We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent de780c4 commit 8d2a241Copy full SHA for 8d2a241
README.md
@@ -507,6 +507,10 @@ plt.imshow(X[0], cmap='gray')
507
508
模型的大小是12.8MB,准确率达到了惊人的 99.21%,即使连 0 和 O 都能精准区分,非常成功。
509
510
+# 扩展
511
+
512
+如果你比较喜欢 PyTorch,可以看 [ctc_pytorch.ipynb](ctc_pytorch.ipynb),精度更高,达到了 99.57%。
513
514
如果你想查看更多经验,可以看看我在百度云魅族深度学习应用大赛的代码和思路:[https://github.com/ypwhs/baiduyun_deeplearning_competition](https://github.com/ypwhs/baiduyun_deeplearning_competition)
515
516
# 参考链接
0 commit comments