toolkit for project
解决git指令更新远程仓库github时每次都要输入用户名和密码问题
导出已有环境：conda env export > environment.yaml
将environment.yaml文件复制到新主机上之后根据索引文件创建并恢复虚拟环境：conda env create -n your
...
DL_GANs
BasicThe idea behind GANs is that you have two networks, a generator 𝐺 and a discriminator 𝐷 , competing against each other. The generator makes
...
posts_supplement
发表于
|
更新于:
|
字数统计:
10
|
阅读次数:
Transform learning
Convolutional Autoencoder: Transpose convolution
Convolutional Autoencoder：Upsampleing + Convolutions
CNNs
OverviewImage Classification Steps
General Steps
the advantage of CNNs
MLPs && CNNs：Fully connected && Local connected
Local conn
...
Notes of Manipulation class
Matlab Coding输出
fprintf('...')：输出字符；
提取数组、矩阵中元素1$ a = A(1); b = B(:,1)
矩阵运算：点乘、逆、转置、行列式1234$ ans = dot(a,b)$ ans = inv(T)$ ans = T'$ ans
...
RNN&&LSTM
RNN理解RNN内部
我们可以用前馈神经网络（FFNNs）那样去理解
Backpropagation through time(BPTT)
For n-layers, can check here
LSTMWord EmbeddingsBasic
Reduce the di
...
Data processing with numpy or pytorch
发表于
|
更新于:
|
字数统计:
322
|
阅读次数:
NumpyNumpy从数值范围创建数组：arange()、linspace()、logsapce()
numpy.arange(start=0, stop, step=1, dtype): start 与 stop 指定的范围以及 step 设定的步长，生成一个 ndarray,不包含stop值；
...
Deep learning in Pytorch
ArchitecturesUtility toolcheck weights or bias
通过print model.state_dict()或model.named_parameters()查看所有参数，信息包括name和params，然后使用点运算符.查看相应的参数；
通过官网查看相应网络模
...