retinaface-keras
retinaface-keras copied to clipboard
bubbliiiing
这是一个retinaface-keras的源码，可以用于训练自己的模型。
Bumps [tensorflow-gpu](https://github.com/tensorflow/tensorflow) from 1.13.2 to 2.12.0. Release notes Sourced from tensorflow-gpu's releases. TensorFlow 2.12.0 Release 2.12.0 TensorFlow Breaking Changes Build, Compilation and Packaging Removed redundant packages tensorflow-gpu and tf-nightly-gpu. These...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [pillow](https://github.com/python-pillow/Pillow) from 8.2.0 to 9.3.0. Release notes Sourced from pillow's releases. 9.3.0 https://pillow.readthedocs.io/en/stable/releasenotes/9.3.0.html Changes Initialize libtiff buffer when saving #6699 [@radarhere] Limit SAMPLESPERPIXEL to avoid runtime DOS #6700 [@wiredfool]...
Bumps [numpy](https://github.com/numpy/numpy) from 1.17.0 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...
Bumps [opencv-python](https://github.com/skvark/opencv-python) from 4.1.2.30 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...
您好，我在wideface数据集中做了一些数据清洗，并加入自己的小部分数据训练，为什么从头训练比在预模型上训练效果要差一些，如果我从头训练的话效果不好可以调整哪些从训练参数呢，感觉keras不想torch那样有很多训练参数可以调整
主干网络模型问题
您好，我想基于您复现的retinaface代码在网络上做一些修改，包括损失上，现在很疑惑您用的这个从头训练的主干网络模型是怎么得到的呢，如果我自定义了一些网络层和损失，您的这个主干网络模型应该不可以直接用的吧。
我在部署模型的过程中，由于平台不支持自定义的层，所以把您自定义的 **UpsampleLike直接修改为UpSampling2D，最中训练的结构也满足要求，但是在运行predict.py的过程中，随机输入一张图片，在Add节点就会出现shape不匹配的问题，在剪枝过程中也会因为shape不同，出错，这里得请教您下为什么不使用UpSampling2D，使用这个如何适用于不同的输入，请指教，感谢！ # P3 = Conv2D_BN_Leaky(cfg['out_channel'], kernel_size=1, strides=1, padding='same', name='C3_reduced', leaky=leaky)(C3) # P4 = Conv2D_BN_Leaky(cfg['out_channel'], kernel_size=1, strides=1, padding='same', name='C4_reduced', leaky=leaky)(C4) # P5 = Conv2D_BN_Leaky(cfg['out_channel'], kernel_size=1, strides=1, padding='same', name='C5_reduced', leaky=leaky)(C5) #...
特征不可复现
https://github.com/bubbliiiing/retinaface-keras/blob/d284764c2f918b9919f1e0e258a6cd6c697b1f1b/nets/retinaface.py#L85
您好我在运行pretrain模型运行predict函数时，出现了shape不匹配的问题，我使用resnet同样进行了测试不会出现 请问我需要先根据你的pretrain模型进行重新训练吗？谢谢 `ValueError: Layer #99 (named "batch_normalization_5"), weight has shape (32,), but the saved weight has shape (64,).`
