
深度学习
火星种萝卜
c++ vc mfc java
展开
-
github上搜索论文代码
Semantic Scholar | AI-Powered Research Tool转载 2022-07-04 20:15:23 · 1781 阅读 · 0 评论 -
华为诺亚调研200多篇文献,视觉Transformer综述入选TPAMI 2022
百度安全验证百度安全验证转载 2022-02-23 19:44:22 · 97 阅读 · 0 评论 -
bert 原理
https://blog.csdn.net/sunhua93/article/details/102764783转载 2020-08-26 23:02:18 · 134 阅读 · 0 评论 -
nadam优化器
https://blog.csdn.net/qq_42109740/article/details/105401197转载 2020-08-26 19:38:19 · 4213 阅读 · 0 评论 -
绘制ROC 曲线 计算 AUC PR曲线(精准率 召回率)示例
#ROC评价colors = ['r', 'g', 'b', 'y', 'k', 'c', 'm', 'brown', 'r']lw = 1Cs = [1e-6, 1e-4, 1e0]plt.figure(figsize=(12,8))plt.xlabel('False Positive Rate')plt.ylabel('True Positive Rate')plt.title('ROC Curve for different classifiers')plt.plot([0, 1]原创 2020-08-23 21:26:40 · 933 阅读 · 0 评论 -
机器学习评价指标ROC AUC
https://blog.csdn.net/qq_20011607/article/details/81712811转载 2020-08-23 20:49:32 · 117 阅读 · 0 评论 -
讲清楚embedding到底在干什么
https://blog.csdn.net/k284213498/article/details/83474972?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.channel_param&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.channe转载 2020-08-23 15:36:59 · 431 阅读 · 0 评论 -
2020-08-23训练过程--Batchsize选择多大对最优参数的影响
https://blog.csdn.net/wydbyxr/article/details/84855489?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.channel_param&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.channel_p转载 2020-08-23 11:56:26 · 277 阅读 · 0 评论 -
2020-08-23损失函数:交叉熵详解 对二元交叉熵损失函数解释的较好
https://zhuanlan.zhihu.com/p/115277553转载 2020-08-23 10:23:52 · 1311 阅读 · 0 评论 -
2020-08-23logloss对数损失函数
注意:softmax使用的即为交叉熵损失函数,binary_cossentropy为二分类交叉熵损失,categorical_crossentropy为多分类交叉熵损失,当使用多分类交叉熵损失函数时,标签应该为多分类模式,即使用one-hot编码的向量。https://www.cnblogs.com/guoyaohua/p/9217206.html...转载 2020-08-23 09:30:41 · 371 阅读 · 0 评论 -
深度学习model.fit计算流图
https://blog.csdn.net/u011119817/article/details/103181664/转载 2020-07-24 18:53:07 · 639 阅读 · 0 评论 -
什么事DQN 强化学习 Deep Q NETWORK
https://zhuanlan.zhihu.com/p/25290858转载 2020-07-18 17:29:02 · 128 阅读 · 0 评论 -
人人看懂GRU
https://zhuanlan.zhihu.com/p/32481747转载 2020-07-01 13:12:15 · 203 阅读 · 0 评论 -
单词向量化
https://blog.csdn.net/menghaocheng/article/details/102792810转载 2020-06-30 22:23:35 · 450 阅读 · 0 评论 -
encoder-decoder 注意力机制整理名望所
https://blog.csdn.net/kylin_learn/article/details/85124081转载 2020-06-30 15:00:17 · 358 阅读 · 0 评论 -
RNN 要点
h1向量代表了今天h2向量代表了今天 天气h3向量代表了今天 天气很h4向量代表了今天 天气很好原创 2020-06-29 11:57:52 · 155 阅读 · 0 评论 -
注意力机制好文章
https://blog.csdn.net/hpulfc/article/details/80449561转载 2020-06-29 09:09:03 · 161 阅读 · 0 评论 -
ValueError: Duplicate node name in graph: lambda_1/zeros/packed
ValueError: Duplicate node name in graph: 'lambda_1/zeros/packed'C:\Users\pc\AppData\Local\Programs\Python\Python37\python.exe C:/Users/pc/AppData/Local/Temp/helloworld.py/attention.pyUsing TensorFlow backend.Traceback (most recent call last): File ".原创 2020-06-28 16:41:52 · 2679 阅读 · 0 评论 -
浅析文本相似度
https://blog.csdn.net/qq_28031525/article/details/79596376?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase转载 2020-06-27 21:23:11 · 123 阅读 · 0 评论 -
相似度算法之余弦相似度
https://blog.csdn.net/zz_dd_yy/article/details/51926305?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-2.nonecase&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-2.nonecase转载 2020-06-27 21:13:31 · 628 阅读 · 0 评论 -
深度学习的相似度计算 向量之间的相似程度计算 Q K V的注意力权重
https://blog.csdn.net/qq_32797059/article/details/106502737转载 2020-06-27 08:29:00 · 870 阅读 · 0 评论 -
深度学习数学推理
https://www.zhihu.com/question/41459109转载 2020-06-25 16:50:14 · 212 阅读 · 0 评论 -
ATTENTION机制Q K V 理解
https://blog.csdn.net/u013887652/article/details/101062567?utm_medium=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase&depth_1-utm_source=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.none转载 2020-06-24 11:45:07 · 1448 阅读 · 0 评论 -
np.eye()的函数能将一个label数组,大小为(1,m)或者(m,1)的数组,转化成one-hot数组
https://blog.csdn.net/m0_37393514/article/details/81455915转载 2020-06-19 08:14:22 · 192 阅读 · 0 评论 -
谷歌云计算提供容器服务URL
https://cloud.google.com/ai-platform转载 2020-06-17 11:57:06 · 144 阅读 · 0 评论 -
pytorch 一个完整的神经网络训练过程
## TODO: Define your model with dropout addedclass Classifier(nn.Module): def __init__(self): super().__init__() self.fc1 = nn.Linear(784, 256) self.fc2 = nn.Linear(256, 128) self.fc3 = nn.Linear(128, 64) self.f...原创 2020-06-16 13:52:34 · 1571 阅读 · 1 评论 -
Attention机制总结 看明白了的
https://zhuanlan.zhihu.com/p/46313756转载 2020-06-13 16:46:10 · 200 阅读 · 0 评论 -
模型汇总24 - 深度学习中Attention Mechanism详细介绍:原理、分类及应用 知乎
https://zhuanlan.zhihu.com/p/31547842转载 2020-06-12 18:52:11 · 225 阅读 · 0 评论 -
一文搞懂ATTENTION机制
https://blog.csdn.net/xz1308579340/article/details/95330572?utm_medium=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase&depth_1-utm_source=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.non转载 2020-06-12 18:24:21 · 212 阅读 · 0 评论 -
关于《注意力模型--Attention注意力机制》的学习
https://www.jianshu.com/p/e14c6a722381转载 2020-06-12 15:22:33 · 265 阅读 · 0 评论 -
attention机制原理及简单实现
https://www.jianshu.com/p/1d67638139da转载 2020-06-11 21:32:02 · 404 阅读 · 0 评论 -
keras图片增强API
https://keras.io/api/preprocessing/image/转载 2020-05-28 13:04:32 · 169 阅读 · 0 评论 -
图片增强来解决图片不足问题
https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html转载 2020-05-28 13:03:26 · 176 阅读 · 0 评论 -
图片增强深度学习deep learning keras
https://machinelearningmastery.com/image-augmentation-deep-learning-keras/转载 2020-05-28 13:02:06 · 171 阅读 · 0 评论 -
kaggle大赛胜利队博客
https://medium.com/kaggle-blog转载 2020-05-28 08:00:17 · 182 阅读 · 0 评论 -
imdb电影情感分析
https://bbs.huaweicloud.com/blogs/127160转载 2020-05-22 10:42:21 · 835 阅读 · 0 评论 -
力扣AI练习题
https://www.lintcode.com/ai/转载 2020-03-24 16:31:07 · 253 阅读 · 0 评论 -
tensorflow实战google深度学习框架 文档及源码GIT
https://blog.csdn.net/qq_41011336/article/details/84836097?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522158497936519724847058848%2522%252C%2522scm%2522%253A%252220140713.130056874..%2522%25...转载 2020-03-24 00:14:00 · 278 阅读 · 0 评论 -
理解深度学习较好微信专栏
https://mp.weixin.qq.com/mp/homepage?__biz=MzU4NzE2MTgyNQ==&hid=1&sn=38998b0c1784d0f64a6e59bd77331da7&scene=18&devicetype=android-24&version=27000c34&lang=zh_CN&nettype=WIF...转载 2020-03-23 23:20:46 · 144 阅读 · 0 评论 -
机器学习信息熵与信息增益
https://www.jianshu.com/p/69dbb042a0e3转载 2020-03-18 20:09:23 · 266 阅读 · 0 评论