gtx 1080ti i7
32g記憶體
三星sm951，256g固態nvme硬碟
vs2013+win10+cuda9.0+cudnn5.1
解決方案：開啟vs2013後，從檔案-->開啟->專案裡重新開啟caffe，只能是暫時的解決方案
error：nuget error:未知命令:「overlay」
error：msb4062 載入任務「nugetpackageoverlay」失敗問題
反正使用nuget怎麼配都有問題
去配置：
d:\wxf\opencv\build
f:\caffe\nugetpackages\glog.0.3.3.0\build\native
f:\caffe\nugetpackages\gflags.2.1.2.1\build\native
$(opencvpath)\x64\vc12\lib;$(librarypath)
$(opencvpath)\include;$(opencvpath)\include\opencv;$(opencvpath)\include\opencv2;$(includepath)
$(gflagspath)\x64\v120\dynamic\lib;$(librarypath)
$(gflagspath)\include;$(includepath)
$(glogpath)\lib\x64\v120\release\dynamic;$(librarypath)
$(glogpath)\include;$(includepath)
opencv_objdetect2410.lib;
opencv_ts2410.lib;
opencv_video2410.lib;
opencv_nonfree2410.lib;
opencv_ocl2410.lib;
opencv_photo2410.lib;
opencv_stitching2410.lib;
opencv_superres2410.lib;
opencv_videostab2410.lib;
opencv_calib3d2410.lib;
opencv_contrib2410.lib;
opencv_core2410.lib;
opencv_features2d2410.lib;
opencv_flann2410.lib;
opencv_gpu2410.lib;
opencv_highgui2410.lib;
opencv_imgproc2410.lib;
opencv_legacy2410.lib;
opencv_ml2410.lib;
libglog.lib;
gflags.lib;
gflags_nothreads.lib;
$(cudadependencies)
$(glogpath)\lib\x64\v120\debug\dynamic;$(librarypath)
$(glogpath)\include;$(includepath)
opencv_ml2410d.lib;
opencv_calib3d2410d.lib;
opencv_contrib2410d.lib;
opencv_core2410d.lib;
opencv_features2d2410d.lib;
opencv_flann2410d.lib;
opencv_gpu2410d.lib;
opencv_highgui2410d.lib;
opencv_imgproc2410d.lib;
opencv_legacy2410d.lib;
opencv_objdetect2410d.lib;
opencv_ts2410d.lib;
opencv_video2410d.lib;
opencv_nonfree2410d.lib;
opencv_ocl2410d.lib;
opencv_photo2410d.lib;
opencv_stitching2410d.lib;
opencv_superres2410d.lib;
opencv_videostab2410d.lib;
libglog.lib;
gflagsd.lib;
gflags_nothreadsd.lib;
$(cudadependencies)
name: "lenet"
layer }
}
錯誤：check failed: labels_.size() == output_layer->channels() (1 vs. 10) number of labels is different from the output layer dimension.
分類的標籤檔案不對，在label.txt中只寫了個0，應該是0,1,2,3,4,5,6,7,8,9
設定訓練模型時的通道數的地方沒找到，後面回來補充下。
之前感覺是均值檔案的問題，因為訓練lenet時沒加減均值的過程，但應該不至於有很高的錯誤率，後面在知乎上 原來訓練集是黑底白字的！將測試樣本改為黑底白字後就ok了
win10 caffe GPU配置注意點
1 cuda安裝注意點 2 cudnn安裝 3 caffe的配置檔案修改 開啟windows中caffe的配置檔案，修改部分 false 如果只是有cpu則將此修改為true,下一行修改為false true 使用gpu則正好相反，並將下一行的版本號改為自己電腦中的版本號 9.1 e cuda to...
不是變數 win10 在win10下安裝manim
manim是製作簡單動畫的乙個python庫，具體介紹請參考 3b1b manim github.com 例如 無論是windows或者是其它作業系統使用者的安裝方式，在鏈結中有詳細說明。下面詳細說明一下安裝步驟，重點放在win10使用者可能遇到的問題上。anaconda,texlive,ffmpe...
Win10下安裝TensorFlow（GPU版本）
之前在用的 tensorflow 是 cpu 版本的，現在感覺雖然自己電腦的 gpu 沒有多強，但還是很有用的，因此把 tensorflow 換成了 gpu 版本的。安裝過程比較順利，但也有一些值得注意的地方，與大家分享下。要注意 tensorflow 需要 python3.5 以上的，別下錯了 有...