From 2559869e04b045b0a92a219219971255fd07544e Mon Sep 17 00:00:00 2001 From: happyboxman2007 Date: Sat, 21 May 2022 20:24:00 +0800 Subject: [PATCH] Update Basic classification: Classify images of clothing.md --- ...ic classification\342\200\224Classify images of clothing.md" | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename Basic classification: Classify images of clothing.md => "Basic classification\342\200\224Classify images of clothing.md" (99%) diff --git a/Basic classification: Classify images of clothing.md "b/Basic classification\342\200\224Classify images of clothing.md" similarity index 99% rename from Basic classification: Classify images of clothing.md rename to "Basic classification\342\200\224Classify images of clothing.md" index e1b8482..1a688de 100644 --- a/Basic classification: Classify images of clothing.md +++ "b/Basic classification\342\200\224Classify images of clothing.md" @@ -83,4 +83,4 @@ test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2) 如上图所示，train_acc=0.91，test_acc=0.88，0.88 < 0.91 并且差距不小，造成这个的原因是过拟合，意思就是模型在训练集上的表现比测试集上的好，有一部分原因是模型记住了训练集的数据和其中的noise，从而对新数据的预测造成负面影响 -代码地址: https://codechina.csdn.net/csdn_codechina/enterprise_technology/-/blob/master/Basic%20classification:%20Classify%20images%20of%20clothing.md \ No newline at end of file +代码地址: https://codechina.csdn.net/csdn_codechina/enterprise_technology/-/blob/master/Basic%20classification:%20Classify%20images%20of%20clothing.md -- GitLab