Skip to content

Instantly share code, notes, and snippets.


Mirodil Mirodil

View GitHub Profile
Mirodil /
Last active May 10, 2018
FileListIterator for keras
import numpy as np
from keras import backend as K
from keras.preprocessing.image import Iterator, load_img, img_to_array
class FileListIterator(Iterator):
"""Iterator capable of reading images from an array of the filenames.
# Arguments
filenames: Path to the directory to read images from.
Each subdirectory in this directory will be
considered to contain images from one class,
Mirodil /
Last active Dec 14, 2018
LearningRateFinder for keras
class LearningRateFinder(Callback):
This callback implements a learning rate finder(LRF)
The learning rate is constantly increased during training.
On training end, the training loss is plotted against the learning rate.
One may choose a learning rate for a model based on the given graph,
selecting a value slightly before the minimal training loss.
# Example
lrf = LearningRateFinder([0.0001, 0.0005, 0.001, 0.005, 0.01, 0.05]), y_train, epochs=1, batch_size=128, callbacks=[lrf])
sbugallo /
Created Jan 23, 2018
ResNeXt 101 for MRCNN
from keras.layers import Conv2D
from keras.layers import Activation
from keras.layers import Add
from keras.layers import BatchNormalization
from keras.layers import ZeroPadding2D
from keras.layers import MaxPooling2D
def identity_block(input_tensor, kernel_size, filters, stage, block, use_bias=True):
This block is the one with no convolutional layer at its shortcut branch
gilrosenthal / install script
Created Jul 4, 2018 Install on Google Colab
View install script
!pip install fastai
!apt-get -qq install -y libsm6 libxext6 && pip install -q -U opencv-python
import cv2
from os import path
from wheel.pep425tags import get_abbr_impl, get_impl_ver, get_abi_tag
platform = '{}{}-{}'.format(get_abbr_impl(), get_impl_ver(), get_abi_tag())
accelerator = 'cu80' if path.exists('/opt/bin/nvidia-smi') else 'cpu'
!pip install -q{accelerator}/torch-0.3.0.post4-{platform}-linux_x86_64.whl torchvision
trevnorris /
Last active Jul 21, 2021
Quick steps of how to create a flame graph using perf

The will setup the latest Node and install the latest perf version on your Linux box.

When you want to generate the flame graph, run the following (folder locations taken from install script):

sudo sysctl kernel.kptr_restrict=0
# May also have to do the following:
# (additional reading )
sudo sysctl kernel.perf_event_paranoid=0
jeremyjordan /
Last active Sep 20, 2021
Keras Callback for implementing Stochastic Gradient Descent with Restarts
from keras.callbacks import Callback
import keras.backend as K
import numpy as np
class SGDRScheduler(Callback):
'''Cosine annealing learning rate scheduler with periodic restarts.
# Usage
schedule = SGDRScheduler(min_lr=1e-5,
View Orthonormal init and LSUV.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
'''This script goes along the blog post
"Building powerful image classification models using very little data"
It uses data that can be downloaded at:
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats