Skip to content

Instantly share code, notes, and snippets.

@dsaint31x

dsaint31x/dl_module_list_dict_sequential.ipynb

Last active May 17, 2024 06:30
Show Gist options
  • Save dsaint31x/f34fcb64f0955a764592edd51628953d to your computer and use it in GitHub Desktop.
Save dsaint31x/f34fcb64f0955a764592edd51628953d to your computer and use it in GitHub Desktop.
Download ZIP
dl_module_list_dict_sequential.ipynb
Display the source blob
Display the rendered blob
Raw
dl_module_list_dict_sequential.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"gpuType": "L4",
"authorship_tag": "ABX9TyOj7EPHVqUR71iuT2XeOmIn",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/dsaint31x/f34fcb64f0955a764592edd51628953d/dl_module_list_dict_sequential.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"source": [
"import torch\n",
"import torch.nn as nn\n",
"\n",
"model = nn.Sequential(\n",
" nn.Linear(10, 20),\n",
" nn.ReLU(),\n",
" nn.Linear(20, 10)\n",
")\n",
"\n",
"print(model)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "iKziq8IWP058",
"outputId": "8b9e9c5e-63d1-441a-8bea-8adbd3b4474b"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Sequential(\n",
" (0): Linear(in_features=10, out_features=20, bias=True)\n",
" (1): ReLU()\n",
" (2): Linear(in_features=20, out_features=10, bias=True)\n",
")\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"import torch\n",
"import torch.nn as nn\n",
"from collections import OrderedDict\n",
"\n",
"model = nn.Sequential(\n",
" OrderedDict({\n",
" 'ds_l0':nn.Linear(10, 20),\n",
" 'ds_act0':nn.ReLU(),\n",
" 'ds_l1':nn.Linear(20, 10),\n",
" })\n",
")\n",
"\n",
"print(model)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "kyFWDY8pOHq6",
"outputId": "6715b963-5f12-48df-d273-243a10f595c1"
},
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Sequential(\n",
" (ds_l0): Linear(in_features=10, out_features=20, bias=True)\n",
" (ds_act0): ReLU()\n",
" (ds_l1): Linear(in_features=20, out_features=10, bias=True)\n",
")\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"import torch\n",
"import torch.nn as nn\n",
"from collections import OrderedDict\n",
"\n",
"model = nn.Sequential(\n",
" OrderedDict([\n",
" ('ds_l0', nn.Linear(10, 20)),\n",
" ('ds_act0',nn.ReLU() ),\n",
" ('ds_l1', nn.Linear(20, 10)),\n",
" ])\n",
")\n",
"\n",
"print(model)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "5L7_bxsFOzXF",
"outputId": "27c45ced-81b4-4756-bb2b-c6a4ba232fe5"
},
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Sequential(\n",
" (ds_l0): Linear(in_features=10, out_features=20, bias=True)\n",
" (ds_act0): ReLU()\n",
" (ds_l1): Linear(in_features=20, out_features=10, bias=True)\n",
")\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"model.ds_l0"
],
"metadata": {
"id": "0UqgKy4jPph6",
"outputId": "a572c8ee-2d43-401f-daf2-8a566ed0faab",
"colab": {
"base_uri": "https://localhost:8080/"
}
},
"execution_count": 4,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"Linear(in_features=10, out_features=20, bias=True)"
]
},
"metadata": {},
"execution_count": 4
}
]
},
{
"cell_type": "code",
"source": [
"import torch\n",
"import torch.nn as nn\n",
"\n",
"class MyModel(nn.Module):\n",
" def __init__(self):\n",
" super(MyModel, self).__init__()\n",
" self.layers = nn.ModuleList([\n",
" nn.Linear(10, 20),\n",
" nn.ReLU(),\n",
" nn.Linear(20, 10)\n",
" ])\n",
"\n",
" def forward(self, x):\n",
" for layer in self.layers:\n",
" x = layer(x)\n",
" return x\n",
"\n",
"model = MyModel()\n",
"print(model)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "VldjbvYVP1mS",
"outputId": "1223b8ba-9b6a-45ae-de1b-fd205fafb39d"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"MyModel(\n",
" (layers): ModuleList(\n",
" (0): Linear(in_features=10, out_features=20, bias=True)\n",
" (1): ReLU()\n",
" (2): Linear(in_features=20, out_features=10, bias=True)\n",
" )\n",
")\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"import torch\n",
"import torch.nn as nn\n",
"\n",
"class MyModel(nn.Module):\n",
" def __init__(self):\n",
" super(MyModel, self).__init__()\n",
" self.layers = nn.ModuleDict({\n",
" 'fc1': nn.Linear(10, 20),\n",
" 'relu': nn.ReLU(),\n",
" 'fc2': nn.Linear(20, 10)\n",
" })\n",
"\n",
" def forward(self, x):\n",
" x = self.layers['fc1'](x)\n",
" x = self.layers['relu'](x)\n",
" x = self.layers['fc2'](x)\n",
" return x\n",
"\n",
"model = MyModel()\n",
"print(model)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "bOj_QrlyP4aW",
"outputId": "835517ac-c71a-4d02-feab-40bc60b4741a"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"MyModel(\n",
" (layers): ModuleDict(\n",
" (fc1): Linear(in_features=10, out_features=20, bias=True)\n",
" (relu): ReLU()\n",
" (fc2): Linear(in_features=20, out_features=10, bias=True)\n",
" )\n",
")\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"import torch\n",
"import torch.nn as nn\n",
"\n",
"class MyModel(nn.Module):\n",
" def __init__(self):\n",
" super(MyModel, self).__init__()\n",
" self.layers = [\n",
" nn.Linear(10, 20),\n",
" nn.ReLU(),\n",
" nn.Linear(20, 10)\n",
" ]\n",
"\n",
" def forward(self, x):\n",
" for layer in self.layers:\n",
" x = layer(x)\n",
" return x\n",
"\n",
"model = MyModel()\n",
"print(model)\n",
"print(\"Model parameters:\", list(model.parameters())) # 파라미터가 추적되지 않음"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "pNpN8LSyP60U",
"outputId": "ad99da24-3716-4047-d070-2b034f06b421"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"MyModel()\n",
"Model parameters: []\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"class MyModel(nn.Module):\n",
" def __init__(self):\n",
" super(MyModel, self).__init__()\n",
" self.layers = [\n",
" nn.Linear(10, 20),\n",
" nn.ReLU(),\n",
" nn.Linear(20, 10)\n",
" ]\n",
"\n",
" def forward(self, x):\n",
" for layer in self.layers:\n",
" x = layer(x)\n",
" return x\n",
"\n",
"model = MyModel()\n",
"model_gpu = model.to('cuda') # 일반 list를 사용하면 GPU로 이동하지 않음"
],
"metadata": {
"id": "gyiwnzWZP9Z4"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"model_gpu"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "cL0yrgqgP_08",
"outputId": "59bbedbb-8a33-4333-9589-2b995e8d9d23"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"MyModel()"
]
},
"metadata": {},
"execution_count": 7
}
]
},
{
"cell_type": "code",
"source": [
"model"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "uC-CGmrKQnya",
"outputId": "1bf68998-d7b7-4880-e6ce-b5423ae73115"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"MyModel()"
]
},
"metadata": {},
"execution_count": 8
}
]
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "C7hVEE3KQpK4"
},
"execution_count": null,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment