Skip to content
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.

Commit 70a1ba1

Browse files
committedMay 24, 2021
Alternative to using itertools, split train data in half and combine halves
In the ab-split notebook I partition the training data in half A, half B and then I put them together. This means I am left with 20k observations and every training image is used The same is done for the validation data and will be done for the training data Turns out this is not working so well
1 parent fcfe5fc commit 70a1ba1

7 files changed

+3031
-53
lines changed
 
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
{
2+
"cells": [],
3+
"metadata": {},
4+
"nbformat": 4,
5+
"nbformat_minor": 4
6+
}

‎.ipynb_checkpoints/random-sample-checkpoint.ipynb

+671
Large diffs are not rendered by default.

‎.ipynb_checkpoints/split-AB-checkpoint.ipynb

+739
Large diffs are not rendered by default.

‎Untitled.ipynb

+45
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,45 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": null,
6+
"metadata": {},
7+
"outputs": [],
8+
"source": [
9+
"import itertools\n",
10+
"import numpy as np\n",
11+
"num_images = 20000\n",
12+
"index_list = np.linspace(0,num_images-1,num_images).astype(int)\n",
13+
"image_combinations = list(itertools.combinations(index_list, 2))"
14+
]
15+
},
16+
{
17+
"cell_type": "code",
18+
"execution_count": null,
19+
"metadata": {},
20+
"outputs": [],
21+
"source": []
22+
}
23+
],
24+
"metadata": {
25+
"kernelspec": {
26+
"display_name": "Python 3",
27+
"language": "python",
28+
"name": "python3"
29+
},
30+
"language_info": {
31+
"codemirror_mode": {
32+
"name": "ipython",
33+
"version": 3
34+
},
35+
"file_extension": ".py",
36+
"mimetype": "text/x-python",
37+
"name": "python",
38+
"nbconvert_exporter": "python",
39+
"pygments_lexer": "ipython3",
40+
"version": "3.8.6"
41+
}
42+
},
43+
"nbformat": 4,
44+
"nbformat_minor": 4
45+
}

‎cross-validation.ipynb

+129-53
Large diffs are not rendered by default.

‎random-sample.ipynb

+739
Large diffs are not rendered by default.

‎split-AB.ipynb

+702
Large diffs are not rendered by default.

0 commit comments

Comments
 (0)
Please sign in to comment.