Created
December 11, 2019 22:39
-
-
Save f0nzie/2b3edad1c6ea92147852f0248ee0b13e to your computer and use it in GitHub Desktop.
backward pytorch
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"nbformat": 4, | |
"nbformat_minor": 0, | |
"metadata": { | |
"colab": { | |
"name": "backward pytorch", | |
"provenance": [], | |
"collapsed_sections": [], | |
"include_colab_link": true | |
}, | |
"kernelspec": { | |
"name": "python3", | |
"display_name": "Python 3" | |
} | |
}, | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "view-in-github", | |
"colab_type": "text" | |
}, | |
"source": [ | |
"<a href=\"https://colab.research.google.com/gist/f0nzie/2b3edad1c6ea92147852f0248ee0b13e/backward-pytorch.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "eFuj7UjM65J6", | |
"colab_type": "code", | |
"colab": {} | |
}, | |
"source": [ | |
"import torch\n", | |
"import numpy as np " | |
], | |
"execution_count": 0, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "EpbLnkLsEpHl", | |
"colab_type": "text" | |
}, | |
"source": [ | |
"## Example 2" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "ToFuUaMr6-3T", | |
"colab_type": "code", | |
"outputId": "b4a8a9c0-6341-482b-cbce-765a036438da", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 197 | |
} | |
}, | |
"source": [ | |
"x = np.arange(1,3,1)\n", | |
"x = torch.from_numpy(x).reshape(len(x), 1)\n", | |
"x = x.float()\n", | |
"x.requires_grad = True\n", | |
"print(x)\n", | |
"w = torch.randn((2,2), requires_grad = True)\n", | |
"print(w)\n", | |
"y = w @ x\n", | |
"print(y)\n", | |
"\n", | |
"# Compute gradients of w1 . x\n", | |
"y[0].backward(retain_graph=True)\n", | |
"print(w.grad)\n", | |
"# tensor([[1., 2.],\n", | |
"# [0., 0.]])\n", | |
"y[1].backward(retain_graph=True)\n", | |
"print(w.grad)" | |
], | |
"execution_count": 2, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"text": [ | |
"tensor([[1.],\n", | |
" [2.]], requires_grad=True)\n", | |
"tensor([[ 0.6973, -1.5348],\n", | |
" [-2.6904, -0.4845]], requires_grad=True)\n", | |
"tensor([[-2.3724],\n", | |
" [-3.6594]], grad_fn=<MmBackward>)\n", | |
"tensor([[1., 2.],\n", | |
" [0., 0.]])\n", | |
"tensor([[1., 2.],\n", | |
" [1., 2.]])\n" | |
], | |
"name": "stdout" | |
} | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "Wywcl4g7EX6g", | |
"colab_type": "text" | |
}, | |
"source": [ | |
"## Example 2" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "lyKAHyp46_Hk", | |
"colab_type": "code", | |
"outputId": "604fd646-12cd-49f8-83c2-6eab0b4c8175", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 197 | |
} | |
}, | |
"source": [ | |
"# From an example on linear regression\n", | |
"x = np.arange(1,16,1)\n", | |
"x = torch.from_numpy(x)\n", | |
"x = x.float()\n", | |
"x = x.view(-1, 3)\n", | |
"x.requires_grad = True # torch.Size([5, 3])\n", | |
"print(x)\n", | |
"# w represents the weights and y the model. very, very simple example\n", | |
"w = torch.randn((5, 5), requires_grad = True)\n", | |
"y = w @ x\n", | |
"print(y)" | |
], | |
"execution_count": 3, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"text": [ | |
"tensor([[ 1., 2., 3.],\n", | |
" [ 4., 5., 6.],\n", | |
" [ 7., 8., 9.],\n", | |
" [10., 11., 12.],\n", | |
" [13., 14., 15.]], requires_grad=True)\n", | |
"tensor([[-1.9718, -1.9902, -2.0085],\n", | |
" [ 0.4344, 0.8532, 1.2720],\n", | |
" [11.7566, 12.0687, 12.3809],\n", | |
" [39.5736, 45.3092, 51.0447],\n", | |
" [-6.0419, -6.4095, -6.7770]], grad_fn=<MmBackward>)\n" | |
], | |
"name": "stdout" | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "oNnt1Z4nF9Do", | |
"colab_type": "code", | |
"outputId": "3dc53689-1f8b-4d2f-afeb-f81442c7e9ba", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 107 | |
} | |
}, | |
"source": [ | |
"y[0,0].backward(retain_graph=True) # this computes the derivative\n", | |
"w.grad" | |
], | |
"execution_count": 4, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": [ | |
"tensor([[ 1., 4., 7., 10., 13.],\n", | |
" [ 0., 0., 0., 0., 0.],\n", | |
" [ 0., 0., 0., 0., 0.],\n", | |
" [ 0., 0., 0., 0., 0.],\n", | |
" [ 0., 0., 0., 0., 0.]])" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 4 | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "g0uthKUaHJZG", | |
"colab_type": "code", | |
"outputId": "bf0b3f74-edf1-4852-8149-eec4d032d71d", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 107 | |
} | |
}, | |
"source": [ | |
"y[0,1].backward(retain_graph=True) # this computes\n", | |
"w.grad" | |
], | |
"execution_count": 5, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": [ | |
"tensor([[ 3., 9., 15., 21., 27.],\n", | |
" [ 0., 0., 0., 0., 0.],\n", | |
" [ 0., 0., 0., 0., 0.],\n", | |
" [ 0., 0., 0., 0., 0.],\n", | |
" [ 0., 0., 0., 0., 0.]])" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 5 | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "iWUqFCMCIyYg", | |
"colab_type": "code", | |
"outputId": "e948e4a0-509a-411b-f3a8-ece497b90d6f", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 107 | |
} | |
}, | |
"source": [ | |
"\n", | |
"y[1,1].backward(retain_graph=True) # this doesn't\n", | |
"w.grad.data" | |
], | |
"execution_count": 10, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": [ | |
"tensor([[ 3., 9., 15., 21., 27.],\n", | |
" [ 8., 20., 32., 44., 56.],\n", | |
" [ 3., 6., 9., 12., 15.],\n", | |
" [ 0., 0., 0., 0., 0.],\n", | |
" [ 0., 0., 0., 0., 0.]])" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 10 | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "ekJdNRXNI-h0", | |
"colab_type": "code", | |
"outputId": "ad0dfe31-4058-4b72-ba01-cb9ed5995f8f", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 107 | |
} | |
}, | |
"source": [ | |
"# this doesn't compute any derivative\n", | |
"y[2,2].backward(retain_graph=True)\n", | |
"w.grad" | |
], | |
"execution_count": 7, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": [ | |
"tensor([[ 3., 9., 15., 21., 27.],\n", | |
" [ 2., 5., 8., 11., 14.],\n", | |
" [ 3., 6., 9., 12., 15.],\n", | |
" [ 0., 0., 0., 0., 0.],\n", | |
" [ 0., 0., 0., 0., 0.]])" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 7 | |
} | |
] | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment