oskar/nn-from-scratch
1
0
Fork 0
Code Issues Pull requests Actions Packages Projects Releases Wiki Activity
nn-from-scratch/add-sc.ipynb

1065 lines
733 KiB
Plaintext
Raw Normal View History

add, not working
2025-11-05 17:53:45 +01:00
{
"cells": [
{
"cell_type": "code",
"id": "initial_id",
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T14:14:33.168058Z",
"start_time": "2025-11-05T14:14:33.163995Z"
}
},
"source": [
"from math import floor\n",
"\n",
"import numpy as np\n"
],
"outputs": [],
"execution_count": 23
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:55:56.162948Z",
"start_time": "2025-11-05T13:55:56.157819Z"
}
},
"cell_type": "code",
"source": [
"# nn_architecture = [\n",
"# {\"input_dim\": 2, \"output_dim\": 4, \"activation\": \"relu\"},\n",
"# {\"input_dim\": 4, \"output_dim\": 6, \"activation\": \"relu\"},\n",
"# {\"input_dim\": 6, \"output_dim\": 6, \"activation\": \"relu\"},\n",
"# {\"input_dim\": 6, \"output_dim\": 4, \"activation\": \"relu\"},\n",
"# {\"input_dim\": 4, \"output_dim\": 1, \"activation\": \"sigmoid\"},\n",
"# ]\n",
"nn_architecture = [\n",
" {\"input_dim\": 2, \"output_dim\": 25, \"activation\": \"relu\"},\n",
" {\"input_dim\": 25, \"output_dim\": 50, \"activation\": \"relu\"},\n",
" {\"input_dim\": 50, \"output_dim\": 50, \"activation\": \"relu\"},\n",
" {\"input_dim\": 50, \"output_dim\": 25, \"activation\": \"relu\"},\n",
" {\"input_dim\": 25, \"output_dim\": 20, \"activation\": \"sigmoid\"},\n",
"]"
],
"id": "48cafaf4b64967bb",
"outputs": [],
"execution_count": 5
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:55:58.151744Z",
"start_time": "2025-11-05T13:55:58.145779Z"
}
},
"cell_type": "code",
"source": [
"def init_layers(nn_architecture, seed = 99):\n",
" np.random.seed(seed)\n",
" number_of_layers = len(nn_architecture)\n",
" params_values = {}\n",
"\n",
" for idx, layer in enumerate(nn_architecture):\n",
" layer_idx = idx + 1\n",
" layer_input_size = layer[\"input_dim\"]\n",
" layer_output_size = layer[\"output_dim\"]\n",
"\n",
" params_values['W' + str(layer_idx)] = np.random.randn(\n",
" layer_output_size, layer_input_size) * 0.1\n",
" params_values['b' + str(layer_idx)] = np.random.randn(\n",
" layer_output_size, 1) * 0.1\n",
"\n",
" return params_values\n"
],
"id": "d13137630b41b756",
"outputs": [],
"execution_count": 6
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:56:00.540357Z",
"start_time": "2025-11-05T13:56:00.536032Z"
}
},
"cell_type": "code",
"source": [
"params = init_layers(nn_architecture)\n",
"# params"
],
"id": "31f205147667dea6",
"outputs": [],
"execution_count": 7
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:56:04.702145Z",
"start_time": "2025-11-05T13:56:04.696109Z"
}
},
"cell_type": "code",
"source": [
"def sigmoid(Z):\n",
" return 1/(1+np.exp(-Z))\n",
"\n",
"def relu(Z):\n",
" return np.maximum(0,Z)\n",
"\n",
"def sigmoid_backward(dA, Z):\n",
" sig = sigmoid(Z)\n",
" return dA * sig * (1 - sig)\n",
"\n",
"def relu_backward(dA, Z):\n",
" dZ = np.array(dA, copy = True)\n",
" dZ[Z <= 0] = 0;\n",
" return dZ;"
],
"id": "c1b960e7dcf09d91",
"outputs": [],
"execution_count": 8
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:56:09.635495Z",
"start_time": "2025-11-05T13:56:09.630354Z"
}
},
"cell_type": "code",
"source": [
"def single_layer_forward_propagation(A_prev, W_curr, b_curr, activation=\"relu\"):\n",
" Z_curr = np.dot(W_curr, A_prev) + b_curr\n",
"\n",
" if activation == \"relu\":\n",
" activation_func = relu\n",
" elif activation == \"sigmoid\":\n",
" activation_func = sigmoid\n",
" else:\n",
" raise Exception('Non-supported activation function')\n",
"\n",
" return activation_func(Z_curr), Z_curr"
],
"id": "efae2e184daf2fce",
"outputs": [],
"execution_count": 9
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:56:11.655081Z",
"start_time": "2025-11-05T13:56:11.649147Z"
}
},
"cell_type": "code",
"source": [
"def full_forward_propagation(X, params_values, nn_architecture):\n",
" memory = {}\n",
" A_curr = X\n",
"\n",
" for idx, layer in enumerate(nn_architecture):\n",
" layer_idx = idx + 1\n",
" A_prev = A_curr\n",
"\n",
" activ_function_curr = layer[\"activation\"]\n",
" W_curr = params_values[\"W\" + str(layer_idx)]\n",
" b_curr = params_values[\"b\" + str(layer_idx)]\n",
" A_curr, Z_curr = single_layer_forward_propagation(A_prev, W_curr, b_curr, activ_function_curr)\n",
"\n",
" memory[\"A\" + str(idx)] = A_prev\n",
" memory[\"Z\" + str(layer_idx)] = Z_curr\n",
"\n",
" return A_curr, memory"
],
"id": "c3cd9e8f51dbe967",
"outputs": [],
"execution_count": 10
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:56:14.173107Z",
"start_time": "2025-11-05T13:56:14.167007Z"
}
},
"cell_type": "code",
"source": [
"def get_cost_value(Y_hat, Y):\n",
" m = Y_hat.shape[1]\n",
" cost = -1 / m * (np.dot(Y, np.log(Y_hat).T) + np.dot(1 - Y, np.log(1 - Y_hat).T))\n",
" return np.squeeze(cost)\n",
"\n",
"# an auxiliary function that converts probability into class\n",
"def convert_prob_into_class(probs):\n",
" probs_ = np.copy(probs)\n",
" probs_[probs_ > 0.5] = 1\n",
" probs_[probs_ <= 0.5] = 0\n",
" return probs_\n",
"\n",
"def get_accuracy_value(Y_hat, Y):\n",
" Y_hat_ = convert_prob_into_class(Y_hat)\n",
" return (Y_hat_ == Y).all(axis=0).mean()"
],
"id": "121416e7bbab57bb",
"outputs": [],
"execution_count": 11
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:56:16.868763Z",
"start_time": "2025-11-05T13:56:16.862696Z"
}
},
"cell_type": "code",
"source": [
"def single_layer_backward_propagation(dA_curr, W_curr, b_curr, Z_curr, A_prev, activation=\"relu\"):\n",
" m = A_prev.shape[1]\n",
"\n",
" if activation == \"relu\":\n",
" backward_activation_func = relu_backward\n",
" elif activation == \"sigmoid\":\n",
" backward_activation_func = sigmoid_backward\n",
" else:\n",
" raise Exception('Non-supported activation function')\n",
"\n",
" dZ_curr = backward_activation_func(dA_curr, Z_curr)\n",
" dW_curr = np.dot(dZ_curr, A_prev.T) / m\n",
" db_curr = np.sum(dZ_curr, axis=1, keepdims=True) / m\n",
" dA_prev = np.dot(W_curr.T, dZ_curr)\n",
"\n",
" return dA_prev, dW_curr, db_curr"
],
"id": "92e4b87664f18a63",
"outputs": [],
"execution_count": 12
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:56:20.146436Z",
"start_time": "2025-11-05T13:56:20.139340Z"
}
},
"cell_type": "code",
"source": [
"def full_backward_propagation(Y_hat, Y, memory, params_values, nn_architecture):\n",
" grads_values = {}\n",
" m = Y.shape[1]\n",
" Y = Y.reshape(Y_hat.shape)\n",
"\n",
" dA_prev = - (np.divide(Y, Y_hat) - np.divide(1 - Y, 1 - Y_hat));\n",
"\n",
" for layer_idx_prev, layer in reversed(list(enumerate(nn_architecture))):\n",
" layer_idx_curr = layer_idx_prev + 1\n",
" activ_function_curr = layer[\"activation\"]\n",
"\n",
" dA_curr = dA_prev\n",
"\n",
" A_prev = memory[\"A\" + str(layer_idx_prev)]\n",
" Z_curr = memory[\"Z\" + str(layer_idx_curr)]\n",
" W_curr = params_values[\"W\" + str(layer_idx_curr)]\n",
" b_curr = params_values[\"b\" + str(layer_idx_curr)]\n",
"\n",
" dA_prev, dW_curr, db_curr = single_layer_backward_propagation(\n",
" dA_curr, W_curr, b_curr, Z_curr, A_prev, activ_function_curr)\n",
"\n",
" grads_values[\"dW\" + str(layer_idx_curr)] = dW_curr\n",
" grads_values[\"db\" + str(layer_idx_curr)] = db_curr\n",
"\n",
" return grads_values"
],
"id": "2c8e4eed1846f003",
"outputs": [],
"execution_count": 13
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:56:23.516827Z",
"start_time": "2025-11-05T13:56:23.511647Z"
}
},
"cell_type": "code",
"source": [
"def update(params_values, grads_values, nn_architecture, learning_rate):\n",
" for layer_idx, layer in enumerate(nn_architecture, 1):\n",
" params_values[\"W\" + str(layer_idx)] -= learning_rate * grads_values[\"dW\" + str(layer_idx)]\n",
" params_values[\"b\" + str(layer_idx)] -= learning_rate * grads_values[\"db\" + str(layer_idx)]\n",
"\n",
" return params_values;"
],
"id": "16320b953a183511",
"outputs": [],
"execution_count": 14
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:56:29.549070Z",
"start_time": "2025-11-05T13:56:29.542074Z"
}
},
"cell_type": "code",
"source": [
"def train(X, Y, nn_architecture, epochs, learning_rate, verbose=False, callback=None):\n",
" # initiation of neural net parameters\n",
" params_values = init_layers(nn_architecture, 2)\n",
" # initiation of lists storing the history\n",
" # of metrics calculated during the learning process\n",
" cost_history = []\n",
" accuracy_history = []\n",
"\n",
" # performing calculations for subsequent iterations\n",
" for i in range(epochs):\n",
" # step forward\n",
" Y_hat, cashe = full_forward_propagation(X, params_values, nn_architecture)\n",
"\n",
" # calculating metrics and saving them in history\n",
" cost = get_cost_value(Y_hat, Y)\n",
" cost_history.append(cost)\n",
" accuracy = get_accuracy_value(Y_hat, Y)\n",
" accuracy_history.append(accuracy)\n",
"\n",
" # step backward - calculating gradient\n",
" grads_values = full_backward_propagation(Y_hat, Y, cashe, params_values, nn_architecture)\n",
" # updating model state\n",
" params_values = update(params_values, grads_values, nn_architecture, learning_rate)\n",
"\n",
" if(i % 1000 == 0):\n",
" if(verbose):\n",
" print(\"Iteration: {:05} - cost: {:.5f} - accuracy: {:.5f}\".format(i, cost, accuracy))\n",
" if(callback is not None):\n",
" callback(i, params_values)\n",
"\n",
" return params_values"
],
"id": "fce33f70bba3898",
"outputs": [],
"execution_count": 15
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:56:34.145803Z",
"start_time": "2025-11-05T13:56:33.471955Z"
}
},
"cell_type": "code",
"source": [
"import os\n",
"import tensorflow as tf\n",
"\n",
"import sklearn.datasets as ds\n",
"import sklearn.utils as su\n",
"from sklearn.datasets import make_moons\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"from matplotlib import cm\n",
"from mpl_toolkits.mplot3d import Axes3D\n",
"sns.set_style(\"whitegrid\")\n",
"\n",
"import keras\n",
"from keras.models import Sequential\n",
"from keras.layers import Dense\n",
"# from keras.utils import np_utils\n",
"from keras import regularizers\n",
"\n",
"from sklearn.metrics import accuracy_score"
],
"id": "cccd73b5018799d4",
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2025-11-05 14:56:33.582332: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
"2025-11-05 14:56:33.605140: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"2025-11-05 14:56:34.038968: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n"
]
}
],
"execution_count": 16
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:56:48.371160Z",
"start_time": "2025-11-05T13:56:48.367011Z"
}
},
"cell_type": "code",
"source": [
"# number of samples in the data set\n",
"N_SAMPLES = 1000\n",
"# ratio between training and test sets\n",
"TEST_SIZE = 0.1"
],
"id": "4f66ffa878f01c02",
"outputs": [],
"execution_count": 17
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T15:23:10.125780Z",
"start_time": "2025-11-05T15:23:10.110063Z"
}
},
"cell_type": "code",
"source": [
"def encode_add(i: int) -> float:\n",
" return float(i) / 10.0\n",
"\n",
"def decode_add(i) -> int:\n",
" return int(i[0] * 10 + i[1])\n",
"\n",
"def add(a:float,b:float):\n",
" r = a * 10.0 + b * 10.0\n",
"\n",
" r0 = floor(r % 10)\n",
" r1 = floor(r / 10)\n",
" return r1,r0\n",
"\n",
"def encode_to_vector(x:float,y:float):\n",
" i,j = add(x,y)\n",
" vector = np.zeros(20)\n",
" vector[i] = 1\n",
" vector[j+10] = 1\n",
" return vector\n",
"\n",
"# add(encode_add(2),encode_add(3))\n",
"# encode_to_vector(encode_add(2),encode_add(3))\n",
"\n",
"def make_sums(\n",
" n_samples=100, *, shuffle=True, noise=None, random_state=None, factor=0.8\n",
"):\n",
" X = []\n",
" y = []\n",
"\n",
" for i in np.linspace(0, 9, 10):\n",
" for j in np.linspace(0, 9, 10):\n",
" i_int = int(i)\n",
" j_int = int(j)\n",
" X.append([i_int, j_int])\n",
" y.append(encode_to_vector( encode_add(i_int), encode_add(j_int) ))\n",
"\n",
" X = np.array(X).T # Shape: (2, 100)\n",
" y = np.array(y).T # Shape: (20, 100)\n",
"\n",
" if shuffle and random_state is not None:\n",
" np.random.seed(random_state)\n",
" indices = np.random.permutation(X.shape[1])\n",
" X = X[:, indices]\n",
" y = y[:, indices]\n",
"\n",
" return X, y\n",
"\n",
"make_sums()\n",
"\n"
],
"id": "7ce930351bba500c",
"outputs": [
{
"data": {
"text/plain": [
"(array([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2,\n",
" 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4,\n",
" 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6,\n",
" 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 8, 8, 8, 8, 8, 8, 8, 8,\n",
" 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9],\n",
" [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 0, 1,\n",
" 2, 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, 3,\n",
" 4, 5, 6, 7, 8, 9, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, 3, 4, 5,\n",
" 6, 7, 8, 9, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, 3, 4, 5, 6, 7,\n",
" 8, 9, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9]]),\n",
" array([[1., 1., 1., ..., 0., 0., 0.],\n",
" [0., 0., 0., ..., 1., 1., 1.],\n",
" [0., 0., 0., ..., 0., 0., 0.],\n",
" ...,\n",
" [0., 0., 0., ..., 0., 1., 0.],\n",
" [0., 0., 0., ..., 0., 0., 1.],\n",
" [0., 0., 0., ..., 0., 0., 0.]], shape=(20, 100)))"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"execution_count": 50
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:38:02.731937Z",
"start_time": "2025-11-05T13:38:02.725571Z"
}
},
"cell_type": "code",
"source": [
"X, y = ds.make_circles(n_samples = N_SAMPLES, noise=0.2, random_state=100)\n",
"# X, y = make_moons(n_samples = N_SAMPLES, noise=0.2, random_state=100)\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=TEST_SIZE, random_state=42)"
],
"id": "bebe0ed00a2d514",
"outputs": [],
"execution_count": 136
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:38:25.210667Z",
"start_time": "2025-11-05T13:38:02.745281Z"
}
},
"cell_type": "code",
"source": [
"params_values = train(np.transpose(X_train), np.transpose(y_train.reshape((y_train.shape[0], 1))), nn_architecture, 30000, 0.01, verbose=True)\n",
"# params_values\n"
],
"id": "ce04892d496c5147",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Iteration: 00000 - cost: 0.69318 - accuracy: 0.50444\n",
"Iteration: 01000 - cost: 0.69315 - accuracy: 0.50444\n",
"Iteration: 02000 - cost: 0.69312 - accuracy: 0.50444\n",
"Iteration: 03000 - cost: 0.69310 - accuracy: 0.50444\n",
"Iteration: 04000 - cost: 0.69308 - accuracy: 0.50444\n",
"Iteration: 05000 - cost: 0.69306 - accuracy: 0.50444\n",
"Iteration: 06000 - cost: 0.69304 - accuracy: 0.50444\n",
"Iteration: 07000 - cost: 0.69301 - accuracy: 0.50444\n",
"Iteration: 08000 - cost: 0.69298 - accuracy: 0.50444\n",
"Iteration: 09000 - cost: 0.69296 - accuracy: 0.50444\n",
"Iteration: 10000 - cost: 0.69292 - accuracy: 0.50444\n",
"Iteration: 11000 - cost: 0.69288 - accuracy: 0.50444\n",
"Iteration: 12000 - cost: 0.69284 - accuracy: 0.50444\n",
"Iteration: 13000 - cost: 0.69278 - accuracy: 0.50444\n",
"Iteration: 14000 - cost: 0.69272 - accuracy: 0.50444\n",
"Iteration: 15000 - cost: 0.69265 - accuracy: 0.50444\n",
"Iteration: 16000 - cost: 0.69256 - accuracy: 0.50444\n",
"Iteration: 17000 - cost: 0.69244 - accuracy: 0.50444\n",
"Iteration: 18000 - cost: 0.69229 - accuracy: 0.50778\n",
"Iteration: 19000 - cost: 0.69210 - accuracy: 0.52778\n",
"Iteration: 20000 - cost: 0.69184 - accuracy: 0.54111\n",
"Iteration: 21000 - cost: 0.69148 - accuracy: 0.55778\n",
"Iteration: 22000 - cost: 0.69097 - accuracy: 0.58333\n",
"Iteration: 23000 - cost: 0.69021 - accuracy: 0.60222\n",
"Iteration: 24000 - cost: 0.68900 - accuracy: 0.62222\n",
"Iteration: 25000 - cost: 0.68693 - accuracy: 0.65111\n",
"Iteration: 26000 - cost: 0.68299 - accuracy: 0.66889\n",
"Iteration: 27000 - cost: 0.67457 - accuracy: 0.68222\n",
"Iteration: 28000 - cost: 0.65530 - accuracy: 0.67333\n",
"Iteration: 29000 - cost: 0.61861 - accuracy: 0.67111\n"
]
}
],
"execution_count": 137
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:38:25.280709Z",
"start_time": "2025-11-05T13:38:25.278689Z"
}
},
"cell_type": "code",
"source": [
"Y_test_hat, _ = full_forward_propagation(np.transpose(X_test), params_values, nn_architecture)\n",
"\n",
"acc_test = get_accuracy_value(Y_test_hat, np.transpose(y_test.reshape((y_test.shape[0], 1))))\n",
"print(\"Test set accuracy: {:.2f} - David\".format(acc_test))\n"
],
"id": "26e7a2a8848714d9",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Test set accuracy: 0.69 - David\n"
]
}
],
"execution_count": 138
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:43:01.544185Z",
"start_time": "2025-11-05T13:43:01.537741Z"
}
},
"cell_type": "code",
"source": [
"# boundary of the graph\n",
"GRID_X_START = -1.5\n",
"GRID_X_END = 1.5\n",
"GRID_Y_START = -1.5\n",
"GRID_Y_END = 1.5\n",
"# output directory (the folder must be created on the drive)\n",
"OUTPUT_DIR = \"./binary_classification_vizualizations/\"\n",
"os.makedirs(OUTPUT_DIR, exist_ok=True)\n",
"### Definition of grid boundaries\n",
"grid = np.mgrid[GRID_X_START:GRID_X_END:100j, GRID_Y_START:GRID_Y_END:100j]\n",
"grid_2d = grid.reshape(2, -1).T\n",
"XX, YY = grid"
],
"id": "b070f03d55981894",
"outputs": [],
"execution_count": 148
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:38:25.355642Z",
"start_time": "2025-11-05T13:38:25.347259Z"
}
},
"cell_type": "code",
"source": [
"def make_plot(X, y, plot_name, file_name=None, XX=None, YY=None, preds=None, dark=False):\n",
" if (dark):\n",
" plt.style.use('dark_background')\n",
" else:\n",
" sns.set_style(\"whitegrid\")\n",
" plt.figure(figsize=(16,12))\n",
" axes = plt.gca()\n",
" axes.set(xlabel=\"$X_1$\", ylabel=\"$X_2$\")\n",
" plt.title(plot_name, fontsize=30)\n",
" plt.subplots_adjust(left=0.20)\n",
" plt.subplots_adjust(right=0.80)\n",
" if(XX is not None and YY is not None and preds is not None):\n",
" plt.contourf(XX, YY, preds.reshape(XX.shape), 25, alpha = 1, cmap=cm.Spectral)\n",
" plt.contour(XX, YY, preds.reshape(XX.shape), levels=[.5], cmap=\"Greys\", vmin=0, vmax=.6)\n",
" plt.scatter(X[:, 0], X[:, 1], c=y.ravel(), s=40, cmap=plt.cm.Spectral, edgecolors='black')\n",
" if(file_name):\n",
" plt.savefig(file_name)\n",
" plt.close()"
],
"id": "553e08ddc23ab78c",
"outputs": [],
"execution_count": 140
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:47:50.552445Z",
"start_time": "2025-11-05T13:47:50.545245Z"
}
},
"cell_type": "code",
"source": "X.T",
"id": "b87560199ee27331",
"outputs": [
{
"data": {
"text/plain": [
"array([[-1.00304644, 0.27761395, 0.7121587 , ..., -0.13965464,\n",
" -0.68842612, 0.59102256],\n",
" [ 0.08532924, -1.33189304, 0.49761513, ..., -0.91986245,\n",
" -0.38146264, 0.40804492]], shape=(2, 1000))"
]
},
"execution_count": 158,
"metadata": {},
"output_type": "execute_result"
}
],
"execution_count": 158
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:46:41.287971Z",
"start_time": "2025-11-05T13:46:41.280330Z"
}
},
"cell_type": "code",
"source": "y",
"id": "e0c22b36e47fd9e4",
"outputs": [
{
"data": {
"text/plain": [
"array([0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,\n",
" 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0,\n",
" 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0,\n",
" 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1,\n",
" 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 1, 0,\n",
" 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0,\n",
" 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1,\n",
" 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 1, 0, 1, 0,\n",
" 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0,\n",
" 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,\n",
" 0, 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0,\n",
" 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0,\n",
" 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0,\n",
" 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,\n",
" 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1,\n",
" 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1,\n",
" 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1,\n",
" 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0,\n",
" 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n",
" 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 1,\n",
" 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 1,\n",
" 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1,\n",
" 0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0,\n",
" 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1,\n",
" 1, 1, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 1,\n",
" 0, 1, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0,\n",
" 1, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1,\n",
" 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1,\n",
" 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1,\n",
" 1, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 0, 1, 1,\n",
" 1, 0, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1,\n",
" 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1,\n",
" 1, 0, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1,\n",
" 0, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 0,\n",
" 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1,\n",
" 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 1, 1, 0, 1, 0,\n",
" 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0,\n",
" 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,\n",
" 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1,\n",
" 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0,\n",
" 0, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 1, 0,\n",
" 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0,\n",
" 1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0,\n",
" 1, 1, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0,\n",
" 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 1,\n",
" 1, 0, 1, 1, 0, 1, 1, 1, 1, 1])"
]
},
"execution_count": 157,
"metadata": {},
"output_type": "execute_result"
}
],
"execution_count": 157
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:38:25.471082Z",
"start_time": "2025-11-05T13:38:25.370173Z"
}
},
"cell_type": "code",
"source": " make_plot(X, y, \"Dataset\")",
"id": "36c83562b7404392",
"outputs": [
{
"data": {
"text/plain": [
"<Figure size 1600x1200 with 1 Axes>"
],
"image/png": "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
},
"metadata": {},
"output_type": "display_data",
"jetTransient": {
"display_id": null
}
}
],
"execution_count": 141
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:39:53.206765Z",
"start_time": "2025-11-05T13:39:27.866713Z"
}
},
"cell_type": "code",
"source": [
"from time import sleep\n",
"def callback_numpy_plot(index, params):\n",
" plot_title = \"NumPy Model - It: {:05}\".format(index)\n",
" file_name = \"numpy_model_{:05}.png\".format(index // 50)\n",
" file_path = os.path.join(OUTPUT_DIR, file_name)\n",
" prediction_probs, _ = full_forward_propagation(np.transpose(grid_2d), params, nn_architecture)\n",
" prediction_probs = prediction_probs.reshape(prediction_probs.shape[1], 1)\n",
" make_plot(X_test, y_test, plot_title, file_name=file_path, XX=XX, YY=YY, preds=prediction_probs, dark=True)\n",
"\n",
"# Training\n",
"params_values = train(np.transpose(X_train), np.transpose(y_train.reshape((y_train.shape[0], 1))), nn_architecture,\n",
" 30000, 0.01, False, callback_numpy_plot)"
],
"id": "b6a4d6a1a1fb289",
"outputs": [],
"execution_count": 144
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:43:06.906300Z",
"start_time": "2025-11-05T13:43:06.780036Z"
}
},
"cell_type": "code",
"source": [
"\n",
"\n",
"prediction_probs_numpy, _ = full_forward_propagation(np.transpose(grid_2d), params_values, nn_architecture)\n",
"prediction_probs_numpy = prediction_probs_numpy.reshape(prediction_probs_numpy.shape[1], 1)\n",
"\n",
"make_plot(X_test, y_test, \"NumPy Model\", file_name=None, XX=XX, YY=YY, preds=prediction_probs_numpy)"
],
"id": "6b36e606efa7f99a",
"outputs": [
{
"data": {
"text/plain": [
"<Figure size 1600x1200 with 1 Axes>"
],
"image/png": "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
},
"metadata": {},
"output_type": "display_data",
"jetTransient": {
"display_id": null
}
}
],
"execution_count": 149
},
{
"metadata": {},
"cell_type": "code",
"source": "",
"id": "dc0b9266ae37298a",
"outputs": [],
"execution_count": null
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:45:25.105461Z",
"start_time": "2025-11-05T13:45:17.001211Z"
}
},
"cell_type": "code",
"source": [
"model = Sequential()\n",
"model.add(Dense(25, input_dim=2,activation='relu'))\n",
"model.add(Dense(50, activation='relu'))\n",
"model.add(Dense(50, activation='relu'))\n",
"model.add(Dense(25, activation='relu'))\n",
"model.add(Dense(1, activation='sigmoid'))\n",
"\n",
"model.compile(loss='binary_crossentropy', optimizer=\"sgd\", metrics=['accuracy'])\n",
"\n",
"# Training\n",
"history = model.fit(X_train, y_train, epochs=200, verbose=0)"
],
"id": "f05ff40ed26e45c2",
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/oskar/projects/nn-from-scratch/.venv/lib/python3.13/site-packages/keras/src/layers/core/dense.py:95: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
" super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
]
}
],
"execution_count": 154
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:45:27.083553Z",
"start_time": "2025-11-05T13:45:26.623760Z"
}
},
"cell_type": "code",
"source": [
"Y_test_prob = model.predict(X_test)\n",
"Y_test_hat = (Y_test_prob > 0.5).astype(int).ravel()\n",
"acc_test = accuracy_score(y_test, Y_test_hat)\n",
"print(\"Test set accuracy: {:.2f} - Goliath\".format(acc_test))"
],
"id": "ef52bee9c93081d3",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001B[1m1/4\u001B[0m \u001B[32m━━━━━\u001B[0m\u001B[37m━━━━━━━━━━━━━━━\u001B[0m \u001B[1m0s\u001B[0m 202ms/stepWARNING:tensorflow:5 out of the last 62926 calls to <function TensorFlowTrainer.make_predict_function.<locals>.one_step_on_data_distributed at 0x7a1f345302c0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.\n",
"\u001B[1m4/4\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 78ms/step\n",
"Test set accuracy: 0.69 - Goliath\n"
]
}
],
"execution_count": 155
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:41:27.539268Z",
"start_time": "2025-11-05T13:40:32.908771Z"
}
},
"cell_type": "code",
"source": [
"def callback_keras_plot(epoch, logs):\n",
" plot_title = \"Keras Model - It: {:05}\".format(epoch)\n",
" file_name = \"keras_model_{:05}.png\".format(epoch)\n",
" file_path = os.path.join(OUTPUT_DIR, file_name)\n",
" prediction_probs = model.predict(grid_2d, batch_size=32, verbose=0)\n",
" prediction_probs = prediction_probs.reshape(-1)\n",
" make_plot(X_test, y_test, plot_title, file_name=file_path, XX=XX, YY=YY, preds=prediction_probs)\n",
"\n",
"\n",
"# Adding callback functions that they will run in every epoch\n",
"testmodelcb = keras.callbacks.LambdaCallback(on_epoch_end=callback_keras_plot)\n",
"\n",
"# Building a model\n",
"model = Sequential()\n",
"model.add(Dense(25, input_dim=2, activation='relu'))\n",
"model.add(Dense(50, activation='relu'))\n",
"model.add(Dense(50, activation='relu'))\n",
"model.add(Dense(25, activation='relu'))\n",
"model.add(Dense(1, activation='sigmoid'))\n",
"\n",
"model.compile(loss='binary_crossentropy', optimizer=\"sgd\", metrics=['accuracy'])\n",
"\n",
"# Training\n",
"history = model.fit(X_train, y_train, epochs=200, verbose=0, callbacks=[testmodelcb])\n"
],
"id": "6feab7da06e7a828",
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/oskar/projects/nn-from-scratch/.venv/lib/python3.13/site-packages/keras/src/layers/core/dense.py:95: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
" super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
]
}
],
"execution_count": 146
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-05T13:43:21.691060Z",
"start_time": "2025-11-05T13:43:21.443563Z"
}
},
"cell_type": "code",
"source": [
"\n",
"prediction_probs = model.predict(grid_2d, batch_size=32, verbose=0)\n",
"prediction_probs = prediction_probs.reshape(-1)\n",
"make_plot(X_test, y_test, \"Keras Model\", file_name=None, XX=XX, YY=YY, preds=prediction_probs)\n"
],
"id": "38dee4608746a358",
"outputs": [
{
"data": {
"text/plain": [
"<Figure size 1600x1200 with 1 Axes>"
],
"image/png": "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
},
"metadata": {},
"output_type": "display_data",
"jetTransient": {
"display_id": null
}
}
],
"execution_count": 150
},
{
"metadata": {},
"cell_type": "code",
"source": "!nvidia-smi\n",
"id": "7369490697e1ed40",
"outputs": [],
"execution_count": null
},
{
"metadata": {},
"cell_type": "code",
"source": [
"import torch\n",
"print(torch.cuda.is_available())"
],
"id": "9958964dbe0d2732",
"outputs": [],
"execution_count": null
},
{
"metadata": {},
"cell_type": "code",
"source": [
"print(torch.cuda.get_device_name(0))\n",
"print(torch.cuda.current_device())"
],
"id": "f88bc28cff654bde",
"outputs": [],
"execution_count": null
},
{
"metadata": {},
"cell_type": "code",
"source": "print(tf.config.list_physical_devices('GPU'))",
"id": "d60dd759b2bf2bf",
"outputs": [],
"execution_count": null
},
{
"metadata": {},
"cell_type": "code",
"source": [
"import torch, time\n",
"\n",
"x_cpu = torch.randn(10000, 10000)\n",
"start = time.time()\n",
"y_cpu = x_cpu @ x_cpu\n",
"print(\"CPU:\", time.time() - start, \"s\")\n",
"\n",
"if torch.cuda.is_available():\n",
" x_gpu = x_cpu.cuda()\n",
" torch.cuda.synchronize()\n",
" start = time.time()\n",
" y_gpu = x_gpu @ x_gpu\n",
" torch.cuda.synchronize()\n",
" print(\"GPU:\", time.time() - start, \"s\")\n"
],
"id": "b482f6b3594de45e",
"outputs": [],
"execution_count": null
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.13.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in a new issue Copy permalink