在minist比賽中有一個非常好的內核
https://www.kaggle.com/yassineghouzam/introduction-to-cnn-keras-0-997-top-6
還有中文譯版:
https://blog.csdn.net/liutianheng654/article/details/81123450
在訓練模型時
報出改錯:“AssertionError: AbstractConv2d Theano optimization failed: there is no implementation available supporting the requested options. Did you exclude both "convdnn" and "convgemm" from the optimizer? If on GPU, is cuDNN available and does the GPU support it? If on CPU, do you have a BLAS library installed Theano can link against?On the CPU we do not support float16.”
我在網上查到cuda暫時只支持NVIDIA的,所以我不打算安裝cuDNN,在尋找cpu方法時有博主說需要安裝OpenBlas噼裏啪啦還要裝啥啥的但沒有詳細的操作,最終回到kaggle頁面下找到了答案。
只需要“conda install numpy scipy mkl-service libpython m2w64-toolchain”就可以解決問題了。