{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "UEBilEjLj5wY"
},
"source": [
"Deep Learning Models -- A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks.\n",
"- Author: Sebastian Raschka\n",
"- GitHub Repository: https://github.com/rasbt/deeplearning-models"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
},
"base_uri": "https://localhost:8080/",
"height": 119
},
"colab_type": "code",
"executionInfo": {
"elapsed": 536,
"status": "ok",
"timestamp": 1524974472601,
"user": {
"displayName": "Sebastian Raschka",
"photoUrl": "//lh6.googleusercontent.com/-cxK6yOSQ6uE/AAAAAAAAAAI/AAAAAAAAIfw/P9ar_CHsKOQ/s50-c-k-no/photo.jpg",
"userId": "118404394130788869227"
},
"user_tz": 240
},
"id": "GOzuY8Yvj5wb",
"outputId": "c19362ce-f87a-4cc2-84cc-8d7b4b9e6007"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Sebastian Raschka \n",
"\n",
"CPython 3.6.8\n",
"IPython 7.2.0\n",
"\n",
"torch 1.0.0\n"
]
}
],
"source": [
"%load_ext watermark\n",
"%watermark -a 'Sebastian Raschka' -v -p torch"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "rH4XmErYj5wm"
},
"source": [
"# Model Zoo -- CNN Gender Classifier (ResNet-152 Architecture, CelebA) with Data Parallelism"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Network Architecture"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The network in this notebook is an implementation of the ResNet-152 [1] architecture on the CelebA face dataset [2] to train a gender classifier. \n",
"\n",
"\n",
"References\n",
" \n",
"- [1] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778). ([CVPR Link](https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html))\n",
"\n",
"- [2] Zhang, K., Tan, L., Li, Z., & Qiao, Y. (2016). Gender and smile classification using deep convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 34-38).\n",
"\n",
"The ResNet-152 architecture is similar to the ResNet-50 architecture, which is in turn similar to the ResNet-34 architecture shown below (from [1]) except that the ResNet 101 is using a Bootleneck block (compared to ResNet-34) and more layers than ResNet-50 (figure shows a screenshot from [1]):\n",
"\n",
"\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The following figure illustrates residual blocks with skip connections such that the input passed via the shortcut matches the dimensions of the main path's output, which allows the network to learn identity functions.\n",
"\n",
"\n",
"\n",
"\n",
"The ResNet-34 architecture actually uses residual blocks with modified skip connections such that the input passed via the shortcut matches is resized to dimensions of the main path's output. Such a residual block is illustrated below:\n",
"\n",
"\n",
"\n",
"The ResNet-50/101/151 then uses a bottleneck as shown below:\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For a more detailed explanation see the other notebook, [resnet-ex-1.ipynb](resnet-ex-1.ipynb)."
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "MkoGLH_Tj5wn"
},
"source": [
"## Imports"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
}
},
"colab_type": "code",
"id": "ORj09gnrj5wp"
},
"outputs": [],
"source": [
"import os\n",
"import time\n",
"\n",
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"import torch\n",
"import torch.nn as nn\n",
"import torch.nn.functional as F\n",
"\n",
"from torch.utils.data import Dataset\n",
"from torch.utils.data import DataLoader\n",
"\n",
"from torchvision import datasets\n",
"from torchvision import transforms\n",
"\n",
"import matplotlib.pyplot as plt\n",
"from PIL import Image\n",
"\n",
"\n",
"if torch.cuda.is_available():\n",
" torch.backends.cudnn.deterministic = True"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Settings"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
},
"base_uri": "https://localhost:8080/",
"height": 85
},
"colab_type": "code",
"executionInfo": {
"elapsed": 23936,
"status": "ok",
"timestamp": 1524974497505,
"user": {
"displayName": "Sebastian Raschka",
"photoUrl": "//lh6.googleusercontent.com/-cxK6yOSQ6uE/AAAAAAAAAAI/AAAAAAAAIfw/P9ar_CHsKOQ/s50-c-k-no/photo.jpg",
"userId": "118404394130788869227"
},
"user_tz": 240
},
"id": "NnT0sZIwj5wu",
"outputId": "55aed925-d17e-4c6a-8c71-0d9b3bde5637"
},
"outputs": [],
"source": [
"##########################\n",
"### SETTINGS\n",
"##########################\n",
"\n",
"# Hyperparameters\n",
"RANDOM_SEED = 1\n",
"LEARNING_RATE = 0.001\n",
"NUM_EPOCHS = 10\n",
"\n",
"# Architecture\n",
"NUM_FEATURES = 128*128\n",
"NUM_CLASSES = 2\n",
"BATCH_SIZE = 128\n",
"DEVICE = 'cuda:2' # default GPU device\n",
"GRAYSCALE = False"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Dataset"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Downloading the Dataset"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Note that the ~200,000 CelebA face image dataset is relatively large (~1.3 Gb). The download link provided below was provided by the author on the official CelebA website at http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"1) Download and unzip the file `img_align_celeba.zip`, which contains the images in jpeg format.\n",
"\n",
"2) Download the `list_attr_celeba.txt` file, which contains the class labels\n",
"\n",
"3) Download the `list_eval_partition.txt` file, which contains training/validation/test partitioning info"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Preparing the Dataset"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Male | \n",
"
\n",
" \n",
" \n",
" \n",
" | 000001.jpg | \n",
" 0 | \n",
"
\n",
" \n",
" | 000002.jpg | \n",
" 0 | \n",
"
\n",
" \n",
" | 000003.jpg | \n",
" 1 | \n",
"
\n",
" \n",
" | 000004.jpg | \n",
" 0 | \n",
"
\n",
" \n",
" | 000005.jpg | \n",
" 0 | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Partition | \n",
"
\n",
" \n",
" | Filename | \n",
" | \n",
"
\n",
" \n",
" \n",
" \n",
" | 000001.jpg | \n",
" 0 | \n",
"
\n",
" \n",
" | 000002.jpg | \n",
" 0 | \n",
"
\n",
" \n",
" | 000003.jpg | \n",
" 0 | \n",
"
\n",
" \n",
" | 000004.jpg | \n",
" 0 | \n",
"
\n",
" \n",
" | 000005.jpg | \n",
" 0 | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Male | \n",
" Partition | \n",
"
\n",
" \n",
" \n",
" \n",
" | 000001.jpg | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" | 000002.jpg | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" | 000003.jpg | \n",
" 1 | \n",
" 0 | \n",
"
\n",
" \n",
" | 000004.jpg | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" | 000005.jpg | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Male | \n",
" Partition | \n",
"
\n",
" \n",
" \n",
" \n",
" | 000001.jpg | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" | 000002.jpg | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" | 000003.jpg | \n",
" 1 | \n",
" 0 | \n",
"
\n",
" \n",
" | 000004.jpg | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" | 000005.jpg | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
"
\n",
"