IR

D3/TP/TP_SETI_Kmeans/Kmeans.py

@@ -21,7 +21,7 @@ def kmeans(points = [0,0], K = 1):
         Pc_index.append(np.random.randint(0,N))
     Pc = points[Pc_index,:]
 
-    while (np.mean(distance(Pc,Pc_save)) > eps and iter < 3):
+    while (np.mean(distance(Pc,Pc_save)) > eps and iter < 10):
         iter += 1
         Pc_save = Pc
         # print(Pc)
@@ -74,9 +74,10 @@ def kmeans_image(path_image, K):
     # imgplot = plt.imshow(img_seg)
     return Pc, index, img_seg
 
-path_image = "fruits.jpg"
+path_image = "images/fruits.jpg"
 
-start_time = time.time()
-Pc, index, img_seg = kmeans_image(path_image=path_image, K=2)
-end_time = time.time()
-print(f"It took {end_time-start_time:.2f} seconds to compute")
+for K in range(1,21):
+    start_time = time.time()
+    Pc, index, img_seg = kmeans_image(path_image=path_image, K=K)
+    end_time = time.time()
+    print(f"It took {end_time-start_time:.2f} seconds to compute for K =", K)

D3/TP/TP_SETI_Kmeans/Kmeans_cuda.py

@@ -1,82 +0,0 @@
-import numpy as np
-import pycuda.autoinit
-import pycuda.driver as cuda
-from pycuda.compiler import SourceModule
-import time
-
-# Load the image and convert it to a NumPy array
-from PIL import Image
-im = Image.open('fruits.jpg')
-im_data = np.array(im)
-
-# Convert the image data to float32 and normalize it
-im_data = im_data.astype(np.float32) / 255
-
-# Create a CUDA kernel to perform K-means clustering
-kernel = """
-__global__ void kmeans(float *data, int *labels, float *centroids, int n, int k, int dim)
-{
-    int tid = blockIdx.x * blockDim.x + threadIdx.x;
-    if (tid >= n)
-        return;
-
-    float min_dist = 10000;
-    int min_centroid = -1;
-    for (int i = 0; i < k; i++)
-    {
-        float dist = 0.0;
-        for (int j = 0; j < dim; j++)
-        {
-            float diff = data[tid * dim + j] - centroids[i * dim + j];
-            dist += diff * diff;
-        }
-        if (dist < min_dist)
-        {
-            min_dist = dist;
-            min_centroid = i;
-        }
-    }
-    labels[tid] = min_centroid;
-}
-"""
-
-mod = SourceModule(kernel)
-kmeans = mod.get_function("kmeans")
-
-# Set the number of clusters and the number of iterations
-k = 2
-n_iter = 5
-
-# Initialize the centroids and labels
-centroids = np.random.rand(k, im_data.shape[-1]).astype(np.float32)
-labels = np.zeros(im_data.shape[:2], dtype=np.int32)
-
-def replace_with_nearest_centroid(centroids, colors):
-    # Compute the distance between each color and each centroid
-    distances = np.sqrt(np.sum((colors[:, :] - centroids) ** 2, axis=2))
-    
-    # Find the index of the centroid that is nearest to each color
-    nearest_centroids = np.argmin(distances, axis=1)
-    
-    # Replace each color with the nearest centroid
-    colors[:] = centroids[nearest_centroids]
-
-
-start_time = time.time()
-
-# Run the K-means algorithm
-for _ in range(n_iter):
-    kmeans(cuda.In(im_data), cuda.Out(labels), cuda.In(centroids), np.int32(im_data.shape[0] * im_data.shape[1]), np.int32(k), np.int32(im_data.shape[-1]), block=(1024,1,1), grid=(im_data.shape[0] * im_data.shape[1] // 1024 + 1, 1))
-
-    # Update the centroids
-    for i in range(k):
-        centroids[i] = np.mean(im_data[labels == i], axis=0)
-
-replace_with_nearest_centroid(centroids=centroids, colors=im_data)
-# Convert the labels back to the original image format
-labels = labels
-
-end_time = time.time()
-print(f"It took {end_time-start_time:.2f} seconds to compute")
-
-

D3/TP/TP_SETI_Kmeans/Kmeans_skcuda.py

@@ -1,23 +1,41 @@
-import numpy as np
-import cv2
 import cupy as cp
+import numpy as np
+from sklearn.cluster import KMeans
+from skimage import io
+import time
+
+# Load the image using skimage
+image = io.imread('fruits.jpg')
+
+# Convert the image to a CuPy array
+image_cp = cp.asarray(image)
+
+# Flatten the image into a 2D array of pixels
+image_flat = image_cp.get().reshape(image_cp.shape[0] * image_cp.shape[1], image_cp.shape[2])
+
+def Kmeans_cuda(K=1):
+    # Use KMeans to cluster the pixels into a specified number of clusters
+    kmeans = KMeans(n_clusters=K, random_state=0).fit(image_flat)
+
+    # Predict the cluster for each pixel
+    clusters = kmeans.predict(image_flat)
 
-# Load the image and convert it to a NumPy array
-image = cv2.imread("fruits.jpg")
-image = image.astype(np.float32)
+    # Create a new CuPy array to hold the modified image
+    new_image_cp = cp.empty_like(image_cp)
 
-# Use cupy to transfer the image to the GPU
-image_gpu = cp.asarray(image)
+    # Iterate over each pixel and assign its value to the corresponding cluster center
+    for i, cluster in enumerate(clusters):
+        new_image_cp[i // image_cp.shape[1], i % image_cp.shape[1]] = cp.asarray(kmeans.cluster_centers_[cluster])
 
-# Perform k-means clustering on the GPU
-cluster_centers_gpu, labels_gpu, _ = cp.cluster.kmeans(image_gpu.reshape(-1, 3), k=8)
+    # Convert the CuPy array back to a NumPy array
+    new_image = cp.asnumpy(new_image_cp)
 
-# Transfer the cluster centers and labels back to the CPU
-cluster_centers = cp.asnumpy(cluster_centers_gpu)
-labels = cp.asnumpy(labels_gpu)
+    # Save the modified image using skimage
+    io.imsave("fruits" + "_%d" % K + "_cuda.jpg", new_image)
 
-# Convert the image pixels to the closest cluster
-clustered_image = cluster_centers[labels].reshape(image.shape)
 
-# Save the clustered image as a PNG file
-cv2.imwrite("clustered_image.png", clustered_image)
+for K in range(1,256):
+    start_time = time.time()
+    Kmeans_cuda(K=K)
+    end_time = time.time()
+    print(f"It took {end_time-start_time:.2f} seconds to compute for K =",K)

D3/TP/TP_SETI_Kmeans/test.ipynb

@@ -1,237 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import matplotlib.pyplot as plt\n",
-    "import numpy as np\n",
-    "import scipy.spatial"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "clusters = 3\n",
-    "mean = np.random.randint(5, size=clusters)\n",
-    "sd = [0.25, 0.25, 0.3]\n",
-    "dim = 2\n",
-    "nb = 50\n",
-    "K= clusters"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def gen_points(mean=1,sd=0.5, nb=100, dim=2, clusters=2):\n",
-    "    size = []\n",
-    "    # for i in range(0,dim):\n",
-    "    size.append(nb)\n",
-    "    size.append(dim)\n",
-    "    points = np.random.normal(mean[0],sd[0],size=size)\n",
-    "    for i in range(1,clusters):\n",
-    "        points = np.concatenate((points,np.random.normal(mean[i],sd[i],size=size)),axis=0)\n",
-    "    \n",
-    "    return points"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def distance(points,Pc):   \n",
-    "    return scipy.spatial.distance.cdist(points[:,:], Pc[:,:])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def kmeans(points = [0,0], K = 1, nb=1, dim=2):\n",
-    "    # Initialisation K prototypes\n",
-    "    Pc_index = []\n",
-    "    Pc_save = np.zeros([K,dim])\n",
-    "    clusters = []\n",
-    "    iter = 0\n",
-    "    eps = 0.1\n",
-    "\n",
-    "    for i in range(0,K):\n",
-    "        Pc_index.append(np.random.randint(0,nb))\n",
-    "    Pc = points[Pc_index,:]\n",
-    "\n",
-    "    # print(Pc.shape)\n",
-    "    # print(points.shape)\n",
-    "\n",
-    "    while (np.mean(distance(Pc,Pc_save)) > eps and iter < 10):\n",
-    "        iter += 1\n",
-    "        Pc_save = Pc\n",
-    "        # print(Pc.shape[1])\n",
-    "        # toto = points[:,:Pc.shape[0]]\n",
-    "        # print(toto.shape)\n",
-    "        dist = distance(points=points[:,:Pc.shape[1]],Pc=Pc)\n",
-    "        clust = np.argmin(dist, axis=1)\n",
-    "        clust = np.expand_dims(clust, axis=0)\n",
-    "        points = np.append(points[:,:Pc.shape[1]], clust.T, axis=1)\n",
-    "        # print(points)\n",
-    "        Pc = np.zeros([K,dim])\n",
-    "        index = np.array([])\n",
-    "\n",
-    "        for n in range(0,2*nb):\n",
-    "            for k in range(0,K):\n",
-    "                index = np.append(index, (clust==k).sum())\n",
-    "                if points[n,-1] == k:\n",
-    "                    # print(points)\n",
-    "                    # print(Pc)\n",
-    "                    Pc[k,:] = np.add(Pc[k,:], points[n,:-1])\n",
-    "\n",
-    "        for k in range(0,K):\n",
-    "            Pc[k,:] = np.divide(Pc[k,:],index[k])\n",
-    "\n",
-    "        # print(Pc)\n",
-    "    return Pc, points\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "points = gen_points(mean,sd,nb,dim,clusters)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "Pc, clusters = kmeans(points,K=K,nb=nb,dim=dim)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def img_2_mat(my_img):\n",
-    "    mat = my_img.reshape(my_img.shape[0]*my_img.shape[1],my_img.shape[2])\n",
-    "    return mat\n",
-    "\n",
-    "def mat_2_img(mat,my_img):\n",
-    "    img_seg = mat.reshape(my_img.shape[0], my_img.shape[1], my_img.shape[2])\n",
-    "    return img_seg\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "(103230, 3)\n"
-     ]
-    }
-   ],
-   "source": [
-    "from skimage import io\n",
-    "\n",
-    "path_image = \"fruits.jpg\"\n",
-    "my_img = io.imread(path_image)\n",
-    "Mat = img_2_mat(my_img)\n",
-    "print(Mat.shape)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[[[0. 1. 2.]\n",
-      "  [0. 1. 2.]\n",
-      "  [0. 1. 2.]]\n",
-      "\n",
-      " [[0. 1. 2.]\n",
-      "  [0. 1. 2.]\n",
-      "  [0. 1. 2.]]]\n",
-      "[[0. 1. 2.]\n",
-      " [0. 1. 2.]\n",
-      " [0. 1. 2.]\n",
-      " [0. 1. 2.]\n",
-      " [0. 1. 2.]\n",
-      " [0. 1. 2.]]\n",
-      "[[[0. 1. 2.]\n",
-      "  [0. 1. 2.]\n",
-      "  [0. 1. 2.]]\n",
-      "\n",
-      " [[0. 1. 2.]\n",
-      "  [0. 1. 2.]\n",
-      "  [0. 1. 2.]]]\n"
-     ]
-    }
-   ],
-   "source": [
-    "A = np.zeros((2,3,3))\n",
-    "for i in range(3):\n",
-    "    A[:,:,i] = i\n",
-    "\n",
-    "print(A)\n",
-    "\n",
-    "B = img_2_mat(A)\n",
-    "\n",
-    "print(B)\n",
-    "B[0,:] = np.array([0,0,0])\n",
-    "A = mat_2_img(B,A)\n",
-    "\n",
-    "print(A)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3.9.4 64-bit",
-   "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": "3.9.4"
-  },
-  "orig_nbformat": 4,
-  "vscode": {
-   "interpreter": {
-    "hash": "2ef431f6525756fa8a44688585fa332ef3b2e5fcfe8fe75df35bbf7028a8b511"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

D3/TP/TP_SETI_MLP/TP2.ipynb

@@ -1851,7 +1851,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.4"
+   "version": "3.9.4 (tags/v3.9.4:1f2e308, Apr  6 2021, 13:40:21) [MSC v.1928 64 bit (AMD64)]"
   },
   "orig_nbformat": 4,
   "vscode": {