Skip to content

Instantly share code, notes, and snippets.

View aowal's full-sized avatar

Md Abdul Aowal aowal

31 followers · 291 following
  • UMass Amherst
  • Amherst, Massachusetts
View GitHub Profile
@N-McA
N-McA / keras_spatial_bias.py
Last active November 13, 2019 19:15
Concatenates the (x, y) coordinate normalised to 0-1 to each spatial location in the image. Allows a network to learn spatial bias. Has been explored in at least one paper, "An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution" https://arxiv.org/abs/1807.03247
import keras.backend as kb
from keras.layers import Layer
def _kb_linspace(num):
num = kb.cast(num, kb.floatx())
return kb.arange(0, num, dtype=kb.floatx()) / (num - 1)
def _kb_grid_coords(width, height):
w, h = width, height
@eamartin
eamartin / notebook.ipynb
Last active November 6, 2022 18:53
Understanding & Visualizing Self-Normalizing Neural Networks
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@mjdietzx
mjdietzx / residual_network.py
Last active March 26, 2024 06:33
Clean and simple Keras implementation of residual networks (ResNeXt and ResNet) accompanying accompanying Deep Residual Learning: https://blog.waya.ai/deep-residual-learning-9610bb62c355.
"""
Clean and simple Keras implementation of network architectures described in:
- (ResNet-50) [Deep Residual Learning for Image Recognition](https://arxiv.org/pdf/1512.03385.pdf).
- (ResNeXt-50 32x4d) [Aggregated Residual Transformations for Deep Neural Networks](https://arxiv.org/pdf/1611.05431.pdf).
Python 3.
"""
from keras import layers
from keras import models
@bartolsthoorn
bartolsthoorn / multilabel_example.py
Created April 29, 2017 12:13
Simple multi-laber classification example with Pytorch and MultiLabelSoftMarginLoss (https://en.wikipedia.org/wiki/Multi-label_classification)
import torch
import torch.nn as nn
import numpy as np
import torch.optim as optim
from torch.autograd import Variable
# (1, 0) => target labels 0+2
# (0, 1) => target labels 1
# (1, 1) => target labels 3
train = []
@panovr
panovr / finetune.py
Created March 2, 2017 23:04
Fine-tuning pre-trained models with PyTorch
import argparse
import os
import shutil
import time
import torch
import torch.nn as nn
import torch.nn.parallel
import torch.backends.cudnn as cudnn
import torch.optim
@wassname
wassname / keras_weighted_categorical_crossentropy.py
Last active December 19, 2023 18:17
Keras weighted categorical_crossentropy (please read comments for updated version)
"""
A weighted version of categorical_crossentropy for keras (2.0.6). This lets you apply a weight to unbalanced classes.
@url: https://gist.github.com/wassname/ce364fddfc8a025bfab4348cf5de852d
@author: wassname
"""
from keras import backend as K
def weighted_categorical_crossentropy(weights):
"""
A weighted version of keras.objectives.categorical_crossentropy
@iamtekeste
iamtekeste / Download Google Drive files with WGET
Created July 8, 2015 11:00
Download Google Drive files with WGET
Download Google Drive files with WGET
Example Google Drive download link:
https://docs.google.com/open?id=[ID]
To download the file with WGET you need to use this link:
https://googledrive.com/host/[ID]
Example WGET command:
@bsweger
bsweger / useful_pandas_snippets.md
Last active April 19, 2024 18:04
Useful Pandas Snippets

Useful Pandas Snippets

A personal diary of DataFrame munging over the years.

Data Types and Conversion

Convert Series datatype to numeric (will error if column has non-numeric values)
(h/t @makmanalp)

@endolith
endolith / output.png
Last active July 26, 2024 00:06
Detecting rotation and line spacing of image of page of text using Radon transform
output.png
@optikalefx
optikalefx / Super Simple Ajax File Upload (XHR2).js
Last active April 4, 2021 15:12
Ajax File upload with jQuery and XHR2Sean Clark http://square-bracket.com
// Ajax File upload with jQuery and XHR2
// Sean Clark http://square-bracket.com
// xhr2 file upload
$.fn.upload = function(remote, data, successFn, progressFn) {
// if we dont have post data, move it along
if (typeof data != "object") {
progressFn = successFn;
successFn = data;
}