我做了3類手勢，每類手勢有90張圖，是28*28的灰度圖，然后用tensorflow仿照MNIST的CNN網路做了一個架構，訓練出來的效果就是：
Step=0, Train loss=1.1398,[Test accuracy=0.33]
Step=30, Train loss=0.7693,[Test accuracy=0.33]
Step=60, Train loss=0.4144,[Test accuracy=0.33]
Step=90, Train loss=0.1760,[Test accuracy=0.33]
Step=120, Train loss=0.0833,[Test accuracy=0.33]
Step=150, Train loss=0.0477,[Test accuracy=0.33]
Step=180, Train loss=0.0313,[Test accuracy=0.33]
Step=210, Train loss=0.0224,[Test accuracy=0.33]
Step=240, Train loss=0.0170,[Test accuracy=0.33]
Step=270, Train loss=0.0135,[Test accuracy=0.33]
Step=300, Train loss=0.0111,[Test accuracy=0.33]
Step=330, Train loss=0.0093,[Test accuracy=0.33]
Step=360, Train loss=0.0080,[Test accuracy=0.33]
Step=390, Train loss=0.0069,[Test accuracy=0.33]
………………
一直到Step=2000，Test accuracy都是0.33。。。
我才3類手勢，隨便猜一張圖都是33%的概率，感覺這個訓練完全沒用啊……求決議，我不知道哪里出錯了。但是同樣的架構，用來識別它那個10個手寫數字的精度就很好，我只是改了輸入，輸出端，還有一兩個卷積核的大小。 蒙蔽ing
轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/81696.html
上一篇：用python進行信道建模