python-headless/ opencv-contrib-python-headless: https://pypi.org/project/opencv-contrib-python-headless/ OpenCV version 4.2.0. Changes: macOS environment updated from xcode8.3...
 Traceback (most recent call last): File "image_demo_mobilenetv2.py", line 89, in predict(image_path) File "image_demo_mobilenetv2.py", line 59, in predict feed_dict={ return_tensors[0]: image_data}) File "C:\Users\lianli\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\client\session.py", line 968, in run run_metadata_ptr) File "C:\Users\lianli\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\client\session.py",...
我想运行convert_weight.py 把608改为416，出现下面错误 Traceback (most recent call last): File "C:\Users\zly\.conda\envs\yolov3-tf1\lib\site-packages\tensorflow\python\framework\ops.py", line 1626, in _create_c_op c_op = c_api.TF_FinishOperation(op_desc) tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimension size must be evenly divisible by 2527 but is 56784 for 'pred_multi_scale/Reshape'...
