Skip to content

Instantly share code, notes, and snippets.

View kenji0x02's full-sized avatar

Kenji kenji0x02

  • Japan
View GitHub Profile
@andreyryabtsev
andreyryabtsev / backmatting.ipynb
Last active January 29, 2026 13:02
BackMatting.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@andrewjong
andrewjong / pytorch_image_folder_with_file_paths.py
Last active October 31, 2024 11:13
PyTorch Image File Paths With Dataset Dataloader
import torch
from torchvision import datasets
class ImageFolderWithPaths(datasets.ImageFolder):
"""Custom dataset that includes image file paths. Extends
torchvision.datasets.ImageFolder
"""
# override the __getitem__ method. this is the method that dataloader calls
def __getitem__(self, index):
@jeremyjordan
jeremyjordan / sgdr.py
Last active December 4, 2023 13:41
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
```python
schedule = SGDRScheduler(min_lr=1e-5,
import numpy as np
from keras import backend as K
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.preprocessing.image import ImageDataGenerator
from sklearn.metrics import classification_report, confusion_matrix
#Start
train_data_path = 'F://data//Train'
@fchollet
fchollet / classifier_from_little_data_script_3.py
Last active February 26, 2025 01:37
Fine-tuning a Keras model. Updated to the Keras 2.0 API.
'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
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
@fchollet
fchollet / classifier_from_little_data_script_1.py
Last active February 18, 2026 04:59
Updated to the Keras 2.0 API.
'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
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
@kariyayo
kariyayo / 00_すごいHaskellたのしく学ぼう!をScalaでやってみたメモ.md
Last active December 14, 2019 11:00
すごいHaskellたのしく学ぼう!をScalaでやってみたメモ
@hayajo
hayajo / 00.md
Last active March 8, 2020 16:05
NDS#36 Go言語入門

sublime text 2

http://www.sublimetext.com/
Total: USD $70 ちょっと値上がってましたね。。

  • クロスプラットフォーム
    • windows
    • mac
    • linux
@juno
juno / github-flow.ja.md
Last active April 9, 2021 02:20
GitHub Flow (Japanese translation) Latest version is here: https://gist.github.com/Gab-km/3705015

GitHub Flow

31 Aug 2011

git-flowの問題点 (Issues with git-flow)

私は人々にGitを教えるためにあちこちを飛び回っているが、最近のほぼすべてのクラスやワークショップでgit-flowについてどう思うかを尋ねられた。私はいつも、git-flowは素晴らしいと思うと答えている。何百万ものワークフローを持ったシステム(Git)を提供し、ドキュメントもあるし、よくテストされている。フレキシブルなワークフローは、実に容易なやり方で多くの開発者の役に立つ。標準的なものになりつつあり、開発者はプロジェクトや企業の間を移動しつつこの標準的なワークフローに馴染むことができる。