Skip to content

Instantly share code, notes, and snippets.

View MannyKayy's full-sized avatar

Emmanuel Kahembwe MannyKayy

65 followers · 410 following
View GitHub Profile
@MannyKayy
MannyKayy / Dockerfile
Last active January 25, 2018 12:04
ChainerMN Dockerfile
FROM nvidia/cuda:8.0-cudnn6-devel-ubuntu14.04
RUN apt-get update
# disable interactive functions
ENV DEBIAN_FRONTEND noninteractive
#################Install MiniConda and other dependencies##########
ENV CONDA_DIR /opt/conda
@MannyKayy
MannyKayy / fc_densenet.py
Created June 8, 2017 16:12 — forked from felixgwu/fc_densenet.py
FC-DenseNet Implementation in PyTorch
import torch
from torch import nn
__all__ = ['FCDenseNet', 'fcdensenet_tiny', 'fcdensenet56_nodrop',
'fcdensenet56', 'fcdensenet67', 'fcdensenet103',
'fcdensenet103_nodrop']
class DenseBlock(nn.Module):
@MannyKayy
MannyKayy / treernn.py
Created June 8, 2017 16:13 — forked from felixgwu/treernn.py
Pytorch TreeRNN
"""
TreeLSTM[1] implementation in Pytorch
Based on dynet benchmarks :
https://github.com/neulab/dynet-benchmark/blob/master/dynet-py/treenn.py
https://github.com/neulab/dynet-benchmark/blob/master/chainer/treenn.py
Other References:
https://github.com/pytorch/examples/tree/master/word_language_model
https://github.com/pfnet/chainer/blob/29c67fe1f2140fa8637201505b4c5e8556fad809/chainer/functions/activation/slstm.py
https://github.com/stanfordnlp/treelstm
@MannyKayy
MannyKayy / using chainercv and chainermn together
Last active June 9, 2017 12:33
This code doesn't run. pickle and mpi related error
#!/usr/bin/env python
from __future__ import print_function
import argparse
import chainer
import chainer.functions as F
import chainer.links as L
from chainer import training
from chainer.training import extensions
@MannyKayy
MannyKayy / detect.py
Created October 15, 2017 21:25 — forked from Lukse/detect.py
Advanced OpenCV 3 python hole detection
import cv2
import sys
import numpy as np
camera = cv2.VideoCapture("video.avi")
# Setup BlobDetector
detector = cv2.SimpleBlobDetector_create()
params = cv2.SimpleBlobDetector_Params()
@MannyKayy
MannyKayy / tied_weight_ae.py
Created October 17, 2017 18:50 — forked from delta2323/tied_weight_ae.py
Chainer example of Tied-weight Autoencoder (Autoencoder with sharing weights)
import chainer
import chainer.functions as F
from chainer import initializers as I
from chainer import reporter
from chainer import training
from chainer.training import extensions as E
import numpy
import scipy.misc
@MannyKayy
MannyKayy / convolutional_autoencoder.py
Created October 17, 2017 18:50 — forked from delta2323/convolutional_autoencoder.py
class ConvolutionalAutoEncoder(chainer.Chain):
def __init__(self):
super(ConvolutionalAutoEncoder).__init__(
c1=L.Convolution2D(...),
c2=L.Convolution2D(...),
dc1=L.Deconvolution2D(...),
dc2=L.Deconvolution2D(...),
)
def convolve(self, x):
@MannyKayy
MannyKayy / gaussian-processes-1.ipynb
Created December 18, 2017 00:16 — forked from abridgland/gaussian-processes-1.ipynb
A Jupyter notebook to accompany Intro to Gaussian Processes - Part I at http://bridg.land/posts/gaussian-processes-1
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@MannyKayy
MannyKayy / gaussian-processes-1.ipynb
Created December 18, 2017 00:16 — forked from abridgland/gaussian-processes-1.ipynb
A Jupyter notebook to accompany Intro to Gaussian Processes - Part I at http://bridg.land/posts/gaussian-processes-1
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@MannyKayy
MannyKayy / chainercv_detection_and_semantic_segmentation.py
Created December 20, 2017 15:34 — forked from yuyu2172/chainercv_detection_and_semantic_segmentation.py
import os
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec
import chainer
from chainercv.datasets import cityscapes_semantic_segmentation_label_colors
from chainercv.datasets import cityscapes_semantic_segmentation_label_names
from chainercv.datasets import voc_bbox_label_names