-
https://github.com/eriklindernoren/ML-From-Scratch
-
https://github.com/eriklindernoren/Action-Recognition/blob/b43ec097ab293ac8d83aac02b5addd27686ebe8c/models.py#L68
-
训练自己的数据集,数据集小,4k多张图,共20类,不管是训练baseline还是稀疏化,mAP怎么都很低,学习率调整了也上不去。
1、在darknet的c的源码上训练baseline,用 eriklindernoren 的test测mAP是0.73,用本项目test测是0.51,并且调整batch size会对结果产生影响,不明原因中。。。
2、用本项目训练baseline,调整了很多次mAP…
-
Public implementation is here: https://github.com/eriklindernoren/Keras-GAN#adversarial-autoencoder
I need to take this and apply this to the tissue patch sample generation strategy that I am using…
-
Hello, I noticed that within your implementation of pix2pix, Datasets will return image in form of like this
https://github.com/eriklindernoren/PyTorch-GAN/blob/fd9f0713eadd03b09e4fa0e828d5b7b6375e…
-
do you have xgboost classifier in
https://github.com/eriklindernoren/ML-From-Scratch/blob/master/mlfromscratch/supervised_learning/xgboost.py
but not regression?
-
https://github.com/eriklindernoren/PyTorch-GAN/blob/a163b82beff3d01688d8315a3fd39080400e7c01/implementations/pix2pix/datasets.py#L26
-
In paper https://arxiv.org/pdf/1611.04076.pdf section `3.2.3 Parameters Selection` in `eq. 9` they use `b=1, a=0, c=1`, but I can't see this constants in the code:
https://github.com/eriklindernoren…
-
https://github.com/eriklindernoren/PyTorch-GAN/blob/a163b82beff3d01688d8315a3fd39080400e7c01/implementations/bicyclegan/models.py#L153
in_channels -> channels
(I guess)
-
Pretty cool project. Gaussian Process might be something you can add in the future.