{ "cells": [ { "cell_type": "markdown", "id": "0f3e5c69-92bd-4b20-84f0-6d35bf6757c6", "metadata": {}, "source": [ "# Dimensionality in Python\n", "\n", "After we know how to operate with vectors and matrices in SuperCollider, we now want to compare it with its counterparts in Python.\n", "Although Python is a [battery included language](https://www.python.org/dev/peps/pep-0206/#batteries-included-philosophy) (meaning it has already a big built-in library), we still rely on an the third-party library called [numpy](https://numpy.org/) when operating with matrices, vectors or more sophisticated mathematical expressions.\n", "\n", "It is an unwritten rule to `import numpy as np` and for this course we will continue with this tradition." ] }, { "cell_type": "code", "execution_count": null, "id": "14f19b97-afa3-4f7a-86ef-84f3140642db", "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import imageio\n", "\n", "np.random.seed(42)" ] }, { "cell_type": "markdown", "id": "9ec98496-f842-4b5d-8fac-4d23b81154e5", "metadata": {}, "source": [ "## From scalar to vector to matrix\n", "\n", "### Scalar\n", "\n", "We can either use the built in functions of Python to generate or transform a scalar or we can use the numpy equivalents are they are interchangeable on this level." ] }, { "cell_type": "code", "execution_count": null, "id": "dc3588bb-b691-413b-a2be-0f7e2c6b9af5", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "5" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "5" ] }, { "cell_type": "code", "execution_count": null, "id": "4313e5a8-ba0d-4569-afde-366a7a1f9102", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "1.5" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "1.5" ] }, { "cell_type": "markdown", "id": "142217c0-9923-4ef2-9d93-2614a44607f6", "metadata": {}, "source": [ "When we look up the definiton of the square root that for a $x \\in \\mathbb{R}_{\\geq 0}$ we can also write\n", "\n", "$$\n", "\\sqrt{x} = x^{\\frac{1}{2}}\n", "$$\n", "\n", "which is motivated by the fact that $\\left( x^{\\frac{1}{2}} \\right)^2 = x^{2\\frac{1}{2}} = x^{\\frac{1}{1}} = x = \\left( \\sqrt{x} \\right) ^2$.\n", "\n", "We can use this convention to use the built in power calculation of Python to calculate a square root, but we cas also use the numpy function `sqrt`." ] }, { "cell_type": "code", "execution_count": null, "id": "753b0f28-cb55-4ada-9d39-4dafdb0aef83", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "1.4142135623730951" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "2.0**(0.5)" ] }, { "cell_type": "code", "execution_count": null, "id": "3a589a3e-b433-4202-bc52-91b4034976aa", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "1.4142135623730950488" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.sqrt(2.0, dtype=np.float128)" ] }, { "cell_type": "markdown", "id": "1424e1cd-0e74-4744-9932-2b44ba856091", "metadata": {}, "source": [ "When using numpy we can also specify the resolution of the float variable - as a computer can only store `0` and `1` we need to find a mapping which translates this `0` and `1` to numbers between e.g. $0$ and $1$ - this is handled by [floating point precission](https://en.wikipedia.org/wiki/Single-precision_floating-point_format) and by default Python useses 64 bits to store its floating points.\n", "With numpy we can define the type of variable we want to use for our calculation by the `dtype` argument - this will come handy later when working with neural networks." ] }, { "cell_type": "markdown", "id": "a2f44395-2a16-423d-bab2-80bf204649ff", "metadata": {}, "source": [ "### Vector\n", "\n", "As in SuperCollider we can use lists to represent a collection of scalars with fixed ordering.\n", "We can use the Python native lists to represent a vector" ] }, { "cell_type": "code", "execution_count": null, "id": "98ecd180-1657-433c-b562-f4c557162a66", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[1, 2, 3]" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "vector = [1, 2, 3]\n", "vector" ] }, { "cell_type": "markdown", "id": "c5da541e-134e-4732-9a7f-4745c13c4599", "metadata": {}, "source": [ "but we will rely more on the *array* functionality of numpy throughout this course." ] }, { "cell_type": "code", "execution_count": null, "id": "34423839-9d6b-4c94-9b41-788c1a47c548", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([1, 2, 3])" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np_vector = np.array([1, 2, 3])\n", "np_vector" ] }, { "cell_type": "markdown", "id": "17c454c1-694a-4ffd-88c2-d2f9d1f897ff", "metadata": {}, "source": [ "Why we use this notation instead of the built in list will become more obvious when we want to interact with the vector." ] }, { "cell_type": "code", "execution_count": null, "id": "850a8b6e-9db1-4970-8301-9a6c8e89d26e", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[1, 2, 3, 1, 2, 3]" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "vector*2" ] }, { "cell_type": "code", "execution_count": null, "id": "1be4dea3-741f-4943-965a-a381c0a9dfca", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([2, 4, 6])" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np_vector*2" ] }, { "cell_type": "markdown", "id": "249f0322-bc7a-4ad7-b969-5651fe0eb9e9", "metadata": {}, "source": [ "Multiplying a scalar *n* to a internal list duplicates the list *n* times - this can come in handy when working with strings, but when working with mathematical objects we prefer to follow the mathematical interpretation of numpy - so from now on we will only focus on numpy.\n", "\n", "When multiplying two vectors numpy performs a pairwise multiplication." ] }, { "cell_type": "code", "execution_count": null, "id": "ce0a6a7d-2caa-4f98-865a-575124372650", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([-7, 16, 27])" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.array([1, 2, 3]) * np.array([-7, 8, 9])" ] }, { "cell_type": "markdown", "id": "57cf926b-8f3f-453c-b1dc-2f4eb669b90e", "metadata": {}, "source": [ "Contrary to SuperCollider it does not allow us to perform this operation if the dimensions of the pairs do not match up." ] }, { "cell_type": "code", "execution_count": null, "id": "805899c8-cbee-468b-a16e-788a4601c93e", "metadata": {}, "outputs": [ { "ename": "ValueError", "evalue": "operands could not be broadcast together with shapes (3,) (2,) ", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m3\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m*\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m5\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m3\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[0;31mValueError\u001b[0m: operands could not be broadcast together with shapes (3,) (2,) " ] } ], "source": [ "np.array([1, 2, 3]) * np.array([5, 3])" ] }, { "cell_type": "markdown", "id": "a20a0bd2-1026-4a61-9c25-d3fdf034e212", "metadata": {}, "source": [ "### Matrices\n", "\n", "There are two ways to define a matrix in numpy - either by providing a list of list of scalars (like in SuperCollider) or using numpy built-in functions which generates a matrix by providing a `size` (sometimes this parameter is also called `shape`)." ] }, { "cell_type": "code", "execution_count": null, "id": "e269e9c3-55c4-4c60-ad1e-3502ee6c85b0", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[1, 2, 3],\n", " [4, 5, 6],\n", " [7, 8, 9]])" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "matrix_a = np.array([[1,2,3],[4,5,6],[7,8,9]])\n", "matrix_a" ] }, { "cell_type": "code", "execution_count": null, "id": "93320890-a127-4df6-a352-81bb67f73b19", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[ 6, 19, 14],\n", " [10, 7, 6],\n", " [18, 10, 10]])" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "matrix_b = np.random.randint(low=0, high=20, size=(3, 3))\n", "matrix_b" ] }, { "cell_type": "markdown", "id": "37e186c1-0a11-4bcd-9606-a194c3d1b9cd", "metadata": {}, "source": [ "We can also, just like with vectors, simply multiply a scalar to our matrix." ] }, { "cell_type": "code", "execution_count": null, "id": "631d4930-cf64-4874-a984-7fc1b3a6c9d2", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[ 2, 4, 6],\n", " [ 8, 10, 12],\n", " [14, 16, 18]])" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "matrix_a * 2" ] }, { "cell_type": "markdown", "id": "87de055e-bcca-4357-986b-6616e25612d0", "metadata": {}, "source": [ "But when multiplying a matrix with another matrix we must pay attention as this does a pairwise multiplication as well - which is not how we defined matrix multiplication" ] }, { "cell_type": "code", "execution_count": null, "id": "1708a167-e18a-4728-aba3-499e0de613bd", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[ 1, 4, 9],\n", " [16, 25, 36],\n", " [49, 64, 81]])" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "matrix_a * matrix_a" ] }, { "cell_type": "markdown", "id": "e6fdba80-3cd6-4090-9681-a2adfe346722", "metadata": {}, "source": [ "But numpy has a built-in function for matrix multiplication." ] }, { "cell_type": "code", "execution_count": null, "id": "770d5da2-e42f-4c69-86c4-5c656f7982b6", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[ 30, 36, 42],\n", " [ 66, 81, 96],\n", " [102, 126, 150]])" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.matmul(matrix_a, matrix_a)" ] }, { "cell_type": "markdown", "id": "64bc4a7e-0b48-4ef5-a2ef-f4d622feea93", "metadata": {}, "source": [ "This will also verify if the dimensions of both matrices are matching." ] }, { "cell_type": "code", "execution_count": null, "id": "9e4d432a-ba24-458c-83ba-999f6cda5fa6", "metadata": {}, "outputs": [ { "ename": "ValueError", "evalue": "matmul: Input operand 1 has a mismatch in its core dimension 0, with gufunc signature (n?,k),(k,m?)->(n?,m?) (size 3 is different from 2)", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmatmul\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrand\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrand\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m3\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m3\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[0;31mValueError\u001b[0m: matmul: Input operand 1 has a mismatch in its core dimension 0, with gufunc signature (n?,k),(k,m?)->(n?,m?) (size 3 is different from 2)" ] } ], "source": [ "np.matmul(np.random.rand(2, 2), np.random.rand(3, 3))" ] }, { "cell_type": "markdown", "id": "44590f6d-e29c-4340-92ac-7442d733e38d", "metadata": {}, "source": [ "## Working with matrices\n", "\n", "After we have seen the basic fundaments of matrices and vectors in Python via numpy we can now use them in an example.\n", "Thanks to the large number of third-party libraries we can almost work with any kind of data in Python, so instead of working with audio like in SuperCollider we will take a look image data." ] }, { "cell_type": "code", "execution_count": null, "id": "4ed7651f-bb46-45a4-a7b1-cb81146a3b22", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "image = imageio.imread('rsh_logo.jpg')\n", "plt.imshow(image);" ] }, { "cell_type": "markdown", "id": "564dd5ee-c862-4da8-84ee-952f40fd7053", "metadata": {}, "source": [ "Digital images are stored as matrices - let's take a look at them.\n", "We can use the `shape` parameter of an array to take a look at the dimensions - just like in SuperCollider." ] }, { "cell_type": "code", "execution_count": null, "id": "eb755f2d-2d88-44ec-b42a-3c512d872c83", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(630, 1200, 3)" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "image.shape" ] }, { "cell_type": "markdown", "id": "1f2f7f0e-d1ee-426e-a77c-8ab1165380ca", "metadata": {}, "source": [ "Taking a look at the shape it tells us that this is a $630 \\times 1200 \\times 3$ matrix - we have yet only encountered $m \\times n$ matrices - so what is going on here?\n", "This is called a *multi-dimensional matrix* - formerly on a $m \\times n$ matrix we only defined for each index tuple $i, j$ a scalar - when working with multi dimensional arrays we do not map each index tuple $i, j$ to a scalar but to a vector of dimension $o$ - so we have a $m \\times n \\times o$ dimensional matrix. We could also store a matrix instead of a vector - so we now have a recursive definition which allows us to represent an arbitrary amount of *multidimensionality*.\n", "\n", "Coming back to our image from above: For each pixel, which is located at a $x$ and $y$ position, we have a corresponding color.\n", "This color is often represented in [RGB](https://en.wikipedia.org/wiki/RGB_color_space) in the digital domain which describes color by stating the brightness of the 3 colors **R**ed, **G**reen and **B**lue - so as a tuple.\n", "\n", "So for each pixel we need to store 3 scalars, so a 3 dimensional vector, leading to\n", "\n", "$$ \\underbrace{630}_{\\text{# of pixels in Y dimension}} \\times \\underbrace{1200}_{\\text{# of pixels in X dimension}} \\times \\underbrace{3}_{\\text{brightness of R, G, B}} $$" ] }, { "cell_type": "markdown", "id": "df8f639c-3f05-4f7b-ac64-964d19291a8b", "metadata": {}, "source": [ "Now we take a look at how we can access and modify certain parameters in an numpy array.\n", "We will use the `m:n` notation in Python which will select everything between `m` and `n`.\n", "If we do not provide a value for `m` and `n` (so only writing `:`) it will select every value from this dimension." ] }, { "cell_type": "code", "execution_count": null, "id": "8c33fd08-0f29-41ef-877c-1cffc8c0ea21", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# take only a look at the brightness of the red channel\n", "plt.imshow(image[:, :, 0], cmap='Reds');" ] }, { "cell_type": "code", "execution_count": null, "id": "399bdc65-e457-4a61-9fc8-45a0d99beb71", "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXAAAAB2CAYAAADRN8iWAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/Z1A+gAAAACXBIWXMAAAsTAAALEwEAmpwYAABEn0lEQVR4nO29d5hcxZX3/zn3dp6cNMoJZaEshJAQiGSCjUnGxovD4py99u7+Fq9/3te73uhdp/XrhI2NAyYbEDkIBEgoC6GEBMpZmhlN7ty33j/uvd23e7onaEYT4H6fZ6a7b6g6lb516tSpKlFK4cKFCxcuhh60gRbAhQsXLlycHVwCd+HChYshCpfAXbhw4WKIwiVwFy5cuBiicAnchQsXLoYoXAJ34cKFiyGKXhG4iFwjIntEZK+I3NlXQrlw4cKFi64hZ+sHLiI68DZwFXAU2Ah8VCm1q+/Ec+HChQsXhdAbDXwRsFcptV8pFQfuB27oG7FcuHDhwkVX8PTi3VHAEcfvo8CFnb1QXV2txo8f34soXQxZKDAaIyQO1CNogIFWGsAzoQo8AzgVo8BoCJM83IBWW4pnRCloMnDyuHCRB5s3b65XStXkXu8NgXcLIvI54HMAY8eOZdOmTec6ShcDBAUopRAUCgVoiHmV+JrD1H3kjySkGVEevBMrqLz7I/gvGYcIYD1pUqcBSjOvS1+SqUIpZcVjSXashfqP/4m4p45hf7wD3+Kx5qOiUEoQS6J8YhQyP0qfyuzCBYjIoXzXe6P6HAPGOH6Ptq5lQSl1l1JqoVJqYU1Nhw7ExbsMkiZiDYuXSe5rovnfXyR5qgVd+dHKNYo/swjfgpGIGFnvYhG/OhccqCyBbFJWEHnhbWIbDxC6fjaeaTX2Q0iavJWVojxpFclL1u7+Qi76C70h8I3AZBGZICI+4DZgRd+I5WIowkGN2ESommO03bWe8Kt7kZQPtCT+JedRdPt8pNgPSsOkbskJKxNaX0E5pEPAaIvS8uNXkdFBQtfPRSsPYjYJK26B7oiRS+SuBu6iv3DWBK6USgJfAZ4D3gIeVErt7CvBXAxBKNN0YtKXAmUQfe0Q7fduQm8XhBTasCBl31iOPro0TaRYnyIgolmESF/zd3Z4CiL3vUns7X2ELppNYOmYdLySxd/dF6SQRu7CxblCr2zgSqmngaf7SBYX7xooDKVhHGik9T9XkjzRjE4Aw9NO6WevxH/ZRIslLat3f3Gesj8Uqj5K8/+sQq8speiT8xGfu6bNxdCDW2td9BmUrawqQSIJ2n71OpE1e9GUlxQR/OePo+QbyywvD4XCABTSbyZjawIzCeE/biV+6iBFly3Ce/F43KbgYijCrbUu+g6mGwqiQfjJt2j92asIPhQKvaaE8v+8Fq3MnyZsSdub+w+CIrG7jpZ716B5yij524sQXSswTenCxeCGS+Au+gy2vTi5t4Gmf30WFQYdHUWC4k8swr9sAohh+3k4X+wvAVHxFNHHdhHffYTSDy/BO3uY6TLomq5dDEG8qwncdufK/bS/53P3yvdsX8jQ2fXcZ3ob9zl3Y1O2McL6rqwvgIorWr7/Gsk9pwAvKZIEFo6h+GPzkYDPfEcyH+KYrcxXJvnT0nn60rKlv2WeT+1rpO2FN9BKKyj66mIQMV0GVfZz+eNUWc8460pndamv0DE8lbHrF6y32TJ3vNc9OXsWbt8jK/5O5DWfyydrbjiF5e9YB/Pf76t225t6cs4X8gwEzrYx5SP83ngVFAon33X7e0/jtp/PfdaZ3r70jMhuRw56VCaTRx/ZRviJjUjCY9JysYeiT1yEZ+Ywi6e1jL+3dAzL/p4vvxxPpxf/FJYx00CVmESn4inT73v9YSq+dS2eiZUmgTvCNZEpEzrco0M55ZO7UCPvbVmY4dkTwMrMywIkLumJ4kyastOSWTqVrx4VbjNm3Pbt/vK8ScuYEZt86TPLIXOtayUgvy9/vrzIV76dtduuyr+3nfy7ksBz0RUxdpaJhQiyr+QpFHZX8fWHxlcg5qwP0m6DkNzfSNvvNpA8lUDwYmgJgssmErh+Cnj1DPtLR+LoEItVTrkNxgqAQuRN+o5KK6gmyRmkDjbSdtdr+KZUE7pxNgT0TNiaYNtR8me9s1FmfjuftTXxtCsi0iF9vVEKbELOhCmmyJ2QCxRybVTYA/BCHVJ2vFlXcPr65+8k+hZZbUZzprMjQVq6hKNs8pWrlhVGPj/+TNvPVlzy18lsdFWvc8M6W7wrTSh93cv1To5csslUmNyeOpe0cu/lfrfjyGhaCqVS6XhEVAEy6iXykKkKJwk/sp3o2n3oyosG6BVeij+6GM+4SuudTIMvZHYoFI2dzu74WlvNDiVCesbUgPDj24nvPUnRB+bhmVhprrBUWC3UGW+hIXju8DuTjo7mub6vdx3L3ikTjuu5+aMcf/ZgKddslV/WwmFlyuRcpLUjCsmY3b4Kl13293xlVjDmLpLWU1OKs850px10hnclgTu15q401a417ExDPTs5MhWvra2F9RvWcvzE0YKE3JNe3SlzKmWwbv1qHl/xCGfONCCioZR0Wfl6DLGIESwCNOVP7DhJ+O510G4AQkqLElw2mcAHp5Ld+BTdnzHsWNG7U+FtDVwcy+ATe8/Q9rNX8Z5XQeCamUiJ35Sl2z6MOaaLTpPQyeigj3vU9GijIMEplDLyXLfrk1HgPROGkf/dju3i3GnfHcrcYbrpTodujogk3R46juay4ymsTJn51XGk5RCqn/HuNqGo9D8HCtlNCxVA31RMpQxO15/mpz//EZUVlXzr//suI0aM6OT5XC3H2VCyCT8SibD69VX87Oc/JhgMMX3aLKqqqh3P9aH5B3tIaaCUBmJA1KDlp2tI7D2NRoAUKTyhECV/dzlS4iNDfplQzF9mY2hqbiYaj6a14aJgiJKS0k7l6NoUYd2zom7739eJ152m/Nbr8S4aaXY8ojsIMP+ozdYwwSSzaDRMe3u7RWzmtl0Bv5/i4hI8Hp2udKKzNcllyDY7H7OfyRBKdp0x3TXza9q58mbnhTMcEbNLzJhsepSEHsKW1ZbPVhq6ijQ/OeeDs2w7Cy/f3EbHsHOJvpD5L78cZ4t3JYGLVVn3HniHNa+/iqFS6JqGrusIGoFAkLKKMhKJBA0NZ0gk4qRSKXRdx+Px4PP5GTtmHFMnT6O0tAxNc9rLHPF0lfGSrW1GI1HiyRgbN2/gn/75H7nwwsUEg4F0WEo5FrVYw3o7irTG7ojSMAyamprYt28v23dtI5GIMG7ceCoqKixTSt8v7U7LgbVboBLiq/bT/uAmBC+gYdBOyaeuwnfhSPKtiU8ZSY4dP8q69a+zecsm3tq9jTPNTXg9XkLBImqHjWDK5KnMnTOXhfMvoKqqxhpR9ERbthq/QGztMdoffB3vyBqKPzUXAh5UmqisxmaRsZ1GuzxSqQTHjx9nw6b1vLP3bfbte5sjRw8Ti0VRykDTdKqqqhk/bgJjx05g3NjxzJ49n1EjR6BrOpqmd7shdw3LXAWsXr2KPe/sIhQqoqiohKJQsdWxmrK3trbS2tqKoVIkkymWXbycKZOmZIfmIOdkMsHjK/5Cc0sTlVVVlBRnOlBnfsTiMU6eOMns2XNZtHBRL9PT/WQfOnSA11a/QjKVpLSsnNLikrSJ0iwHjWg0RlNTA5FolLLScm64/ia8Xp+dig5pbw+3seKJxxDNoLq6FhQYhkLTzHbT2NhIY1MD5WUVvP/aDxIMhsjXadp52NbWyosvvUBj0xmKi4qprKhE003uaGpqIhKJcMmySxkzelyfZc27ksABENh/cB+//ePvSKXiKGXQ2tKCJoLP7ycQCJBIJIhGYlRVV1FaVkbjmXrq6+vQdS+lJSVMHD+Jyy67kqvfdx01VTVomp4VRc8mpIRYLE4kHKWkvIzd+3awfvMalKHooGEr0HQNTdPSBG6kDFJG9nBXRPB4PPiDAYpDRXg8fkYMH01RUTHndEhrTVwqEVRLjOZvP49KKHS8JInhq66k5KsXga53GAQ0nKnjpVUr+fP9f+Lgwf2MHD2SeXMWUVQUpOFMHXv27GHP3l1s27mFxx5/iFtv/iif+fQXKC0t65CfhZGZZFORJOGfrCXR2kzlJy7FM314OhVpm7DDpmuXQ0trM3vefovnnnuGdRvWcOLEMZRojB0zhmnTZ1BZWYPP5yMSaefIkSNs3LKBF156Do/Xw6jhI5kyZQaXXnw5F1xwIcNqatNKgB1P76B45rmneOb5FShA1zyEQqF0uOZIIYLX68Pj8VIUCDFx/HimTJqczrdc04AixZq1a3jllZfQPILP50uTD0AqmULTdYqLQzTWN/G5z36ZCxZcUCC8vkJmFLVh4zp+/sufIl6IhCME/cG0fCKCYRgk4gl0XUcZignjJ/GB938ALx6yJ10znWk8EeOpp1awe+8udI9udbgaSkEykcDn9xGPx5k4bhKXL7+CYDCU01admraitb2ZR/7yAIePHiISjaCJhtfnQdM0YrEYkUiEQ0cO8LUv/S3FxcVZ+Z+V3p7kUH9O8C1cuFD1337ginAkzOnTp1GGIpGMseb11fzlsQeJxCIkU0nKS8v5yuf/hqnTplMUKqKtvZXjx06w+vVXeGX1S9Q31AMac2bN5fOf+SKzZ83LaojmkFbveihp5fHmNzbxz//2/9Pc0kh1VS1Xv+9aZkydSUlJiSUx5upEpXhu5bM8/ezj+Hw+UMLtt32SuXPmZcbJSkAM4rEYO3bu4KHHHqC1tZU7Pv5p/voTn0akLwnDmRRrwypRYGi0/NcqGr+7Aj0eNC3Onjjl37mGkn+4FPE5OzxF/ZkGfvKzH7Jy5bOUlpRz6y0f4bLlVzJx/ERACIfDvLP3bZ559gmef/kZkokkl116JV/78jepqqxOh9PVyCJtbjA0Iit20/C1e9A8ZQx76Yt4JpRlDWMcTRoRjWQiyfZdb7LiqUd5fd0aGhpOU1lezUUXLmHpRcuYMnkaw4YNJxgMImLOPTQ1NXP48AHeeHMzL73yIvsP7LM6OWH5Jcv5zre+Z2lvvTdp2e21ru40zS1NnDx1ghVPPMrmrRvRdQ+GMvB5/Xzwuhu4dNnlBIMhgsEQlZWVeL1eM/Y8eaeUorW1hZMnT3Dk2GEefuR+3np7Jz5fiGQyzojhI7jt1o8zbco0PB4PNTXDKCoq7hcXQqWUqQ03NqCUYsfO7Tz06AOcOHkUXfeglEEwUMTNN3yIxRcuwe/z4/f7GTlyVFY76DjZaHD69CkaG89w4uRxHn/yUbZu24Ku+7jj43dwwcIL8fmCBANBhg0bZilUhdNrGClOnDhBIpGgqbmJN97YzLPPP0F9YwMej49UKklZSSnf+od/YsG8hdijxFxvmXwQkc1KqYW517vUwEVkDPAHoNaK8S6l1E9E5LvAZ4E669F/VObmVoMEQjBYxLhxE9ITWbru4dU1qzh4aD+ppMHw4SNYsmQZwVAIgIqKKsaMHs/555/P1GnT+MOffkdj0xl2vbWLn/7sB/zt33ybGTNmFpwc7UwWgEg0QjKZwOv184XPfIVLL7kUr9dv3XfaNxW7du/IDM8UjBkzltmz5pqh5QzJZ82ay/a3trHqlZWUlJSkNYJzo4VbVkglJLefpP2+DZDwWlIn8J4/nOCNMxGfntZvxUr7fff/ieeff5ry8nI+fvsnuemDtxAKZTSRUCjE3DlzGTduLIlUnKefeYJIJEwiEXe4cnXHLGSm3TjeSuSBDSROtlHz3x/EM77clN5hlhL7U4TW1haeff4pHn70QY4eP4KuCRcvvoTrr7+Z+XMXUF5WjlPjAoWmQWVlOZWVC5g1azYXXLCYJ59+jJdXvUhbeyvvvLOXWCxGIBBMy9Yb0rPfHTaslmHDhjFp0hTKyso5fPQwdfV1iAijR47hqiuv4bzzJmdN+Nlpzm/ThZKSUkpKSpg8eQqtra28vffttLwXXbiUKy670mwrecJ0/u5riAiVlZVUVJQDwugxY2iPtPOHe38LKKLRBIsXzeWWmz5szZ3Y8nRu+hTRqa0dTm3tCKZOnU5jcxPrN6xj6rRJ3Pqh2/D7AmlTpo18abWvaZrOyJGjABgnwtQpU/D6dP5w7+8QMe83Njfy5vatzJwxi4A/YL1/9vMJ3fFCSQJ/q5SaASwGviwiM6x7P1JKzbX+Bg15pyspmakPENP2bTVCEBCNVMqwCihDysXFJVx5+dVcdflVGIZBIBRg34G9PLbiYZpbmlBGZnJIuvBisDVWhSIWC9PS2sriRUu49JLL8PkC5A7tsOQtKirCZ9nvFCrtDZCv4QUCQUaNHI2ua4RCGTudPft+LqBiKcJ/fIPEO/VoSsfAQHmF0A2z8ZxXicJAlEoT5tZtb/DEU49RVORn6uSpXH7ZVXlNPUpBeVklt9/2Saoqq4nHY9huec4J3U69dRCUAdG1B2h/cTuB2ZMI3joTe0IqtxGKCM3NZ/jDn37DXb/9OafrTuHx+Ljisvfxta98g0svvozysooOspq/7f1cFLru4fwZs/j0X3+e6665Ho/uIRaP0tzanJasr2DnCQrGj53A8OHDSaUSgIHX58Pr8XYg2tz3s1KSfsZsG7U1tfj9AQwjBaIoLS3H6/V1YxLxXMKM2+8LMGH8RPz+ACpl5sPoMWMpLS1NP9eZfpVdB7T0Z8AfxDBSlJeW4POabVN6MI+U7SmjCASCTJwwGU3zWLZ1HaVg48a1nDnTYD+YlbaeoksCV0qdUEptsb63Yu79PeqsYutnmO5TTrcg0NN2ZcNS6UxiVIaR7gaVUgT8QS695Apqa4aRSibweP1s2/kGR44c7H5eZ5WnOeFISnHpsuV4PJ68XgFOUrE7FedxB7nkZT9fFCwmlUhRUpJrK+5rmHHHNx4h/Ow2iJoTwzoavimVBC6figqZ15SYHZeRMli34XXaw21oupfpU2dSW1Obk/7sz5rqYYweOYZDh48Qi0Xzpr0QBIVxvI22360j1WZQ+vXlaLUldOwszLAikTb+suIhHn7sIUR0UimDuefP4dN3fIHx4yaZdtUO8Zrl09HNTFFTPYybb/owc+bMp7H5DI2NDWQ66Z6O3jKyZv4MnO5/Ihoej26qCdZ9I08c+eLN54ZnexlZQy1rAhnL8+jcattOWTsrb00XbGumJoJuzU85vXAKu0Bmx5G5YM+HdExj7jqEruuiVd5ijmCSyRipVAqv18u+/XvZ+dYOS77edeo98gMXkfHAPGC9dekrIrJNRH4rIhUF3vmciGwSkU11dXX5HulzOLWJfHmcHkKKVQiWppqtAwvjx01k9KjxpFJJdN1Le3s7p+tOOrTh7psplFIYBsydu4DZs+ZmDcPzaYQAonXu5+oM46qrrubvvvktzpt4XjoFVszdkq8r2TMygmqLEXlyD7FdjaZdEIOkL0nwkqn459fah6lh7zbY2hbmyJHDBAIBjJRhegN1ID5Jd1pgmlNuv/2TXHfNB7I8IrLTXkDelCLy3G5iz+2maPkkAsvGIVomb7P955OsWbeaBx64H03zkkjEqK6s4Auf+wqjRozOKhPnu4UbsHltzKixXHHpVbS1tnGmsSHPc72BU/PPjlpEs7sWrIpdMBSn/PnroGb+FWhD/Tl/li9+EAwUBvYZrNno2DF1amPGTmhmkVN2fD1Jr5OD4vEYI0eOprSkCEWKcCTMypeeJxqLkt1Oe56f3fZCEZFi4BHgb5RSLSLyC+B7VqzfA34AfCr3PaXUXcBdYE5i9ljCs4RdIDmjGmsCzjaCQsacQtpWbg+JfX4flZWVppnFupdKWntYizPjuyZxXde5/v0f5Jr3XU1RUWaol9VxWJ2JQjAs05sy+5l0mvJrQIqJ489j4viJDltx5l5vbOH5Gnlidz3hx99ErGG8IQpteIDgDTOhyJd5WRSaEmLRdpqbGs0JJ1LsO7iXxqYzVFXWpBuikziUUui6zrKLl7Ps4uWIkrwNtBBSR1to+f6LqCoPoQ9fiD66lOwFO5n8OHHiOA8+dD+RWIxQKEBrazs33XAr06dON5+TbN/r/FqsfU+ynl24cBFzzp9Lc1MrzobqnFjrKfLXAXuEqWfmTVAdij3f3E1+TypHS0i/U7genQttPJ+s2RoxpNuhODos6KzPymu7tn6R3a7Na4U4O1c7z20nZmdvjlraw60smH8Buuj8ZcWDBIMh3nhzCwcP7WfGtPMt2XN9/LuHbtUkEfFikve9Sqm/WEKeUkqllDme+zXQT06hvYTdu9oV3FlgyvmnSCaTtLQ1o2mWKUM0/IFQjxqgaUMzvwcCIUpKyrv3vrL+pTuZwjFktLF8+2ufbePK0Qjsr9EUkb/sILGnLhOfxAjNn4Jvydi0R0c6bhFE09A95kSnruns3vMWmzZtIJFIFIjX/BSH8cg5PhKxTpRXmVVx9mSvSinafryG+L6jBJdMI3DVJPDo6XzIPG9+f/6lZ9m1ZxeBoI9oNMLE8ZO57toPYnfimc9s5Dc9ZF8bNXIU3/qH73DR4qXOp/Jldo/QldkjPZDJo9TljiQ6DTO3/K26WCiMvkancWROD0lPRPcmHvOLHXT3yrvjfchV7iKRCIZh4Pf6ueTi5RSHShAxV2U/89zTZDI2X9hOQsqPLplETGnuBt5SSv3Qcd25jPAmYEdXYfU/8lU2sRVdNCwiVwpsezlYgzI4fuIYR48cxePxkkwmqaioZHjtcIcNzAyvk+it207NLI9M9m1xDn5NVboDHReoSJIeLTvDztYIewSlwMhUHLtSJ/bX0XbPBszc85jNx+8l9OkFaCV+23poxm+RZFGomNraWhKJBCJCuD3Mn+//Iy+vet66lht5RhtxTgLb6TdvZAlrvaWIvriPtj+/jlZVTNEtC/CMKrFmOZwdnPn8mcYGnnnuSXxec8IvmUhy+aWXU1Fe6ezHcXaM+fM/O58z5aszdcqMdJ3pDel1/m4mhwQN5+HNnXb9BcO0R4IWGal8OzYOLJyde1ciFW4z2byQG1bPy0ywz3QFs+7EYnFSKXOh0aiRo5g6ZTrxeAJ/wM8rr73M4SOH8nBErqJROMbuqJJLgY8Dl4vIVuvvOuD7IrJdRLYBlwHf6GYqBxjK0lYE80R0G059w8zIdevXcvLkMTy6TioRZ/GiJYwdOz4rnHcrFJk9TwBEmYTc/vPNJE+eQceDjoGiDf+0MQSumpzX3AKmPXvKeZOJhttAwOP1cPjYIX780x/w23vuoqGh3qFNQ/6RRG64pqe13WEASFOYth+uInGmkeCFMwjcNA0lYj2lsCes7fc3b9nEiRMn8PlMH93y0nIuWHhhr/Ou/yHmfIMI9r4n5oDEoHfn1Zmbo5l9cW/Dem/BrqaaZk6m+vw+ysorWLx4CX6/H6/HR139SV559eX0aLDjxG3XBNMdL5TVSilRSs12ugwqpT6ulJplXf+gUupEbxLcf8hMxoGR/kwPYwyIxeOsfv1VHnrkfgwMWtvbuGjxEm695SOW76Y92dG7odughuBosCYBxvfX0X7PGkAnZZOnplP02UWIVy+oCYkIV1x2DVMmT6etrRVQ+AMBEqkkf/jT3Xz9m1/m6WeeoKWlOctzoKtZfsFALG1dpRRtv3+TyIbdeItKKP3WZWjF1sKVLO0mYxbZsmUDhmESVCqVYsTIUYwcObJfzAPnAqIMNDF90zWtF6MvMM18ebbXHYr5MlBQShGNRu0feD1ezp8+i2E1taRSBkVFIV597SXOnDnTaTh19acL3nv3LqUvCHNPDUMZKBGMlKLN2pwoGg3T1NTEq6tf5smnV1BXV0dJSQnXX3cdn73js1RV2WuZoC9smYMZ4pwrADAU4d9sJRmLohMy+zoVxz+6hsDNM1GiOtqpHQQ8atRovvn1O/nef3yH0/WnCQaD6LpOaXkZh48e5Ac//i9efuUlbrrxFmZMm0F5eSWda+GmAcz+S751mvaHNpJqilD62SvwXzTWmRrA3hvGLP94PM7JU8fTq+uUUowZMxafLzAkScrOahEhEo6wb/8+wuHI2YbGkaMHMUeZOspImYQ+BPNloGDWKaG9rc0xsoSxY8cxZ/Ycjp84htfj5eCRg6zfuJZrr35/TgiWoiGKZ557omA870ECNwCNgL+IU6dP8eOffB/do5NKpWgPt3PkyFFOnDrOsOoabrnxw8yZM49lSy+1GrbdUN79FTnj9WEO0pJ7ThFdsRVJeRCsDhBF4JaZeMr8lg3W0nULeMvMnj2bO//+Ozz8lwfYum0LsVgMv99HqCiEYRis3/Q6u9/eyaKFF/KB627k/JmzHZsRdZTQNLILRluM8MNbib5xGO/EkZR+Yyn2JKhSYhVX9qq8lpYWmlua8Hg86XulJaXWYouhNqqyRxUausfDiVPH+dH/fh+xxic9hQYYKoWhUmiaRsqeCxlq2TIIIJaCoOumn3ooWMyCeYt4edVLJJIJkokUGzeuZemSiym11nDYa1ZEhIbGep5/vvAayfcggVsz12KubmxtbUOR4uDhQxw/cZRgMITX66Gmppbrrr2eabY7mcOlyJ5t7tUk4SBHZl7cQNAIP/U2saN1ePBgmBSOXhwg+IEZKJ+GKC1vVjjd1DRNY8H8CxgzeiyrXl3JU8+uYP+B/QT8Pnz+AEVFxUSiUV5+5SV27NzOrbd8hGuvvoGioqICEpofyW0nzYnVmEHpFy9Gn1hlG7ms2V3VgXzi8YTlBWMuUkFBaWkpup5tVRwa2nhmJsBIGVRWVnPxkospLi6xFqj1LDRd83D46BFWv/6qtRIzBWfVFby3oZQiFo3g9fkoKytLX58zaz6TJk1m28438fp87HxrB/v372Xe3IUOF0SzTNetW8vOXdsLxvGeI3C7YUejEc6beB7/eOd3AKGxqYl777+H5557mpLyEt7as5Of/+p/ufPvv8PIEaNwUlp+39l3F0yKNjso41gLkVf2IG2etH+IgcK7YBSe8yqwF484/uX14wVB04Ta2uHc+MFbWHTBYp586gmeevZxWlpaKS4uxufzYxgGDWfquevuX1J35gwfu+2TlBSXOMKxtGsUKpag9cerSRw+Reh9swndNCt7Ey2hg2xKgcej4/F6UaSwa0UqaVhlq3CeWNObsjYnFTvuDd239ccuEYOUkaKyspJrr76eUaPGdO7CUCg0ETZv2cjr614jlVIopaEG2dkvZp/r8NQgs9q650qVY+LQMVo7a9ksF+BkKklTazOagM/rT8dVWVnJxYsvYfPmDfhLAzQ2N/LGG5uYNmUG/mDQcosUmlsaeenl56kZVgvszRvX4CqVfoA9NLHh8/morKxi4oSJ3Pl33+baa95Pa0sbXq+PTVs28vs/3U0sHiO7Ush7wJRimkM0pUhuPErizWOY2rhJ7ZpoBJdNRas2tWOzzmaTRWeTgX5/gAnjJ/CFz32Rf//ef7Ng3gJisSixWAxQeH0+DAVPrHiMTRvXmZqgwyfWPFhAiD20g7bHNiNlJQRvvwB9XGYzI9Iy5Y6UFOXl5ZSVlGOkUmbjFaGxuZFUKpkm794h27/33Jplcg79UObGbX6fn0Ag2OM/n8/vmM8YvHXcLDbT/7o3e7Sk23K6iHpbVtneWLnODiLCJcuWM3zYCOLxGIlEkvUb11HXUJeVit173mLzG5u5fPn7Csb0niPwtL+stYIrUwkEny/A17/6TebPWUg0GqW4uJinnnqMtetXY5tdcgvn3QvTm9hojRF+9W3UiXY0pWGIgBhotX58C0cgIdPTwxxgd686ZUhdw+v1MX/uQr733f/i85/5IpWV5SSTBiIevD6d9rC5T0lD1uY/5vupYy00/svzGJKk6P0zKXrfFHMP8k4as11mPp+PmppajFRmZW193SmSyZQlYw+yqltpxTE8PjekmNby09ro2fuc23vwDGZItk7lWPvQ03C6clntHfKt1KytHcHSpZcQiYTxej3sO7CXPe/swTBMJSkajZi8I3DdNdcXDPs9R+Di1IiUynzH/FkUKuX22z9BdVUVSik0j5ff/PZXHD12JB3CewJWMo1jLSRWH8QwQKFby+cFfWIlnokVliZs+YR0Z2fGDntKmPMLpSWl3HrzR/nm1+5kxPDhRCLtCILX5+HtvXvYf3C/w0ccjPYozd97kdjh43hHVlPy8QvRarNt5Z2TpTB3znw0a+GFiLD/wD6amhptaXuWX52g8PLtvkLOBmf0QSeRnucZpPMAaZGs+mCkCj7areAsd2Knx0hvEY1GaGltwefzU1FR0eH+tVd/gIrSchQGsXicVa+uJBqLoFAcP3mcDZvWMXfOPCZMOC9P6Cb6ncC72mWsn6TIe1UT03921szZXHn5VSgDgsEQR44e4t4//56Wlpb0++kFge9SLVwpQaUMEjtPkNhVhyZ62udaNAPfpJHoo8vJ7OfVecXvPJ/MYbBH93DRhRfz1S99Hb8/QDyewOv10drWxt539qRXZYIi8tQe2ldsRROh5JYF+C4Zh7NcC5GO8/qiCy5kxPBRRKNRfD4fp+pOsX7jWmtRkXQaTtfIHKBr7/dyrpCbtT3ZN6bTcNPhD846btuaAVqamyh0eHN3YBgG4XAYUOmTt3rbcaWSKRLxGLrusfaDd+ajYuKEScyft4hoJIrP5+eNNzexd9/bJBIJtr65hbq6epYtuZRgIFAwjvecBm4PwSWz9jz7jghFoWKuuOxqxowahWEkCQZDvPLay7y+bo315Dk47X2QQcDc9+TF/RjhGOaqVVNbJgTe6bVIWcDBS2c/4E579VgmqvnzL+TiJZcQCUdACYlEgvb2NrCmVZP7mmj//UaSdU34J4+i6JvLkKAX22+2kCAmmRrphlldNYzLll9BLGIttkDjhRefJRJtP8uUOOOy0oSB6YN+7rw4ckcag9300RewN9iy7ddNTY20t599ucViUU7XnwaEqsqqXpnQ7LIQTdLHIhpGtvkVFF6vh8uXX4nf60cEzjQ08PKqlbS3t7B6zSuUlZYx6/y5eKx9hPJhQAm8PzTxfEN2IduE4mzx9qVJ503hssuuIJVMAkI0FuXxFY9w6PABZ+jnYHiZf2vMgk+fwzxU7TGiz+0ls2Gn6W2ilxejn1/bkSgdJhSnXF3JqJTt9WEG6NF0LrjgAkKhAIaRRAyxbNWCEUvR/tBWYit3oeOh/L9uwDOqFNNvBlDS5YrvzDJnjRtvuIlJkyYRiZhzHjt3bePJJ1eQniy16kl38znznPl33/338o/fvpNIJGw/0avyKiSHM6+zns1bl1QHOYcSFPZKU1N2j0fn5KmT1NXVZU0aZtdB50jFmWbze1NTM++88zaaCBMmmEf8ZfKngBx5ysK+JiIkk0niiTiGYR/I4mwwpulu5szzmTJlKslkkqKiIjZuXMea11/jnb17WDh/AcOHD6cz9CuBD/RQzJzjUOkjEe2dk50mERMKTdO4+soPMHXSdGKJCD5/kD3v7Oa5558iHG6zQyS3gLvT0PM/k1tZcthRssnwnHd+CqKrD5E6VIdgLqbRMJ3VpKoE34zqtNS5MmfLpTh1+gTPPPs4DQ315lNZm22Z72Vsj6YdsrqyBo/XS9JI4Q14KasoRylIbDlO++/Xk0zGKbl9Kf4rz8POO0nLUMh8kpHR9l6oqa7lIx+6nZA/SDKZxB8Mcu/9f2TXnp1p8utgonCQX95ysAYTdfV1PPHMY+w7uAd/wFdQrrNBPhdNM12a2ZWpjiSVeZf070y+507OZyaa052jQ/yedNDnAiXFZYSCRYBC172cOHmcA4f2pk1slpTk1tBcKGWS69Fjhzl05CBFJaXMmTU7fa83yYpGI7S1teHzea1zb013T6d85WWVLF60FE3T8HoD1J2p4xe/+b8kkykWzl+cdy98J/qVwHNPyDiXM/KZntCx3aQSc8GJXRuFtGdJx4k1qK0dzi0fug0joTCMJAg8+cwKtu980xoS2T17x4bcXSLPfDfSDUeAaCxCKmUu/1aorI2lcl2SzlUeRle+g0EMEQ/mqj6F0hSeEWXow8yKJZ11OhYOHz7Ej37yPzz59OPp/HJW4ow1y/aZhmPHjqd3cquuqGTGzDlIc4yWH71GfM9x/OdPoOTvLkb57CpsHyOhKOwFKGnitn97PD6WLlnGtde+H2UYeLweGlvO8Ou77+LQoYOmXdWqI+ZK3M6I0Nr3UDPLbOvWLRw9dpQ5sxeiifcsfZRzUpBVDwwH2QrKks9wRqOccmZvlOTc9jRTLumIrHZjHqkmltvmYIAAtTW1jB93HslkChHTzLZh4wZaWpqxy8TcGdDcckHE6UVmrtC1k9vc3MwLK5/j2IljnD9jFuPHTrTe7zy9dtsrpFDZJxn5fP70weXZ+a7h9/uYO2ce1dXVJBJRRHTC7e2MGzOOyZOndClDd/cDP2jtPLhVRDZZ1ypF5AURecf67DjNmgN7Oamd+P5Bxr9TKYNUKom9l7C9g5vdALLN4uYwaNnSS7lk6XKrJ/XT1NzEvff/kcam7NOFeqKB5E+71QitBhcOt5FMJrHtqMrR+fV2a9LuQEUSxNYcQfBja7cigCeBb/pwKLLXgDmIuEAWVFRUECoq5tnnnqa+4XTmeeuwhIz5xNT2YvEYL696kWQyjlIpZs2Zz7jRY4k8spPIY1vwVIQo/fwSPFOqrY7NIidbZ+7ShJLd2MrLK/noh2/nmquuIRlPouke3tyxhV//7hccOHjAPJ6sUF6n93bP1vZOnj7JS6+sJBxuZ+JEpxfB2bm65ZPbhrl5lamYiDURn2sHzzYhOOy0aZLLxCH2nhHKJj0D51YouYpK/2/+paioqGDJ4qVoYq1L0DysWbeaVa+8RCwWT8uW2+HmjjbCkXaeeOpRXlj5LCXFpbz/2g9S5Dho+2yN4WZchqWEkT7+reP8mTBmzHjOnzELez2CUjBn9jxGjhjdJa/0RAO/TJk7EdpH298JrFRKTQZWWr97hHM19LI1vPQw3SqEcKSdxqYzWDoKBgrd48ka0mfEMXtWv8/Pp+74DGPHjCMajREKFbP1zS38+u5fEI22pxtK1iRSFwTb0W4Gtk0MIJGIUV9fb02AmHtznLbse/nD6P3ZerlI7DtDcm89gidtKFJKgZ5AO8+a5FEZw4Wzo7Rhp6e0pJTqYTUcOX6Q391zF80tzZYGZL+Q6ZwSyQT3P3gfW97cjKbpDKup5QPX3UjwQISmf38WgyT+6+YQvPl88GuWZ4yWFqEn9OjMw2HDRnDHJz/P5z7zJUpCxUTCYdatW8P3f/hvvPbqKgxrNOR429TMlWMnS2uDrUNHDnD3PXex8Y31+AMBxo0dm/1er8squ64lkgkikTCadSJPPB5Pj95y38mnNeZrgw1n6onE4ohoGIbizJkzxBOJvM8OhAlF04RLll3G0osuoanpDKIpwuFW7v3z73ngoXtpbM4cY5ch7syII5mMs33nm/zwx//NH/98D/FYjPddeS2LFi7OKJrdIG873R3buuLMmQbq6+qIx+Ppw0vycUJ5WTmLFizG5/OTSiYJBAJcsPBCvN7Ck5c2erOU/gZgufX998Aq4B+6+/K5L3DBUOZ+xijzZIzX1rzCqVMn8Xm9JHXFsWPH2b79TRbOv8AaMuaSrinj2DET+Nhf/TX/88P/SE82PPPc04ho3Hzzhxkzehw+jwcRPbMIogeFb35PkTIM4okYr69dzfoNa/F4PGgaGIaw8qXnmT51OjNnzkTXNDTRgdyzJfsO8U3HMRJhNLwmSQuISqHrRXjHloF1zFnWVv959hxRCkKhYiorKvH5fTz7wtMkFfz1x+5gxPAR1vDc1FbONDbwyKMP8sBDfyaRjFFaUs7Hbv8UC6bPp/Ej92EcqcM7sZbSTy9Gry2yNE57V0JriC8ZOs2HQvVOKUVVVTW33Phhpk2ezm/u+RVbt29iy5sb2bd/H8vXX87NN9zC5EnT0DU97T6ZHn8og8NHDrJ24xqeefYJDh06RDQapaiomNqa4elnSG+u1TPkzisYKgUqRSQW46VVL7Jv3158PrM5HztxnC1bNzF8+HB8fr/l657ZzKtQnTGMJArzmLnXVq+ydiH0oomwYeNa5s2Zy+JFS/B4PIimp9vLwMxtCaUlJXzly9+gvb2FNWtfI1RUSmNLI7/9w12sXfcaS5dcwsSJkygKFSFibuPQ3t7O0eNH2bljG29se4MTJ4+hlOKqy67h9ts+TllpmRm6M109aMt2Hra0tPLSqpW0tDQTiUV49LGH+cynvkhRqLij15BozJ41nxHDR7Prre0sXryE6TPO714udCfzReQA0IhZX3+llLpLRJqUUuXWfQEa7d85734O+BzA2LFjFxw8eDD3frcEPRvs3LWd+x74E/X1p2lvj3Dg4D40HTRNRzSdRCJGRXk106dOx+fzUlVZw5e+8BV8vo5+l83NTdx9z1088eSjiG42iLa2VkqKS6gsr2L+vIV84+t/i98f7Fa6nPm+/+A+HnjwzzQ21tPQUMehwweJxRN4vB5r4hDisRjFRaWMHzee6uoayssq+fjH/poRw0eSoZG+y8umrz9Fy/99DoxSxBrNKBVHKsoY9vIdeGePyBNvNnVmRuIGv/r1z7j7nt9QUlpMNBpl+PBRLJi3gJnTZxIMFXHw4H7Wrn2Nt97eg64Js2fN5hMf+wwXLbiI9h+tpfHfVpBKpaj+PzdT/PdLzMANcDiiZyItkBNd13V7kkloa2/l1dde5omnH2PX7p20NLdSXlbBjOkzmTplGhMnTMCj+4hGYxw9foR9+99hz9u7OHnqJP6An5KiEqZPnck1V1/HlZdfi9frceSX1uORea7sjz/xCC+8+BxtbW0cOXKQlLW9AQJJI4lHvIwZM4bysgrmz13Ih275SNo0INbwyTlZufvtndzz+9/R0tLIiZMnOF1/Gp/Pnng1zAleb4BxY8dRVTWMD3/oIyxcsAh7e95MuP2BzPwTQDQa5t77/sSzzz3F6fpTeLzm4dThcBhd0wgFQqaCpinC4QiJZAqf3wtKMXzYCK5//4189CO3EwxmTCd23e1OuuwR/563d/OXxx7myJFDnK47xcmTJ/D4PIhoRKNRxo0eR0VFBUuXXMJNN9zaYZO2X/z6p/z8lz/hn//pP7j5hluz7mmattlh/Uijuxr4xUqpYyIyDHhBRHbnJECJ5LeAqjyHGvdXQYtoaJpGSUkxFeVVzJ03l7LSMpShQNNIpeKcPHmKSCRKOBqhWrC2f4TMZIcZVnl5BR/9yMcoKS7hVN1J68R4iMfitDS3UFlZedbpSiYStLe1o2kaw2qHM2XqDCorq8yeWpkTmEoZ1NfX0dzcTCqVJB6PO+LrTX52JGGlIHGsEUPZp9mY+WCIwlfmR68tznrP3lgKnGXr3MRJ4+YbP0Rt7XC27XiTYyeOUXf6FC+/8iLPP/80Pr8Xn89HUVExV11xNQsWXMCypcuoLh9G/LUDtP5xNanWCEVXz6P4S4tIq75atuTdy4fChwpnTFlY9tAbWLxoCTvf2sGOHdvZvmsbx08cZf+Bd0gaSWKxGF6PB6/Xh8fjpaqymtkz5zJz5iymTpnGtGnTKSstt0YrnLU91XzVqekqNF3H5/UwYsRwpk2dRlVNtTkqUxCJhWlqbCISDhNLxGlubiYWi6W1v3x5kkgkScRjlJWVUlVdTXV1DUVFpShr/qWlpZlwWzuRSDuJRNLas6bQIdv9AzvOYLCIT37iUyxbdgkbNq5l564dnDp9ivb2NqKRCOFoGMNI4fMGqCivpqSkjKrqas6fcT5LFi9j6pRpOeFCZ/WkEBobz9DU2EhRcRELx11IdVVVeo5EKcWpkydpONNAIpHIWjlqZ915EyYxYfxEli5ZmhWu6mQNQbc08KwXRL4LtAGfBZYrpU6IeT7mKqXU1M7eXbhwodq0aVOP4jtb2HY5M7PMDPB4PNb+z5ln4vF4uhLa9ztb+pxMJkkmM+c42rY1Z9g9NZ8YhkHCsi+aQz0ty/5lN95EIuGYFNEsDam3jcf2T7X9qBUqEqf+mt/TvnoPugph2ipSGCqBb9YYajd8Ec2f3z7XmSxKKSKRsGkbbKintbWF5pZm/AE/ZSXllJdXMKJ2JEXFRYhA6lgbTX//BK0PbcA/eQTV930C75zMiKO/SMOuS42NDdTVnaapuYlwOEx7uJ1AwE9RqIhQqJjy8nIqK6ooKSk9p/LZrm/xuDlZ56wLYJ4uZE6AZ0wmPp/PnOjMCceGYRjEYrF0XfN6ven6nN2OzHe8Xi+6nmlLg2W5vVIGbW1t1NWdprGpkUgkTDjcTiqVJBQMEQyGKK+oorqqmrKysl6tunR2XrllYvOB02Rlc4em6VnlZePUqZPs37+Piy66iNzpybPWwEWkCNCUUq3W9/cB/wKsAD4J/Kf1+Xj3k94/sCuu/R2yK62IEAgEOlzLDcN5P1OxTc3UOdTqqWx2uJqm4ff7C97PTcu5tjkajRFSDRFE2ZvKqvQJPVqRB83vNWlfyPI86Y7bVShURDAYMrc6dZhcbIu6ORGvULEk4Ye20vbUG+ihIOX/5xq8s4abmS39TxgiQlVVDVVVNYDDm8EyaTuH2+eyfOywdV0nYC2xzo1T1/Us8nW+WyjfNE0jGAzmvSci+P3+tKkgM7IafBARSkqKKSkpJndXyYzIhRW03sTrLBPndTuvnJ1iPgwfPtyxcKd7+dsdE0ot8KglhAf4s1LqWRHZCDwoIp8GDgEf7laM/YDOCiWXyDt6hKisBpFbUXP9aPt7Aqfvh6y25p3+h9GeINkeRtBtB0sMW/OqLUuTVhZ5d1nhjA4NKstsY/m62N4tiTeO0/KvKzFaE5T+zXIC10zD0ECzPG4Uejfi7FvkTiRaF037qmT2Pul/WXp+H862sxmcxG0j29vEhNPfPfuzbzqi7rbJQnmd8QrKerpbYXZJ4Eqp/cCcPNcbgCu6en8g0VkFzUfSvfHlLkT0nRVAZ6aart7taVyFYQ8hVFohlvYkWiqKEg1NQUpAU0KKJIbPg5OuxXrP9kApLEPH67a/sU3eYC6DT7XHaPj8YyQa6wldNoOSzyxCyvxWV9P/uz/Y5Ox0sclcs+vOuZejK8WkO3W9u8hXjoNV6y6MnAnubiw66wm6yvMsSXKe66u8fFeeyJPrk90V8i1GKPReV8R9tig0MujKptynsCZvjJYoiVQUUXqO17KgKSBrKC7p97oOPE+anPYHzP3Hm7/1AtGd7+AdN4yyr16Ox7Fsv2cTln0F51YL2V42kK9xnltpOqub3dHMc+t5ZyZE53u5zw9GQjd1gkJ50Pedf0/5IJ/S1lUb7+z+u5LAzxV6UmHPtnKfzWigN/EBDi8SK05rsksTc3WfpszFMoKGEUk4X8yS9exMGrYXCxixBOF7NtN672p0v5+yTy8jcO1k0uRvm2BEOipX5xxdRyhZHVnfCtddW3a++tOXHf3A+Hz3BP3fqfR0tN0VejJiek8TeHczdSBdpDq73msbvG3GtcjbJlIllvXbIm6VfkZInW4B296LvdS6O6McAPOAXXtXQ+vMH5P4FcRf2k/Lz1dhtLZR9qnlFH/+IiSgp00VmpwreuwK0mmM2WU1OLTSXCLvily6qkc9CW+gcbZKUH/jbEb8uXhPE/i7Ab1tSPmquCjDOjpNgVLWfhMmCRttCWiJQonfnNpUWWsxKUxglruifVgwpD1KlEDynQZafvwKib3HCCyaQtm/XoVU24uiHLL1KrVDF70d0fX3c4MB/SXruYinu2G+Bw90cJFGlmIp2N4UBL2IeBGl8Nj6ucI0oTS0Ez/eAhj2Uh1HgF15/+Q8K6ZHSaouQtM/ryTy0jY8E8ZQ9evb0IaV9WlSXbh4N8Il8PcwHM5UYJtPlEJKfHj1IArzLBmTugUND0a4DeNAo2X4sBf6W5N8na1cyzHXYPl8q9Yk4Z+upvXPa9Cqy6j4l2vxTqvBkNR7V9124aKbcAncRfYEJqCXBpDiINg7/SlBIRhopJJR4ltPOCqORf7dtDdmOgsF4SRtd23gzH++gKc8QNmXlxO8bhp4QEPrH988Fy6GMFwCfy8jm7fThKlVhdDGlKIkib1axz4YQ+Ia8XVHUGlvFHH87yQqyTafSCxF+92baPr+s6DHKf3ohRR9dhGU+TAnTrs+Gs2Fi/c6XAJ/DyNjlTa/pSnWq+OdXIPSUohF6gbWySxGgNhbR4m/cRLBSJN+5mCFAlCZzXuIpQj/eTvNP1xJqr6RomsWUvKd96HXlqalEHJJ34ULF7lwCfy9jNx5RcdEo3fBSHQxpzA1Umho5nF0QOpoE/EXD1imbDHt5NZCTgP7kADSS8tV+tADBbEUkYd30PBPjxI/eoKipbMo//VNaLXFHQVz+duFi07hErgLc1Mqyf4evHQChEpRaCh00wYuKdPvOwrtj28yTSmGeReLrDNnZGbsM+YeKDqqOUrbz9fS8MUHMU61ELxwJhX3fRRPZVEOWVvnZPZfFrhwMSThEriL/BhXRvCyyRiEAcN0CUdA6WhKJ7GtjtZfrsc43pL27ZZczdkidDEMkrvraPr3lTTc+QSpWITAsqlU/ehGPCPKXKZ24eIs0Z3tZKcCDzguTQT+CSjH3BPcPt33H5VST/e1gC4GBpoIRR+bReTpNzASSXNnQgX2GZRGyiD88FYkKBR/fim+eSPNF63FObZbonG6jciz79D2p3XEVh1CVAz/silU/Ov78SwcnjmUwbV3u3DRY3RnN8I9wFwAEdGBY8CjwB3Aj5RS/3MuBXQxUBD8yybgWzqR2Kp9IB7T+c86pUcTHYkYRO/ZRGzDEUI3zyNw+WT0kSWgpTDqosTWHyLyzG7imw+QOh1FGTGCF55HxfdvwDdvFOiprvfAcuHCRUH0dCn9FcA+pdQhV2N6t0OhVQco+9rF1G85irTY276mzAU7SjDwouIavHma5refovl//ei+IJrSSSZbMSIpCINmCEriBC+fRs3dtyFjykFTYOiu+cSFi16gpzbw24D7HL+/IiLbROS3IlKR7wUR+ZyIbBKRTXV1dfkecTEoIaDp+C6eSOiv5pD0RlFi+qSo9In0KUxTiQc97EfqIXW8ncSJVrQ6QWvzoinBCKYo/tgihj18B9q4MkQTqzNw4cJFb9BtAhcRH/BB4CHr0i+A8zDNKyeAH+R7Tyl1l1JqoVJqYU1NTe+kddGvUCi06hDFX1xG4NIJKD2BvYegvcrG3qvQPGJN0ovuUxgoLYmM9FP61cup/O8bkPIAdpXTRKyDoQfv8VwuXAx29MSEci2wRSl1CsD+BBCRXwNP9rFsLgYUtmeJwjdrOOXf+QCNPE185dsYKoDgwT7MR1ea5f9t7u1tEEXTFfryiZR9ZinBq6da5O3ChYu+RE8I/KM4zCciMkIpdcL6eROwoy8FczHAsHeTtTae8i8bR9VPbqX5P58n8uAOVCyCiB8lGoayzSkJDMAzqZLiv1pE4LY5+KZUWSYTFy5c9DW6ReBinkZ/FfB5x+Xvi8hcTD+Cgzn3XAx1OE4gt45uwDuthsr/vpHwsim0/fAVoruPYh/IoHQd39haQjfNJPiJeXgmDUMLeQFFytq30IULF32LbhG4UqodqMq59vFzIpGLQQT78AXLzi2CNixI8acWEvzAdGJbjpPafQKtyIc+tRb/jGFIVQg0DUOywzDX97i2bhcu+hLuiTwu8iK9mDJ90Jp9TQMN9OHFhK6bAtdNMTe5slZqmjq7oKMs4tfM1Zj9foalCxfvfrgE7qJTmKd852Nex+mUStLGlsymhNYVAS3v+y5cuOgtXAJ3kR+dHLhqHt4g6XvpwxwkYy7BOrg489uFCxd9DZfAXfQYuYTu+nG7cDEwcJ0DXLhw4WKIwiVwFy5cuBiicAnchQsXLoYoXAJ34cKFiyEKl8BduHDhYojCJXAXLly4GKJwCdyFCxcuhihcAnfhwoWLIQqXwF24cOFiiMIlcBcuXLgYonAJ3IULFy6GKCS9EVF/RCbSCuzptwjPHtVA/UAL0Q24cvYtXDn7DkNBRhg6co5TSnU4VLi/N7Pao5Ra2M9x9hgissmVs+/gytm3GApyDgUZYejIWQiuCcWFCxcuhihcAnfhwoWLIYr+JvC7+jm+s4UrZ9/ClbNvMRTkHAoywtCRMy/6dRLThQsXLlz0HVwTigsXLlwMUfQbgYvINSKyR0T2isid/RVvdyAiB0Vku4hsFZFN1rVKEXlBRN6xPisGQK7fishpEdnhuJZXLjHxv1b+bhOR+QMs53dF5JiVp1tF5DrHvW9Zcu4Rkav7ScYxIvKyiOwSkZ0i8nXr+qDKz07kHGz5GRCRDSLypiXnP1vXJ4jIekueB0TEZ133W7/3WvfHD7Cc94jIAUd+zrWuD1g7Oisopc75H6AD+4CJgA94E5jRH3F3U76DQHXOte8Dd1rf7wT+awDkugSYD+zoSi7gOuAZzCOEFwPrB1jO7wJ/l+fZGVb5+4EJVr3Q+0HGEcB863sJ8LYly6DKz07kHGz5KUCx9d0LrLfy6UHgNuv6L4EvWt+/BPzS+n4b8EA/5WchOe8BPpTn+QFrR2fz118a+CJgr1Jqv1IqDtwP3NBPcZ8tbgB+b33/PXBjfwuglHoVOJNzuZBcNwB/UCbWAeUiMmIA5SyEG4D7lVIxpdQBYC9m/TinUEqdUEptsb63Am8Boxhk+dmJnIUwUPmplFJt1k+v9aeAy4GHreu5+Wnn88PAFdIPp2F3ImchDFg7Ohv0F4GPAo44fh+l80rZ31DA8yKyWUQ+Z12rVUqdsL6fBGoHRrQOKCTXYMzjr1jD0N86TFADLqc1fJ+HqY0N2vzMkRMGWX6KiC4iW4HTwAuY2n+TUiqZR5a0nNb9ZqBqIORUStn5+W9Wfv5IRPy5cloYDO2oINxJTBMXK6XmA9cCXxaRS5w3lTm2GnTuOoNVLgu/AM4D5gIngB8MqDQWRKQYeAT4G6VUi/PeYMrPPHIOuvxUSqWUUnOB0Zha/7SBlSg/cuUUkfOBb2HKewFQCfzDwEl49ugvAj8GjHH8Hm1dGxRQSh2zPk8Dj2JWxlP20Mn6PD1wEmahkFyDKo+VUqeshmMAvyYzrB8wOUXEi0mK9yql/mJdHnT5mU/OwZifNpRSTcDLwEWYJgd7iw6nLGk5rftlQMMAyXmNZapSSqkY8DsGUX72BP1F4BuBydYMtQ9zEmNFP8XdKUSkSERK7O/A+4AdmPJ90nrsk8DjAyNhBxSSawXwCWsWfTHQ7DAN9Dty7IY3YeYpmHLeZnklTAAmAxv6QR4B7gbeUkr90HFrUOVnITkHYX7WiEi59T0IXIVpr38Z+JD1WG5+2vn8IeAla8QzEHLudnTagmmnd+bnoGlHXaK/ZksxZ3ffxrSTfbu/4u2GXBMxZ/HfBHbasmHa51YC7wAvApUDINt9mMPlBKYt7tOF5MKcNf+Zlb/bgYUDLOcfLTm2YTaKEY7nv23JuQe4tp9kvBjTPLIN2Gr9XTfY8rMTOQdbfs4G3rDk2QH8k3V9ImYHshd4CPBb1wPW773W/YkDLOdLVn7uAP5ExlNlwNrR2fy5KzFduHDhYojCncR04cKFiyEKl8BduHDhYojCJXAXLly4GKJwCdyFCxcuhihcAnfhwoWLIQqXwF24cOFiiMIlcBcuXLgYonAJ3IULFy6GKP4f86dAOFXcjpYAAAAASUVORK5CYII=\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# taking a look at the subset y=300 to 400 and x=400 to 800\n", "plt.imshow(image[300:400, 400:800, :]);" ] }, { "cell_type": "markdown", "id": "89248c94-060a-4940-bd09-6df2998ef55f", "metadata": {}, "source": [ "We can also modify the image by using the pairwise multiplication of numpy on it to modify the colors of our pixels." ] }, { "cell_type": "code", "execution_count": null, "id": "a5577919-a67f-4a3c-9fc1-c56c38d25202", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# deleting the red channel and half the brightness of blue\n", "# we divide the image by 255.0 so the RGB values are between 0 and 1\n", "plt.imshow(image/255.0 * np.array([[[0.0, 1.0, 0.5]]]));" ] }, { "cell_type": "markdown", "id": "e6bb8720-73ef-4435-903e-a320b1587d8b", "metadata": {}, "source": [ "We can also assign certain values for a region of our image easily with this notation" ] }, { "cell_type": "code", "execution_count": null, "id": "ff3b763a-1107-4d4f-b178-0fc3e785fac9", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# assign green = 127 for region y=200 to 500 and x=100 to 600\n", "image[200:500, 100:600, 1] = 127\n", "plt.imshow(image);" ] }, { "cell_type": "code", "execution_count": null, "id": "2b1f8ff6-643d-4de3-95c0-ff412713cc1f", "metadata": {}, "outputs": [], "source": [] } ], "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" } }, "nbformat": 4, "nbformat_minor": 5 }