Skip to content

Instantly share code, notes, and snippets.

View alisher-ai's full-sized avatar
🏠
Working from home

Alisher Abdulkhaev alisher-ai

🏠
Working from home
View GitHub Profile
@rok
rok / unet_weight_map.py
Last active January 17, 2025 12:42
U-Net weight map generation
%matplotlib inline
import numpy as np
from skimage.io import imshow
from skimage.measure import label
from scipy.ndimage.morphology import distance_transform_edt
def generate_random_circles(n = 100, d = 256):
circles = np.random.randint(0, d, (n, 3))
x = np.zeros((d, d), dtype=int)
@rwightman
rwightman / median_pool.py
Last active August 13, 2024 10:57
PyTorch MedianPool (MedianFilter)
import math
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn.modules.utils import _pair, _quadruple
class MedianPool2d(nn.Module):
""" Median pool (usable as median filter when stride=1) module.
@ikegami-yukino
ikegami-yukino / steps.sh
Last active April 30, 2020 04:24 — forked from albertstartup/steps.sh
aws gpu, ubuntu 16.04, nvidia driver 367, cuda 8,
# Required download
# cudnn-8.0-linux-x64-v5.1.tgz
curl -L -o cuda_8.0.44_linux.run https://developer.nvidia.com/compute/cuda/8.0/prod/local_installers/cuda_8.0.44_linux-run
curl -L -O http://us.download.nvidia.com/XFree86/Linux-x86_64/367.27/NVIDIA-Linux-x86_64-367.27.run
sudo apt-get install build-essential
sudo apt-get install linux-image-extra-`uname -r`
sudo sh cuda_8.0.44_linux.run
echo -e "export CUDA_HOME=/usr/local/cuda\nexport PATH=\$PATH:\$CUDA_HOME/bin\nexport LD_LIBRARY_PATH=\$LD_LINKER_PATH:\$CUDA_HOME/lib64" >> ~/.bashrc
@shagunsodhani
shagunsodhani / CurriculumLearning.md
Created May 8, 2016 17:14
Notes for Curriculum Learning paper

Curriculum Learning

Introduction

  • Curriculum Learning - When training machine learning models, start with easier subtasks and gradually increase the difficulty level of the tasks.
  • Motivation comes from the observation that humans and animals seem to learn better when trained with a curriculum like a strategy.
  • Link to the paper.

Contributions of the paper