540 lines
399 KiB
Plaintext
540 lines
399 KiB
Plaintext
|
{
|
|||
|
|
"nbformat": 4,
|
|||
|
|
"nbformat_minor": 0,
|
|||
|
|
"metadata": {
|
|||
|
|
"colab": {
|
|||
|
|
"name": "Image_super_resolution_using_SRGAN.ipynb",
|
|||
|
|
"provenance": [],
|
|||
|
|
"include_colab_link": true
|
|||
|
|
},
|
|||
|
|
"kernelspec": {
|
|||
|
|
"name": "python3",
|
|||
|
|
"display_name": "Python 3"
|
|||
|
|
},
|
|||
|
|
"accelerator": "GPU"
|
|||
|
|
},
|
|||
|
|
"cells": [
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {
|
|||
|
|
"id": "view-in-github",
|
|||
|
|
"colab_type": "text"
|
|||
|
|
},
|
|||
|
|
"source": [
|
|||
|
|
"<a href=\"https://colab.research.google.com/github/PacktPublishing/Hands-On-Computer-Vision-with-PyTorch/blob/master/Chapter13/Image_super_resolution_using_SRGAN.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"id": "vXvKdQgrg8WI",
|
|||
|
|
"outputId": "17592253-82e6-48cd-816e-49d6d05f0f64",
|
|||
|
|
"colab": {
|
|||
|
|
"base_uri": "https://localhost:8080/",
|
|||
|
|
"height": 90
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"source": [
|
|||
|
|
"import os\n",
|
|||
|
|
"if not os.path.exists('srgan.pth.tar'):\n",
|
|||
|
|
" !pip install -q torch_snippets\n",
|
|||
|
|
" !wget -q https://raw.githubusercontent.com/sizhky/a-PyTorch-Tutorial-to-Super-Resolution/master/models.py -O models.py\n",
|
|||
|
|
" from pydrive.auth import GoogleAuth\n",
|
|||
|
|
" from pydrive.drive import GoogleDrive\n",
|
|||
|
|
" from google.colab import auth\n",
|
|||
|
|
" from oauth2client.client import GoogleCredentials\n",
|
|||
|
|
"\n",
|
|||
|
|
" auth.authenticate_user()\n",
|
|||
|
|
" gauth = GoogleAuth()\n",
|
|||
|
|
" gauth.credentials = GoogleCredentials.get_application_default()\n",
|
|||
|
|
" drive = GoogleDrive(gauth)\n",
|
|||
|
|
"\n",
|
|||
|
|
" downloaded = drive.CreateFile({'id': '1_PJ1Uimbr0xrPjE8U3Q_bG7XycGgsbVo'})\n",
|
|||
|
|
" downloaded.GetContentFile('srgan.pth.tar')\n",
|
|||
|
|
" from torch_snippets import *\n",
|
|||
|
|
" device = 'cuda' if torch.cuda.is_available() else 'cpu'"
|
|||
|
|
],
|
|||
|
|
"execution_count": null,
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"\u001b[K |████████████████████████████████| 61kB 9.3MB/s \n",
|
|||
|
|
"\u001b[K |████████████████████████████████| 36.7MB 81kB/s \n",
|
|||
|
|
"\u001b[K |████████████████████████████████| 102kB 12.3MB/s \n",
|
|||
|
|
"\u001b[?25h Building wheel for contextvars (setup.py) ... \u001b[?25l\u001b[?25hdone\n"
|
|||
|
|
],
|
|||
|
|
"name": "stdout"
|
|||
|
|
}
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"id": "3Wzd705WhDx7",
|
|||
|
|
"outputId": "21c43f37-72d3-4859-80e2-c8cb0ea11a8a",
|
|||
|
|
"colab": {
|
|||
|
|
"base_uri": "https://localhost:8080/",
|
|||
|
|
"height": 1000
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"source": [
|
|||
|
|
"model = torch.load('srgan.pth.tar', map_location='cpu')['generator'].to(device)\n",
|
|||
|
|
"model.eval()"
|
|||
|
|
],
|
|||
|
|
"execution_count": null,
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"/usr/local/lib/python3.6/dist-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.container.Sequential' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.\n",
|
|||
|
|
" warnings.warn(msg, SourceChangeWarning)\n",
|
|||
|
|
"/usr/local/lib/python3.6/dist-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.conv.Conv2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.\n",
|
|||
|
|
" warnings.warn(msg, SourceChangeWarning)\n",
|
|||
|
|
"/usr/local/lib/python3.6/dist-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.activation.PReLU' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.\n",
|
|||
|
|
" warnings.warn(msg, SourceChangeWarning)\n",
|
|||
|
|
"/usr/local/lib/python3.6/dist-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.batchnorm.BatchNorm2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.\n",
|
|||
|
|
" warnings.warn(msg, SourceChangeWarning)\n",
|
|||
|
|
"/usr/local/lib/python3.6/dist-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.pixelshuffle.PixelShuffle' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.\n",
|
|||
|
|
" warnings.warn(msg, SourceChangeWarning)\n",
|
|||
|
|
"/usr/local/lib/python3.6/dist-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.activation.Tanh' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.\n",
|
|||
|
|
" warnings.warn(msg, SourceChangeWarning)\n",
|
|||
|
|
"/usr/local/lib/python3.6/dist-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.activation.LeakyReLU' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.\n",
|
|||
|
|
" warnings.warn(msg, SourceChangeWarning)\n",
|
|||
|
|
"/usr/local/lib/python3.6/dist-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.pooling.AdaptiveAvgPool2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.\n",
|
|||
|
|
" warnings.warn(msg, SourceChangeWarning)\n",
|
|||
|
|
"/usr/local/lib/python3.6/dist-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.linear.Linear' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.\n",
|
|||
|
|
" warnings.warn(msg, SourceChangeWarning)\n"
|
|||
|
|
],
|
|||
|
|
"name": "stderr"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"output_type": "execute_result",
|
|||
|
|
"data": {
|
|||
|
|
"text/plain": [
|
|||
|
|
"Generator(\n",
|
|||
|
|
" (net): SRResNet(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(3, 64, kernel_size=(9, 9), stride=(1, 1), padding=(4, 4))\n",
|
|||
|
|
" (1): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (residual_blocks): Sequential(\n",
|
|||
|
|
" (0): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (1): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (2): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (3): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (4): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (5): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (6): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (7): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (8): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (9): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (10): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (11): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (12): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (13): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (14): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (15): ResidualBlock(\n",
|
|||
|
|
" (conv_block1): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" (2): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block2): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (subpixel_convolutional_blocks): Sequential(\n",
|
|||
|
|
" (0): SubPixelConvolutionalBlock(\n",
|
|||
|
|
" (conv): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (pixel_shuffle): PixelShuffle(upscale_factor=2)\n",
|
|||
|
|
" (prelu): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (1): SubPixelConvolutionalBlock(\n",
|
|||
|
|
" (conv): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
|
|||
|
|
" (pixel_shuffle): PixelShuffle(upscale_factor=2)\n",
|
|||
|
|
" (prelu): PReLU(num_parameters=1)\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" (conv_block3): ConvolutionalBlock(\n",
|
|||
|
|
" (conv_block): Sequential(\n",
|
|||
|
|
" (0): Conv2d(64, 3, kernel_size=(9, 9), stride=(1, 1), padding=(4, 4))\n",
|
|||
|
|
" (1): Tanh()\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
" )\n",
|
|||
|
|
")"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {
|
|||
|
|
"tags": []
|
|||
|
|
},
|
|||
|
|
"execution_count": 2
|
|||
|
|
}
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"id": "At4qwZ21hG0P",
|
|||
|
|
"outputId": "2094f895-4be8-4906-b809-48e851c3e692",
|
|||
|
|
"colab": {
|
|||
|
|
"base_uri": "https://localhost:8080/",
|
|||
|
|
"height": 401
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"source": [
|
|||
|
|
"!wget https://www.dropbox.com/s/nmzwu68nrl9j0lf/Hema6.JPG"
|
|||
|
|
],
|
|||
|
|
"execution_count": null,
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"--2020-10-18 07:03:41-- https://www.dropbox.com/s/nmzwu68nrl9j0lf/Hema6.JPG\n",
|
|||
|
|
"Resolving www.dropbox.com (www.dropbox.com)... 162.125.81.1, 2620:100:6031:1::a27d:5101\n",
|
|||
|
|
"Connecting to www.dropbox.com (www.dropbox.com)|162.125.81.1|:443... connected.\n",
|
|||
|
|
"HTTP request sent, awaiting response... 301 Moved Permanently\n",
|
|||
|
|
"Location: /s/raw/nmzwu68nrl9j0lf/Hema6.JPG [following]\n",
|
|||
|
|
"--2020-10-18 07:03:42-- https://www.dropbox.com/s/raw/nmzwu68nrl9j0lf/Hema6.JPG\n",
|
|||
|
|
"Reusing existing connection to www.dropbox.com:443.\n",
|
|||
|
|
"HTTP request sent, awaiting response... 302 Found\n",
|
|||
|
|
"Location: https://ucf5e7114771406b2f7aa5fb2772.dl.dropboxusercontent.com/cd/0/inline/BBejwhTNggmFOJ7aYiOqEpaCw3sj3rdL7-AxT_M727gOkQwnRbLkbUrGjnr-XZAgNflb_omszLDAre8ehKa8Vo-CzBodwQBGrIFrK2NMqE-eK9izcl8d4ZSWAPwuMVJaptU/file# [following]\n",
|
|||
|
|
"--2020-10-18 07:03:42-- https://ucf5e7114771406b2f7aa5fb2772.dl.dropboxusercontent.com/cd/0/inline/BBejwhTNggmFOJ7aYiOqEpaCw3sj3rdL7-AxT_M727gOkQwnRbLkbUrGjnr-XZAgNflb_omszLDAre8ehKa8Vo-CzBodwQBGrIFrK2NMqE-eK9izcl8d4ZSWAPwuMVJaptU/file\n",
|
|||
|
|
"Resolving ucf5e7114771406b2f7aa5fb2772.dl.dropboxusercontent.com (ucf5e7114771406b2f7aa5fb2772.dl.dropboxusercontent.com)... 162.125.81.15, 2620:100:6031:15::a27d:510f\n",
|
|||
|
|
"Connecting to ucf5e7114771406b2f7aa5fb2772.dl.dropboxusercontent.com (ucf5e7114771406b2f7aa5fb2772.dl.dropboxusercontent.com)|162.125.81.15|:443... connected.\n",
|
|||
|
|
"HTTP request sent, awaiting response... 200 OK\n",
|
|||
|
|
"Length: 21002 (21K) [image/jpeg]\n",
|
|||
|
|
"Saving to: ‘Hema6.JPG’\n",
|
|||
|
|
"\n",
|
|||
|
|
"Hema6.JPG 100%[===================>] 20.51K --.-KB/s in 0.001s \n",
|
|||
|
|
"\n",
|
|||
|
|
"2020-10-18 07:03:43 (20.8 MB/s) - ‘Hema6.JPG’ saved [21002/21002]\n",
|
|||
|
|
"\n"
|
|||
|
|
],
|
|||
|
|
"name": "stdout"
|
|||
|
|
}
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"id": "yVNjAI3rhR4E"
|
|||
|
|
},
|
|||
|
|
"source": [
|
|||
|
|
"preprocess = T.Compose([\n",
|
|||
|
|
" T.ToTensor(),\n",
|
|||
|
|
" T.Normalize([0.485, 0.456, 0.406],\n",
|
|||
|
|
" [0.229, 0.224, 0.225]),\n",
|
|||
|
|
" T.Lambda(lambda x: x.to(device))\n",
|
|||
|
|
"])\n",
|
|||
|
|
"\n",
|
|||
|
|
"postprocess = T.Compose([\n",
|
|||
|
|
" T.Lambda(lambda x: (x.cpu().detach()+1)/2),\n",
|
|||
|
|
" T.ToPILImage()\n",
|
|||
|
|
"])"
|
|||
|
|
],
|
|||
|
|
"execution_count": null,
|
|||
|
|
"outputs": []
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"id": "mA5-CPxhhTYU"
|
|||
|
|
},
|
|||
|
|
"source": [
|
|||
|
|
"image = readPIL('Hema6.JPG')\n",
|
|||
|
|
"image.size\n",
|
|||
|
|
"# (260,181)\n",
|
|||
|
|
"image = image.resize((130,90))\n",
|
|||
|
|
"im = preprocess(image)"
|
|||
|
|
],
|
|||
|
|
"execution_count": null,
|
|||
|
|
"outputs": []
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"id": "tlw-luG6hXY_"
|
|||
|
|
},
|
|||
|
|
"source": [
|
|||
|
|
"sr = model(im[None])[0]\n",
|
|||
|
|
"sr = postprocess(sr)"
|
|||
|
|
],
|
|||
|
|
"execution_count": null,
|
|||
|
|
"outputs": []
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"id": "wFRuf-XAhYFp",
|
|||
|
|
"outputId": "1a8e82fa-ec1d-49da-c251-93f304d8c306",
|
|||
|
|
"colab": {
|
|||
|
|
"base_uri": "https://localhost:8080/",
|
|||
|
|
"height": 303
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"source": [
|
|||
|
|
"subplots([image, sr], nc=2, figsize=(10,10), titles=['Original image','High resolution image'])"
|
|||
|
|
],
|
|||
|
|
"execution_count": null,
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"2020-10-18 07:03:58.160 | INFO | torch_snippets.loader:subplots:359 - plotting 2 images in a grid of 1x2 @ (10, 10)\n"
|
|||
|
|
],
|
|||
|
|
"name": "stderr"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"output_type": "display_data",
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 720x720 with 2 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {
|
|||
|
|
"tags": [],
|
|||
|
|
"needs_background": "light"
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"id": "QHSV2lNyhZkf"
|
|||
|
|
},
|
|||
|
|
"source": [
|
|||
|
|
""
|
|||
|
|
],
|
|||
|
|
"execution_count": null,
|
|||
|
|
"outputs": []
|
|||
|
|
}
|
|||
|
|
]
|
|||
|
|
}
|