File size: 11,083 Bytes
38fd365 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 |
{
"cells": [
{
"cell_type": "markdown",
"id": "b1c9de9d-6777-4a1d-bb7c-c2413d01bd7d",
"metadata": {},
"source": [
"# Generate Data\n",
"\n",
"This bundle uses simple synthetic data for training and testing. Using `create_test_image_3d` we'll create images of spheres with labels for each divided into 3 classes distinguished by intensity. The network will be able to train very quickly on this of course but it's for demonstration purposes and your specialised bundle will by modified for your data and its layout. \n",
"\n",
"Assuming this notebook is being run from the `docs` directory it will create two new directories in the root of the bundle, `train_data` and `test_data`.\n",
"\n",
"First imports:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "1e7cb4a8-f91a-4f15-a8aa-3136c2b954d6",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"import json\n",
"import random\n",
"\n",
"import matplotlib.pyplot as plt\n",
"import nibabel as nib\n",
"import numpy as np\n",
"\n",
"plt.rcParams[\"image.interpolation\"] = \"none\""
]
},
{
"cell_type": "markdown",
"id": "2b2c3de5-01e5-4578-832b-b24a75d095d5",
"metadata": {},
"source": [
"As shown here, the images are spheres in a 3D volume with associated labels:"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"def generate_images(image_size=128, border=20, shape_probabilities=None, shape_sizes=None):\n",
" image = np.zeros((image_size, image_size))\n",
"\n",
" if shape_probabilities is None:\n",
" shape_probabilities = [0.25, 0.2, 0.3, 0.25] # Default probabilities for circle, triangle, rectangle\n",
"\n",
" if shape_sizes is None:\n",
" shape_sizes = [(10, 30), (20, 40), (20, 40)] # Default size ranges for circle, triangle, rectangle\n",
"\n",
" def draw_zero(image):\n",
" return image\n",
"\n",
" def draw_circle(image):\n",
" center_x, center_y = np.random.randint(border, image_size - border), np.random.randint(border, image_size - border)\n",
" radius = np.random.randint(*shape_sizes[0])\n",
" y, x = np.ogrid[-center_x:image_size-center_x, -center_y:image_size-center_y]\n",
" mask = x ** 2 + y ** 2 <= radius ** 2\n",
" image[mask] = 1\n",
" return image\n",
"\n",
" def draw_triangle(image):\n",
" size = np.random.randint(*shape_sizes[1])\n",
" x1, y1 = np.random.randint(border, image_size - border), np.random.randint(border, image_size - border)\n",
" x2, y2 = x1 + size, y1\n",
" x3, y3 = x1 + size // 2, y1 - int(size * np.sqrt(3) / 2)\n",
" triangle = np.array([[x1, x2, x3], [y1, y2, y3]])\n",
" mask = plt.matplotlib.path.Path(np.transpose(triangle)).contains_points(\n",
" np.array([(i, j) for i in range(image_size) for j in range(image_size)])\n",
" )\n",
" image[mask.reshape(image_size, image_size)] = 1\n",
" return image\n",
"\n",
" def draw_rectangle(image):\n",
" x1, y1 = np.random.randint(border, image_size - border), np.random.randint(border, image_size - border)\n",
" x2, y2 = x1 + np.random.randint(*shape_sizes[2]), y1 + np.random.randint(*shape_sizes[2])\n",
" image[x1:x2, y1:y2] = 1\n",
" return image\n",
"\n",
" label, shape = random.choices([(0, draw_zero), (1, draw_circle), (2, draw_triangle), (3, draw_rectangle)], weights=shape_probabilities)[0]\n",
" image = shape(image)\n",
"\n",
" return image, label"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAekAAAHqCAYAAAAgWrY5AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAAAJ4ElEQVR4nO3dy27cOBRAQXHQ///LnMXAgTO2O51+8UiqWnlhwAQi5OCSeow559wAgJx/Vi8AAPieSANAlEgDQJRIA0CUSANAlEgDQJRIA0CUSANAlEgDQNTl1l8cY7xyHZzIvS+5cw3yLI+8aNF1yLPcch2apAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEg6rJ6AQBzzl8/jzEWroRn+/xvW1e89kQaWGZP/4HDCiINvJ04w21EGngbcYa/48YxAIgySQMvZ4KG+4g08DLiDI8RaeDpxBmeQ6SBpxFneC6RBh4mzvAaIg3cTZzhtUQa+GviDO/hOWkAiDJJAzcxPcP7maSBPxJoWMMkDfxInGEtkQa+EGdoEGlg2zZhhiJn0oBAQ5RIA0CUSAPbGGP1EoBvOJMGtm37PdS2v6HBJA18McYwXUOASAM/EmpYS6SBq0zVsI4zaeAmzqzh/UzSwF8zWcN7iDQARNnuBu7yMU3b+uYauy6PEWngIc6q4XVsdwNPY2qC5xJp4Kk8sgXPI9LAS4g1PE6kgZcSarifG8eAl3NzGdzHJA0AUSINvJWzaridSANLCDX8mUgDy5iq4To3jgHLCTV8zyQNAFEiDQBRIg0AUSINAFEiDQBRIg0AUSINAFEiDQBRIg0AUSINAFEiDQBR3t292Jxz9RJ+5H3KAGuZpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEgSqQBIEqkASBKpAEg6rJ6AWc3xli9BACiTNIAEDXmnHP1IgCAr0zSABAl0gAQJdIAECXSABAl0gAQJdIAECXSABAl0gAQJdIAECXSABAl0gAQJdIAECXSABAl0gAQdbn1F8cYr1wHJ3Lv11FdgzzLI1/odR3yLLdchyZpAIgSaQCIEmkAiBJpAIgSaQCIEmkAiBJpAIgSaQCIEmkAiBJpAIgSaQCIEmkAiBJpAIgSaQCIEmkAiBJpAIgSaQCIEmkAiBJpAIgSaQCIEmkAiBJpAIgSaQCIEmkAiBJpAIgSaQCIEmkAiBJpAIgSaQCIEmkAiBJpAIi6rF4A7MWcc/USfjTGWL0E4AVM0gAQJdIAECXSABAl0gAQJdIAECXSABAl0gAQJdIAECXSABAl0gAQJdIAECXSABAl0gAQJdIAECXSABAl0gAQJdIAECXSABAl0gAQJdIAECXSABAl0gAQJdIAECXSABAl0gAQJdIAECXSABAl0gAQdVm9ANiLMcbqJQAnY5IGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCivBf1kzvnrZ6+ABGA1kzQARJmkt98naACoOHWkxRmAstNudws0AHWnmqSFGYA9OUWkxRmAPTp0pMUZgD077Zk0ANQdNtKmaAD27lDb3cIMwJEcItLiDMAR7TrS4gzAke32TFqgATi63UbaV6oAOLrdRnrb/gu1WANwVLuONAAc2SEibZoG4IgOEelts/UNwPHs+hGs73wOtTvAAdizw0zS3zFZA7Bnh470ttkGB2C/Dh/pD0INwN4c7kz6GufVAOzJaSZpANib00baWTUAdaeN9AehBqDq9JHeNlM1AE2nunHsT4QagBKTNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESNOedcvQgA4CuTNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARIk0AESJNABEiTQARF1u/cUxxivXwYnc+3VU1yDP8sgXel2HPMst16FJGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCiRBoAokQaAKIuqxcAAPeYc778b4wxXv43rjFJA0CUSANAlEgDQJRI32DO+ZazDwD4zI1jVwgzACuJ9DfEGYAC290AEGWS/sQEDUCJSG/iDEDTqSMtzgCUnTLS4gzAHpwq0uIMwJ6cItLiDMAeHTrS4gzAnnlOGgCiDhtpUzQAe3fYSK/+UDcAPOqwkd62/0It1gDs1aEj/UGoAdijQ9/d/dnnUDuvBmAPTjFJ/5/JGoA9OGWkAWAPThtpN5UBUHfaSH8QawCqTh/pD0INQM1p7u6+hTvAASgxSf/AZA3AaiJ9hfNqAFay3X0DoQZgBZM0AESJNABEiTQARIk0AESJNABEiTQARHkEC0JWvOnOI4bQZZIGgCiRBoAokQaAKJEGgCiRBoAokQaAKJEGgCjPSQOwS2d4xt8kDQBRIg0AUSINAFEiDQBRIg0AUSINAFEiDQBRIg0AUSINAFEiDQBRIg0AUSINAFEiDQBRIg0AUSINAFEiDQBRIg0AUSINAFEiDQBRIg0AUWPOOVcvAgD4yiQNAFEiDQBRIg0AUSINAFEiDQBRIg0AUSINAFEiDQBRIg0AUf8CeDXUWZWl5zcAAAAASUVORK5CYII=",
"text/plain": [
"<Figure size 500x500 with 9 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig, axes = plt.subplots(3, 3, figsize=(5, 5))\n",
"for i, ax in enumerate(axes.flatten()):\n",
" for j in range(9):\n",
" images, label = generate_images(128)\n",
" ax.imshow(images, cmap='gray')\n",
" ax.axis('off')\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"id": "8e08c4a1-6630-4ab3-832b-e53face81e35",
"metadata": {},
"source": [
"50 image/label pairs are now generated into the directory `../data/train_data`, assuming this notebook is run from the `docs` directory this will be in the bundle root:"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"num_images = 50\n",
"out_dir = os.path.abspath(\"../data/train_data\")\n",
"os.makedirs(out_dir, exist_ok=True)\n",
"\n",
"train_data = []\n",
"for i in range(num_images):\n",
" data = {}\n",
" img, lbl = generate_images(128)\n",
" n = nib.Nifti1Image(img, np.eye(4))\n",
" train_file_path = os.path.join(out_dir, f\"img{i:02}.nii.gz\")\n",
" nib.save(n, train_file_path)\n",
"\n",
" data[\"image\"] = train_file_path\n",
" data[\"label\"] = lbl\n",
" train_data.append(data)\n",
"\n",
"with open(os.path.abspath(\"../data/train_samples.json\"), \"w\") as f:\n",
" json.dump(train_data, f, indent=2)"
]
},
{
"cell_type": "markdown",
"id": "7fe344f7-d01d-49d5-adca-a7071939ca53",
"metadata": {},
"source": [
"We'll also generate some test data in a separate folder:"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "c3b8d8f3-8d73-4657-98f3-5605d4b1bad9",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"num_images = 10\n",
"out_dir = os.path.abspath(\"../data/test_data\")\n",
"os.makedirs(out_dir, exist_ok=True)\n",
"\n",
"train_data = []\n",
"for i in range(num_images):\n",
" data = {}\n",
" img, lbl = generate_images(128)\n",
" n = nib.Nifti1Image(img, np.eye(4))\n",
" train_file_path = os.path.join(out_dir, f\"img{i:02}.nii.gz\")\n",
" nib.save(n, train_file_path)\n",
"\n",
" data[\"image\"] = train_file_path\n",
" data[\"label\"] = lbl\n",
" train_data.append(data)\n",
"\n",
"with open(os.path.abspath(\"../data/test_samples.json\"), \"w\") as f:\n",
" json.dump(train_data, f, indent=2)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "599cff25-4894-481b-aec3-6aedda327a09",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"img00.nii.gz img02.nii.gz img04.nii.gz img06.nii.gz\timg08.nii.gz\n",
"img01.nii.gz img03.nii.gz img05.nii.gz img07.nii.gz\timg09.nii.gz\n"
]
}
],
"source": [
"!ls {out_dir}"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|