mnisyif/semantics
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Incorporate Cupy for GPU acceleartion support

Browse source
This commit is contained in:
Murtadha 2024-09-26 21:06:51 -04:00
parent 1f4e31fe70
commit 2ea7b8c4a7
1 changed files with 113 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

144
bel_NN_dynamic.ipynb
View file

@ -2,24 +2,55 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import os\n",
"\n",
"import numpy as np\n", "import numpy as np\n",
"import pandas as pd\n", "import pandas as pd\n",
"import cupy as cp\n",
"\n",
"from sklearn.model_selection import train_test_split\n", "from sklearn.model_selection import train_test_split\n",
"from itertools import product" "from itertools import product"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"GPU is available. Using CuPy for GPU acceleration.\n"
]
}
],
"source": [
"try:\n",
" import cupy as cp\n",
" if cp.cuda.is_available():\n",
" print(\"GPU is available. Using CuPy for GPU acceleration.\")\n",
" xp = cp\n",
" else:\n",
" print(\"GPU is not available. Falling back to NumPy on CPU.\")\n",
" xp = np\n",
"except ImportError:\n",
" print(\"CuPy not found. Using NumPy on CPU.\")\n",
" xp = np"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"data = pd.read_csv('data/bel_data_test.csv')\n", "data = pd.read_csv('data/bel_data_test.csv')\n",
"data = np.array(data)\n", "data = xp.array(data)\n",
"\n", "\n",
"# Split data\n", "# Split data\n",
"X = data[:, 1:].T\n", "X = data[:, 1:].T\n",
@ -40,9 +71,18 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Input layer size: 1024\n",
"Output layer size: 61\n"
]
}
],
"source": [ "source": [
"# Determine input and output layer sizes\n", "# Determine input and output layer sizes\n",
"input_size = X_train.shape[0]\n", "input_size = X_train.shape[0]\n",
@ -54,7 +94,18 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14, "execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"X_train, Y_train = xp.array(X_train), xp.array(Y_train)\n",
"X_val, Y_val = xp.array(X_val), xp.array(Y_val)\n",
"X_test, Y_test = xp.array(X_test), xp.array(Y_test)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -63,23 +114,23 @@
" L = len(layer_dims)\n", " L = len(layer_dims)\n",
" \n", " \n",
" for l in range(1, L):\n", " for l in range(1, L):\n",
" params[f'W{l}'] = np.random.randn(layer_dims[l], layer_dims[l-1]) * np.sqrt(2. / layer_dims[l-1])\n", " params[f'W{l}'] = xp.random.randn(layer_dims[l], layer_dims[l-1]) * xp.sqrt(2. / layer_dims[l-1])\n",
" params[f'b{l}'] = np.zeros((layer_dims[l], 1))\n", " params[f'b{l}'] = xp.zeros((layer_dims[l], 1))\n",
" \n", " \n",
" return params" " return params"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 15, "execution_count": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def ReLU(Z):\n", "def ReLU(Z):\n",
" return np.maximum(Z, 0)\n", " return xp.maximum(Z, 0)\n",
"\n", "\n",
"def softmax(Z):\n", "def softmax(Z):\n",
" A = np.exp(Z) / sum(np.exp(Z))\n", " A = xp.exp(Z) / sum(xp.exp(Z))\n",
" return A\n", " return A\n",
"\n", "\n",
"def forward_prop(X, params):\n", "def forward_prop(X, params):\n",
@ -91,13 +142,13 @@
" A_prev = A\n", " A_prev = A\n",
" W = params[f'W{l}']\n", " W = params[f'W{l}']\n",
" b = params[f'b{l}']\n", " b = params[f'b{l}']\n",
" Z = np.dot(W, A_prev) + b\n", " Z = xp.dot(W, A_prev) + b\n",
" A = ReLU(Z)\n", " A = ReLU(Z)\n",
" caches.append((A_prev, W, b, Z))\n", " caches.append((A_prev, W, b, Z))\n",
"\n", "\n",
" WL = params[f'W{L}']\n", " WL = params[f'W{L}']\n",
" bL = params[f'b{L}']\n", " bL = params[f'b{L}']\n",
" ZL = np.dot(WL, A) + bL\n", " ZL = xp.dot(WL, A) + bL\n",
" AL = softmax(ZL)\n", " AL = softmax(ZL)\n",
" caches.append((A, WL, bL, ZL))\n", " caches.append((A, WL, bL, ZL))\n",
"\n", "\n",
@ -107,10 +158,14 @@
" return Z > 0\n", " return Z > 0\n",
"\n", "\n",
"def one_hot(Y):\n", "def one_hot(Y):\n",
" one_hot_Y = np.zeros((Y.size, Y.max() + 1))\n", " # one_hot_Y = xp.zeros((Y.size, Y.max() + 1))\n",
" one_hot_Y[np.arange(Y.size), Y] = 1\n", " # one_hot_Y[xp.arange(Y.size), Y] = 1\n",
" one_hot_Y = one_hot_Y.T\n", " # one_hot_Y = one_hot_Y.T\n",
" return one_hot_Y\n", " # return one_hot_Y\n",
" Y = Y.astype(int)\n",
" one_hot_Y = xp.zeros((Y.size, int(xp.max(Y)) + 1))\n",
" one_hot_Y[xp.arange(Y.size), Y] = 1\n",
" return one_hot_Y.T\n",
"\n", "\n",
"def backward_prop(AL, Y, caches):\n", "def backward_prop(AL, Y, caches):\n",
" grads = {}\n", " grads = {}\n",
@ -120,17 +175,17 @@
"\n", "\n",
" dAL = AL - Y\n", " dAL = AL - Y\n",
" current_cache = caches[L-1]\n", " current_cache = caches[L-1]\n",
" grads[f\"dW{L}\"] = 1 / m * np.dot(dAL, current_cache[0].T)\n", " grads[f\"dW{L}\"] = 1 / m * xp.dot(dAL, current_cache[0].T)\n",
" grads[f\"db{L}\"] = 1 / m * np.sum(dAL, axis=1, keepdims=True)\n", " grads[f\"db{L}\"] = 1 / m * xp.sum(dAL, axis=1, keepdims=True)\n",
" dA_prev = np.dot(current_cache[1].T, dAL)\n", " dA_prev = xp.dot(current_cache[1].T, dAL)\n",
"\n", "\n",
" for l in reversed(range(L-1)):\n", " for l in reversed(range(L-1)):\n",
" current_cache = caches[l]\n", " current_cache = caches[l]\n",
" dZ = dA_prev * ReLU_deriv(current_cache[3])\n", " dZ = dA_prev * ReLU_deriv(current_cache[3])\n",
" grads[f\"dW{l+1}\"] = 1 / m * np.dot(dZ, current_cache[0].T)\n", " grads[f\"dW{l+1}\"] = 1 / m * xp.dot(dZ, current_cache[0].T)\n",
" grads[f\"db{l+1}\"] = 1 / m * np.sum(dZ, axis=1, keepdims=True)\n", " grads[f\"db{l+1}\"] = 1 / m * xp.sum(dZ, axis=1, keepdims=True)\n",
" if l > 0:\n", " if l > 0:\n",
" dA_prev = np.dot(current_cache[1].T, dZ)\n", " dA_prev = xp.dot(current_cache[1].T, dZ)\n",
"\n", "\n",
" return grads\n", " return grads\n",
"\n", "\n",
@ -144,15 +199,15 @@
" return params\n", " return params\n",
"\n", "\n",
"def get_predictions(AL):\n", "def get_predictions(AL):\n",
" return np.argmax(AL, axis=0)\n", " return xp.argmax(AL, axis=0)\n",
"\n", "\n",
"def get_accuracy(predictions, Y):\n", "def get_accuracy(predictions, Y):\n",
" return np.sum(predictions == Y) / Y.size" " return xp.sum(predictions == Y) / Y.size"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 16, "execution_count": 8,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -191,7 +246,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 17, "execution_count": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -210,7 +265,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 18, "execution_count": 10,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -222,7 +277,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -233,9 +288,36 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 12,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Performing grid search...\n",
"Training architecture: [1024, 64, 64, 61]\n"
]
},
{
"ename": "TypeError",
"evalue": "'ndarray' object cannot be interpreted as an integer",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[12], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# Perform grid search\u001b[39;00m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPerforming grid search...\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 3\u001b[0m best_configs \u001b[38;5;241m=\u001b[39m \u001b[43mgrid_search\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mX_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlayer_configs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43malpha\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.01\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43miterations\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m4000\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 5\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124mTop 5 Architectures:\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 6\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m config, accuracy, _, _ \u001b[38;5;129;01min\u001b[39;00m best_configs[:\u001b[38;5;241m5\u001b[39m]:\n",
"Cell \u001b[0;32mIn[9], line 7\u001b[0m, in \u001b[0;36mgrid_search\u001b[0;34m(X_train, Y_train, X_val, Y_val, layer_configs, alpha, iterations, accuracy_threshold)\u001b[0m\n\u001b[1;32m 5\u001b[0m layer_dims \u001b[38;5;241m=\u001b[39m [input_size] \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mlist\u001b[39m(layer_config) \u001b[38;5;241m+\u001b[39m [output_size]\n\u001b[1;32m 6\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTraining architecture: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mlayer_dims\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 7\u001b[0m best_params, accuracy, acc_store \u001b[38;5;241m=\u001b[39m \u001b[43mgradient_descent\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mX_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlayer_dims\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43malpha\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43miterations\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maccuracy_threshold\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 8\u001b[0m results\u001b[38;5;241m.\u001b[39mappend((layer_config, accuracy, best_params, acc_store))\n\u001b[1;32m 9\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mArchitecture \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mlayer_dims\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m: Best Validation Accuracy: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00maccuracy\u001b[38;5;132;01m:\u001b[39;00m\u001b[38;5;124m.4f\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
"Cell \u001b[0;32mIn[8], line 8\u001b[0m, in \u001b[0;36mgradient_descent\u001b[0;34m(X_train, Y_train, X_val, Y_val, layer_dims, alpha, iterations, accuracy_threshold)\u001b[0m\n\u001b[1;32m 6\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(iterations):\n\u001b[1;32m 7\u001b[0m AL, caches \u001b[38;5;241m=\u001b[39m forward_prop(X_train, params)\n\u001b[0;32m----> 8\u001b[0m grads \u001b[38;5;241m=\u001b[39m \u001b[43mbackward_prop\u001b[49m\u001b[43m(\u001b[49m\u001b[43mAL\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcaches\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 9\u001b[0m params \u001b[38;5;241m=\u001b[39m update_params(params, grads, alpha)\n\u001b[1;32m 11\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m i \u001b[38;5;241m%\u001b[39m \u001b[38;5;241m100\u001b[39m \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n",
"Cell \u001b[0;32mIn[7], line 42\u001b[0m, in \u001b[0;36mbackward_prop\u001b[0;34m(AL, Y, caches)\u001b[0m\n\u001b[1;32m 40\u001b[0m L \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlen\u001b[39m(caches)\n\u001b[1;32m 41\u001b[0m m \u001b[38;5;241m=\u001b[39m AL\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m1\u001b[39m]\n\u001b[0;32m---> 42\u001b[0m Y \u001b[38;5;241m=\u001b[39m \u001b[43mone_hot\u001b[49m\u001b[43m(\u001b[49m\u001b[43mY\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 44\u001b[0m dAL \u001b[38;5;241m=\u001b[39m AL \u001b[38;5;241m-\u001b[39m Y\n\u001b[1;32m 45\u001b[0m current_cache \u001b[38;5;241m=\u001b[39m caches[L\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\n",
"Cell \u001b[0;32mIn[7], line 33\u001b[0m, in \u001b[0;36mone_hot\u001b[0;34m(Y)\u001b[0m\n\u001b[1;32m 32\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mone_hot\u001b[39m(Y):\n\u001b[0;32m---> 33\u001b[0m one_hot_Y \u001b[38;5;241m=\u001b[39m \u001b[43mxp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mzeros\u001b[49m\u001b[43m(\u001b[49m\u001b[43m(\u001b[49m\u001b[43mY\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msize\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmax\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 34\u001b[0m one_hot_Y[xp\u001b[38;5;241m.\u001b[39marange(Y\u001b[38;5;241m.\u001b[39msize), Y] \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m 35\u001b[0m one_hot_Y \u001b[38;5;241m=\u001b[39m one_hot_Y\u001b[38;5;241m.\u001b[39mT\n",
"File \u001b[0;32m~/.pyenv/versions/semantics/lib/python3.12/site-packages/cupy/_creation/basic.py:248\u001b[0m, in \u001b[0;36mzeros\u001b[0;34m(shape, dtype, order)\u001b[0m\n\u001b[1;32m 229\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mzeros\u001b[39m(\n\u001b[1;32m 230\u001b[0m shape: _ShapeLike,\n\u001b[1;32m 231\u001b[0m dtype: DTypeLike \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mfloat\u001b[39m,\n\u001b[1;32m 232\u001b[0m order: _OrderCF \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mC\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[1;32m 233\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m NDArray[Any]:\n\u001b[1;32m 234\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Returns a new array of given shape and dtype, filled with zeros.\u001b[39;00m\n\u001b[1;32m 235\u001b[0m \n\u001b[1;32m 236\u001b[0m \u001b[38;5;124;03m Args:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 246\u001b[0m \n\u001b[1;32m 247\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 248\u001b[0m a \u001b[38;5;241m=\u001b[39m \u001b[43mcupy\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mndarray\u001b[49m\u001b[43m(\u001b[49m\u001b[43mshape\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43morder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43morder\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 249\u001b[0m a\u001b[38;5;241m.\u001b[39mdata\u001b[38;5;241m.\u001b[39mmemset_async(\u001b[38;5;241m0\u001b[39m, a\u001b[38;5;241m.\u001b[39mnbytes)\n\u001b[1;32m 250\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m a\n",
"File \u001b[0;32mcupy/_core/core.pyx:137\u001b[0m, in \u001b[0;36mcupy._core.core.ndarray.__new__\u001b[0;34m()\u001b[0m\n",
"File \u001b[0;32mcupy/_core/core.pyx:202\u001b[0m, in \u001b[0;36mcupy._core.core._ndarray_base._init\u001b[0;34m()\u001b[0m\n",
"\u001b[0;31mTypeError\u001b[0m: 'ndarray' object cannot be interpreted as an integer"
]
}
],
"source": [ "source": [
"# Perform grid search\n", "# Perform grid search\n",
"print(\"Performing grid search...\")\n", "print(\"Performing grid search...\")\n",