摘要: 上述模型效果: Training samples: 19094Validation samples: 4774--Training Step: 597 | total loss: 3.60744 | time: 110.471s| RMSProp | epoch: 001 | loss: 3.607 阅读全文
posted @ 2018-05-01 23:28 bonelee 阅读(1426) 评论(0) 推荐(0)
摘要: from:https://blog.csdn.net/qq_14845119/article/details/73648100 Inception v1的网络,主要提出了Inceptionmodule结构(1*1,3*3,5*5的conv和3*3的pooling组合在一起),最大的亮点就是从NIN( 阅读全文
posted @ 2018-05-01 22:44 bonelee 阅读(3440) 评论(1) 推荐(0)
摘要: from:https://blog.csdn.net/diamonjoy_zone/article/details/70904212 环境:Win8.1 TensorFlow1.0.1 软件:Anaconda3 (集成Python3及开发环境) TensorFlow安装:pip install te 阅读全文
posted @ 2018-05-01 19:07 bonelee 阅读(3311) 评论(1) 推荐(1)
摘要: tflearn 数据集太大无法加载进内存问题? Hi, all! I'm trying to train deep net on a big dataset that doesn't fit into memory. Is there any way to use generators to rea 阅读全文
posted @ 2018-05-01 16:01 bonelee 阅读(1248) 评论(0) 推荐(0)
摘要: numpy.argmax numpy.argmax(a, axis=None, out=None)[source] Returns the indices of the maximum values along an axis. Parameters: a : array_like Input ar 阅读全文
posted @ 2018-05-01 15:28 bonelee 阅读(1427) 评论(0) 推荐(0)