- 博客(8)
- 收藏
- 关注
原创 论文笔记A Neural Conversational Model
Abstract1.Previous approaches often restrict to specific domains and require handcrafted rules.2.Use the Sequence to Sequence frame work.3.The strength of the model that it can be trained end-to-end and thus requires much fewer hand-crafted rules.4. Th
2020-08-03 20:38:23 287
原创 论文笔记-Personalizing Dialogue Agents: I have a dog, do you have pets too?
Abstract1.闲聊机器人存在的问题:The lack of specificity,do not display a consistent personality and are often captivating.2.文章所做的工作By the given profile information and the information about the person they are talking to predict the utterance predictionIntroduct
2020-08-03 12:41:32 591
原创 win10+cuda9.0+cudnn7.6.5 for cuda9.0+torch1.0
1.#检查cuda的安装情况nvcc --version2.将cudnn中的库文件移动到cuda的文件夹中3.#检查cudnn,跑demo程序,两个PASS4.#cuda9.0conda install pytorch1.0.0 torchvision0.2.1 cuda90 -c pytorch5.#添加源conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/...
2020-06-26 15:23:59 639
原创 CNN的实现
CNN神经网络的实现卷积层的实现class Convolution: def __init__(self, W, b, stride=1, pad=0): self.W = W self.b = b self.stride = stride self.pad = pad # 中间数据(ba...
2020-01-22 21:36:06 296
原创 神经网络的实现
1.生成numpy数组# np.arry()接收列表作为参数x = np.array([1.0,2.0,3.0])print(x)2.numpy的算数运算# np.arry()接收列表作为参数x = np.array([1.0,2.0,3.0])y = np.array([4.0,5.0,6.0])# x + y = [5. 7. 9.]# x + 2 = ..# x - ...
2020-01-16 23:08:28 727 1
原创 Anaconda包管理
在conda install不能用之后用pip的操作。新建环境操作跟之前的都一样,用pip install --target制定目录下载管理。
2020-01-01 21:28:54 102
原创 Django实践-安装
Django实践-安装文前说两句Django的安装文前说两句最近在写毕业设计,准备给问答机器人加一个前端。有两种解决的办法,第一种是把Python封装成resful api接口,还有一种方法就是用Django框架,考虑到后期有可能还会做类似的工作,所以选择了Django框架,学习ing…Django的安装https://www.runoob.com/django/django-instal...
2019-12-31 09:45:00 109
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人