guweigang

git init                                                  # 初始化本地git仓库（创建新仓库）
git config --global user.name "xxx"                       # 配置用户名
git config --global user.email "[email protected]"              # 配置邮件
git config --global color.ui true                         # git status等命令自动着色
git config --global color.status auto
git config --global color.diff auto
git config --global color.branch auto
git config --global color.interactive auto
git config --global --unset http.proxy                    # remove  proxy configuration on git
git clone git+ssh://[email protected]/VT.git             # clone远程仓库

fmder

import numpy
from scipy.ndimage.interpolation import map_coordinates
from scipy.ndimage.filters import gaussian_filter

def elastic_transform(image, alpha, sigma, random_state=None):
    """Elastic deformation of images as described in [Simard2003]_.


    .. [Simard2003] Simard, Steinkraus and Platt, "Best Practices for
       Convolutional Neural Networks applied to Visual Document Analysis", in

chsasank

import numpy as np
from scipy.ndimage.interpolation import map_coordinates
from scipy.ndimage.filters import gaussian_filter

def elastic_transform(image, alpha, sigma, random_state=None):
    """Elastic deformation of images as described in [Simard2003]_.


    .. [Simard2003] Simard, Steinkraus and Platt, "Best Practices for
       Convolutional Neural Networks applied to Visual Document Analysis", in

nasimrahaman

import torch
import torch.nn as nn


def log_sum_exp(x):
    # See implementation detail in
    # http://timvieira.github.io/blog/post/2014/02/11/exp-normalize-trick/
    # b is a shift factor. see link.
    # x.size() = [N, C]:
    b, _ = torch.max(x, 1)

bmabey

"""
Functions that implement some of the same functionality found in Matlab's bwmorph.

`thin` - was taken and adapted from https://gist.github.com/joefutrelle/562f25bbcf20691217b8
`spur` - Not perfect but pretty close to what matlab does via LUTs
`endpoints` - lines up perfectly with matlab's output (in my limited testing)
`branches` - this results in more clustered pixels than matlab's version but it pretty close
"""
import numpy as np
import scipy.ndimage as ndi

jeremyjordan

def soft_dice_loss(y_true, y_pred, epsilon=1e-6): 
    ''' 
    Soft dice loss calculation for arbitrary batch size, number of classes, and number of spatial dimensions.
    Assumes the `channels_last` format.
  
    # Arguments
        y_true: b x X x Y( x Z...) x c One hot encoding of ground truth
        y_pred: b x X x Y( x Z...) x c Network output, must sum to 1 over c channel (such as after softmax) 
        epsilon: Used for numerical stability to avoid divide by zero errors
    

jinglescode

import torch
import torch.nn as nn

class conv_block_nested(nn.Module):

    def __init__(self, in_ch, mid_ch, out_ch):
        super(conv_block_nested, self).__init__()
        self.activation = nn.ReLU(inplace=True)
        self.conv1 = nn.Conv2d(in_ch, mid_ch, kernel_size=3, padding=1, bias=True)
        self.bn1 = nn.BatchNorm2d(mid_ch)

TengdaHan

Multi-node-training on slurm with PyTorch

What's this?

• A simple note for how to start multi-node-training on slurm scheduler with PyTorch.
• Useful especially when scheduler is too busy that you cannot get multiple GPUs allocated, or you need more than 4 GPUs for a single job.
• Requirement: Have to use PyTorch DistributedDataParallel(DDP) for this purpose.
• Warning: might need to re-factor your own code.
• Warning: might be secretly condemned by your colleagues because using too many GPUs.