694 lines
563 KiB
Plaintext
694 lines
563 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"#### Zadanie 1 (6pkt):\n",
|
||
|
|
"\n",
|
||
|
|
"Zadanie polega na wykonaniu rozsądnej ilości testów dotyczących różnej ilości warstw ukrytych i różnej ilości neuronów w tych warstwach. Posługujemy się profesjonalną implementacją sieci MLP, np. z sklearn. Ponadto należy przetestować różne ilości iteracji, regularyzacje oraz wykonać wizualizacje dokładności i błędu funkcji kosztu dla kolejnych iteracji."
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 38,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"from sklearn.preprocessing import LabelEncoder\n",
|
||
|
|
"from sklearn.neural_network import MLPClassifier\n",
|
||
|
|
"import matplotlib.pyplot as plt\n",
|
||
|
|
"\n",
|
||
|
|
"import sys\n",
|
||
|
|
"import subprocess\n",
|
||
|
|
"import pkg_resources\n",
|
||
|
|
"import numpy as np\n",
|
||
|
|
"\n",
|
||
|
|
"from tqdm import tqdm\n",
|
||
|
|
"\n",
|
||
|
|
"\n",
|
||
|
|
"required = {'scikit-image'}\n",
|
||
|
|
"installed = {pkg.key for pkg in pkg_resources.working_set}\n",
|
||
|
|
"missing = required - installed\n",
|
||
|
|
"\n",
|
||
|
|
"if missing: \n",
|
||
|
|
" python = sys.executable\n",
|
||
|
|
" subprocess.check_call([python, '-m', 'pip', 'install', *missing], stdout=subprocess.DEVNULL)\n",
|
||
|
|
"\n",
|
||
|
|
"def load_train_data(input_dir, newSize=(64,64)):\n",
|
||
|
|
" import numpy as np\n",
|
||
|
|
" import pandas as pd\n",
|
||
|
|
" import os\n",
|
||
|
|
" from skimage.io import imread\n",
|
||
|
|
" import cv2 as cv\n",
|
||
|
|
" from pathlib import Path\n",
|
||
|
|
" import random\n",
|
||
|
|
" from shutil import copyfile, rmtree\n",
|
||
|
|
" import json\n",
|
||
|
|
"\n",
|
||
|
|
" import seaborn as sns\n",
|
||
|
|
" import matplotlib.pyplot as plt\n",
|
||
|
|
"\n",
|
||
|
|
" import matplotlib\n",
|
||
|
|
" \n",
|
||
|
|
" image_dir = Path(input_dir)\n",
|
||
|
|
" categories_name = []\n",
|
||
|
|
" for file in os.listdir(image_dir):\n",
|
||
|
|
" d = os.path.join(image_dir, file)\n",
|
||
|
|
" if os.path.isdir(d):\n",
|
||
|
|
" categories_name.append(file)\n",
|
||
|
|
"\n",
|
||
|
|
" folders = [directory for directory in image_dir.iterdir() if directory.is_dir()]\n",
|
||
|
|
"\n",
|
||
|
|
" train_img = []\n",
|
||
|
|
" categories_count=[]\n",
|
||
|
|
" labels=[]\n",
|
||
|
|
" for i, direc in enumerate(folders):\n",
|
||
|
|
" count = 0\n",
|
||
|
|
" for obj in direc.iterdir():\n",
|
||
|
|
" if os.path.isfile(obj) and os.path.basename(os.path.normpath(obj)) != 'desktop.ini':\n",
|
||
|
|
" labels.append(os.path.basename(os.path.normpath(direc)))\n",
|
||
|
|
" count += 1\n",
|
||
|
|
" img = imread(obj)#zwraca ndarry postaci xSize x ySize x colorDepth\n",
|
||
|
|
" img = cv.resize(img, newSize, interpolation=cv.INTER_AREA)# zwraca ndarray\n",
|
||
|
|
" img = img / 255#normalizacja\n",
|
||
|
|
" train_img.append(img)\n",
|
||
|
|
" categories_count.append(count)\n",
|
||
|
|
" X={}\n",
|
||
|
|
" X[\"values\"] = np.array(train_img)\n",
|
||
|
|
" X[\"categories_name\"] = categories_name\n",
|
||
|
|
" X[\"categories_count\"] = categories_count\n",
|
||
|
|
" X[\"labels\"]=labels\n",
|
||
|
|
" return X\n",
|
||
|
|
"\n",
|
||
|
|
"def load_test_data(input_dir, newSize=(64,64)):\n",
|
||
|
|
" import numpy as np\n",
|
||
|
|
" import pandas as pd\n",
|
||
|
|
" import os\n",
|
||
|
|
" from skimage.io import imread\n",
|
||
|
|
" import cv2 as cv\n",
|
||
|
|
" from pathlib import Path\n",
|
||
|
|
" import random\n",
|
||
|
|
" from shutil import copyfile, rmtree\n",
|
||
|
|
" import json\n",
|
||
|
|
"\n",
|
||
|
|
" import seaborn as sns\n",
|
||
|
|
" import matplotlib.pyplot as plt\n",
|
||
|
|
"\n",
|
||
|
|
" import matplotlib\n",
|
||
|
|
"\n",
|
||
|
|
" image_path = Path(input_dir)\n",
|
||
|
|
"\n",
|
||
|
|
" labels_path = image_path.parents[0] / 'test_labels.json'\n",
|
||
|
|
"\n",
|
||
|
|
" jsonString = labels_path.read_text()\n",
|
||
|
|
" objects = json.loads(jsonString)\n",
|
||
|
|
"\n",
|
||
|
|
" categories_name = []\n",
|
||
|
|
" categories_count=[]\n",
|
||
|
|
" count = 0\n",
|
||
|
|
" c = objects[0]['value']\n",
|
||
|
|
" for e in objects:\n",
|
||
|
|
" if e['value'] != c:\n",
|
||
|
|
" categories_count.append(count)\n",
|
||
|
|
" c = e['value']\n",
|
||
|
|
" count = 1\n",
|
||
|
|
" else:\n",
|
||
|
|
" count += 1\n",
|
||
|
|
" if not e['value'] in categories_name:\n",
|
||
|
|
" categories_name.append(e['value'])\n",
|
||
|
|
"\n",
|
||
|
|
" categories_count.append(count)\n",
|
||
|
|
" \n",
|
||
|
|
" test_img = []\n",
|
||
|
|
"\n",
|
||
|
|
" labels=[]\n",
|
||
|
|
" for e in objects:\n",
|
||
|
|
" p = image_path / e['filename']\n",
|
||
|
|
" img = imread(p)#zwraca ndarry postaci xSize x ySize x colorDepth\n",
|
||
|
|
" img = cv.resize(img, newSize, interpolation=cv.INTER_AREA)# zwraca ndarray\n",
|
||
|
|
" img = img / 255#normalizacja\n",
|
||
|
|
" test_img.append(img)\n",
|
||
|
|
" labels.append(e['value'])\n",
|
||
|
|
"\n",
|
||
|
|
" X={}\n",
|
||
|
|
" X[\"values\"] = np.array(test_img)\n",
|
||
|
|
" X[\"categories_name\"] = categories_name\n",
|
||
|
|
" X[\"categories_count\"] = categories_count\n",
|
||
|
|
" X[\"labels\"]=labels\n",
|
||
|
|
" return X\n",
|
||
|
|
"\n",
|
||
|
|
"def get_dataset(new_size=64):\n",
|
||
|
|
" data_train = load_train_data(\"train_test_sw/train_sw\", newSize=(new_size,new_size))\n",
|
||
|
|
" X_train = data_train['values']\n",
|
||
|
|
" y_train = data_train['labels']\n",
|
||
|
|
"\n",
|
||
|
|
" data_test = load_test_data(\"train_test_sw/test_sw\", newSize=(new_size,new_size))\n",
|
||
|
|
" X_test = data_test['values']\n",
|
||
|
|
" y_test = data_test['labels']\n",
|
||
|
|
"\n",
|
||
|
|
" class_le = LabelEncoder()\n",
|
||
|
|
" y_train_enc = class_le.fit_transform(y_train)\n",
|
||
|
|
" y_test_enc = class_le.fit_transform(y_test)\n",
|
||
|
|
"\n",
|
||
|
|
" X_train = X_train.flatten().reshape(X_train.shape[0], int(np.prod(X_train.shape) / X_train.shape[0]))\n",
|
||
|
|
" X_test = X_test.flatten().reshape(X_test.shape[0], int(np.prod(X_test.shape) / X_test.shape[0]))\n",
|
||
|
|
"\n",
|
||
|
|
" return X_train, y_train_enc, X_test, y_test_enc\n",
|
||
|
|
"\n",
|
||
|
|
"def test_mlp(X_train, y_train, X_val, y_val, X_test, y_test, hidden_layer_sizes, alpha, max_iter):\n",
|
||
|
|
" mlp = MLPClassifier(hidden_layer_sizes=hidden_layer_sizes, alpha=alpha, max_iter=max_iter)\n",
|
||
|
|
" accuracy = []\n",
|
||
|
|
"\n",
|
||
|
|
" result = {\n",
|
||
|
|
" 'num_layers': len(hidden_layer_sizes),\n",
|
||
|
|
" 'layer_sizes': hidden_layer_sizes,\n",
|
||
|
|
" 'regularization': alpha,\n",
|
||
|
|
" 'max_iter': max_iter\n",
|
||
|
|
" }\n",
|
||
|
|
"\n",
|
||
|
|
" for i in tqdm(range(max_iter)):\n",
|
||
|
|
" mlp.partial_fit(X_train, y_train, np.unique(y_train))\n",
|
||
|
|
" accuracy.append(mlp.score(X_train, y_train))\n",
|
||
|
|
" if i == 50:\n",
|
||
|
|
" result['checkpoint_train_accuracy'] = np.mean(accuracy)\n",
|
||
|
|
" result['checkpoint_val_accuracy'] = mlp.score(X_val, y_val)\n",
|
||
|
|
" result['checkpoint_test_accuracy'] = mlp.score(X_test, y_test)\n",
|
||
|
|
"\n",
|
||
|
|
" result['full_train_accuracy'] = np.mean(accuracy)\n",
|
||
|
|
" result['full_val_accuracy'] = mlp.score(X_val, y_val)\n",
|
||
|
|
" result['full_test_accuracy'] = mlp.score(X_test, y_test)\n",
|
||
|
|
" result['accuracy_curve'] = accuracy\n",
|
||
|
|
" result['loss_curve'] = mlp.loss_curve_\n",
|
||
|
|
"\n",
|
||
|
|
" return result\n",
|
||
|
|
"\n",
|
||
|
|
"def print_result(result):\n",
|
||
|
|
" print(f\"NUMBER OF HIDDEN LAYERS = {result['num_layers']}\")\n",
|
||
|
|
" print(f\"HIDDEN LAYER SIZES = {result['layer_sizes']}\")\n",
|
||
|
|
" print(f\"REGULARIZATION = {result['regularization']}\")\n",
|
||
|
|
" print(\"\\n50 EPOCHS\")\n",
|
||
|
|
" print(f\"train_accuracy = {round(result['checkpoint_train_accuracy'] * 100, 2)}%\")\n",
|
||
|
|
" print(f\"val_accuracy = {round(result['checkpoint_val_accuracy'] * 100, 2)}%\")\n",
|
||
|
|
" print(f\"test_accuracy = {round(result['checkpoint_test_accuracy'] * 100, 2)}%\")\n",
|
||
|
|
" print(f\"\\n{result['max_iter']} EPOCHS\")\n",
|
||
|
|
" print(f\"train_accuracy = {round(result['full_train_accuracy'] * 100, 2)}%\")\n",
|
||
|
|
" print(f\"val_accuracy = {round(result['checkpoint_val_accuracy'] * 100, 2)}%\")\n",
|
||
|
|
" print(f\"test_accuracy = {round(result['full_test_accuracy'] * 100, 2)}%\")\n",
|
||
|
|
"\n",
|
||
|
|
"def get_plot(result):\n",
|
||
|
|
" f = plt.figure(figsize=(12,6))\n",
|
||
|
|
" plt.plot(result['loss_curve'], label='loss')\n",
|
||
|
|
" plt.plot(result['accuracy_curve'], label='accuracy')\n",
|
||
|
|
" plt.legend(loc='best')\n",
|
||
|
|
" plt.xlabel('number of iterations')\n",
|
||
|
|
" plt.grid()\n",
|
||
|
|
" plt.show()\n",
|
||
|
|
"\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 2,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"from sklearn.model_selection import train_test_split\n",
|
||
|
|
"\n",
|
||
|
|
"NEW_SIZE = 64\n",
|
||
|
|
"\n",
|
||
|
|
"ONE_LAYER = (286,)\n",
|
||
|
|
"TWO_LAYERS = (437, 46)\n",
|
||
|
|
"THREE_LAYERS = (2166, 286, 38)\n",
|
||
|
|
"\n",
|
||
|
|
"\n",
|
||
|
|
"X_train, y_train, X_test, y_test = get_dataset(new_size=NEW_SIZE)\n",
|
||
|
|
"\n",
|
||
|
|
"X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.05, random_state=42)\n",
|
||
|
|
"\n",
|
||
|
|
"all_results = []"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 4,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"100%|██████████| 200/200 [03:46<00:00, 1.13s/it]\n",
|
||
|
|
"100%|██████████| 200/200 [04:01<00:00, 1.21s/it]\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"all_results.append(test_mlp(X_train, y_train, X_val, y_val, X_test, y_test, hidden_layer_sizes=ONE_LAYER, alpha=0.1, max_iter=200))\n",
|
||
|
|
"all_results.append(test_mlp(X_train, y_train, X_val, y_val, X_test, y_test, hidden_layer_sizes=ONE_LAYER, alpha=0.001, max_iter=200))"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 5,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"100%|██████████| 200/200 [05:31<00:00, 1.66s/it]\n",
|
||
|
|
"100%|██████████| 200/200 [05:19<00:00, 1.60s/it]\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"all_results.append(test_mlp(X_train, y_train, X_val, y_val, X_test, y_test, hidden_layer_sizes=TWO_LAYERS, alpha=0.1, max_iter=200))\n",
|
||
|
|
"all_results.append(test_mlp(X_train, y_train, X_val, y_val, X_test, y_test, hidden_layer_sizes=TWO_LAYERS, alpha=0.001, max_iter=200))"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 7,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"100%|██████████| 200/200 [42:29<00:00, 12.75s/it]\n",
|
||
|
|
"100%|██████████| 200/200 [44:00<00:00, 13.20s/it]\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"all_results.append(test_mlp(X_train, y_train, X_val, y_val, X_test, y_test, hidden_layer_sizes=THREE_LAYERS, alpha=0.01, max_iter=200))\n",
|
||
|
|
"all_results.append(test_mlp(X_train, y_train, X_val, y_val, X_test, y_test, hidden_layer_sizes=THREE_LAYERS, alpha=0.001, max_iter=200))"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 40,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"100%|██████████| 200/200 [46:41<00:00, 14.01s/it]\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"# TODO błąd przy regularyzacji\n",
|
||
|
|
"all_results[4] = test_mlp(X_train, y_train, X_val, y_val, X_test, y_test, hidden_layer_sizes=THREE_LAYERS, alpha=0.1, max_iter=200)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 41,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"NUMBER OF HIDDEN LAYERS = 1\n",
|
||
|
|
"HIDDEN LAYER SIZES = (286,)\n",
|
||
|
|
"REGULARIZATION = 0.1\n",
|
||
|
|
"\n",
|
||
|
|
"50 EPOCHS\n",
|
||
|
|
"train_accuracy = 70.72%\n",
|
||
|
|
"val_accuracy = 61.54%\n",
|
||
|
|
"test_accuracy = 71.81%\n",
|
||
|
|
"\n",
|
||
|
|
"200 EPOCHS\n",
|
||
|
|
"train_accuracy = 87.68%\n",
|
||
|
|
"val_accuracy = 61.54%\n",
|
||
|
|
"test_accuracy = 70.27%\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAr8AAAFzCAYAAAA322G8AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAABNo0lEQVR4nO3deXhdVaH+8e86Y4aTOWnadC4tnecyFSipgAwqg6KAioADcr3idJ2Hq165PxUEvQ73alUUVCjKoIgyQykIBdpS6DzQgc7N0GZOzrR+f6yTNG2TtidJkzT7/TxPnpycYe91VvY5+91rr7W2sdYiIiIiIuIFvr4ugIiIiIhIb1H4FRERERHPUPgVEREREc9Q+BURERERz1D4FRERERHPUPgVEREREc8I9ObKiouL7ahRo3pzlQA0NDSQnZ3d6+s9manO0qP6Sp/qLD2qr/SpztKj+kqf6iw9vVlfy5Ytq7TWlnT0WK+G31GjRrF06dLeXCUAixYtory8vNfXezJTnaVH9ZU+1Vl6VF/pU52lR/WVPtVZenqzvowx2zp7TN0eRERERMQzFH5FRERExDMUfkVERETEM3q1z6+IiIiIHBSLxdixYwfNzc19XZQTLi8vj7Vr1/boMjMyMhg2bBjBYPC4X6PwKyIiItJHduzYQU5ODqNGjcIY09fFOaHq6urIycnpseVZa6mqqmLHjh2MHj36uF+nbg8iIiIifaS5uZmioqIBH3xPBGMMRUVFabeaK/yKiIiI9CEF367rSt0p/IqIiIh4WCQS6esi9CqFXxERERHxDIVfEREREcFay5e+9CWmTJnC1KlTuf/++wHYvXs38+bNY8aMGUyZMoUXXniBRCLBDTfc0PbcH//4x31c+uOn2R5ERERE+oHv/n01a3bV9ugyJ5Xl8u33TD6u5z700EOsWLGCN954g8rKSk477TTmzZvHvffey0UXXcQ3vvENEokEjY2NrFixgp07d7Jq1SoADhw40KPlPpEGfMvv1soG3qiI93UxRERERPq1F198kWuvvRa/309paSnnnXcer732Gqeddhq/+93v+M53vsPKlSvJyclhzJgxbN68mVtuuYXHH3+c3Nzcvi7+cRvwLb9/W7GLHy9r4dPvs/h9Gk0pIiIi/dPxttD2tnnz5rF48WL+8Y9/cMMNN/CFL3yBj3zkI7zxxhs88cQT/PKXv+TPf/4zd911V18X9bgM+JbfgN8F3lgi2cclEREREem/zj33XO6//34SiQQVFRUsXryY008/nW3btlFaWsonPvEJPv7xj7N8+XIqKytJJpO8733v49Zbb2X58uV9XfzjNuBbfoOp8BtP2j4uiYiIiEj/deWVV/Lyyy8zffp0jDHcdtttDB48mLvvvpvbb7+dYDBIJBLhnnvuYefOndx4440kk65x8fvf/34fl/74Dfjw6/e5xu1EQuFXRERE5HD19fWAu2DE7bffzu23337I49dffz3XX3/9Ea87mVp72xvw3R5aW35jSXV7EBEREfG6AR9+A6mW37hafkVEREQ8b+CHXw14ExEREZGUAR9+NeBNRERERFoN+PB7sNuDWn5FREREvG7Ah9+2AW/q8ysiIiLieQM+/LZNdaZuDyIiIiKeN+DDb0BTnYmIiIj0uXg83tdFADwQfoOa6kxERETkqK644gpmz57N5MmTWbBgAQCPP/44s2bNYvr06Zx//vmAuyDGjTfeyNSpU5k2bRoPPvggAJFIpG1ZDzzwADfccAMAN9xwAzfffDNnnHEG3/rWt3j11Vc566yzmDlzJnPnzmX9+vUAJBIJvvjFLzJlyhSmTZvGz372M5599lmuuOKKtuU+9dRTXHnlld1+rwP+Cm+tLb8a8CYiIiL92mNfhT0re3aZg6fCJT845tPuuusuCgsLaWpq4rTTTuPyyy/nE5/4BIsXL2b06NFUV1cD8L3vfY+8vDxWrnTl3L9//zGXvWPHDl566SUaGxux1vLCCy8QCAR4+umn+frXv86DDz7IggUL2Lp1KytWrCAQCFBdXU1BQQGf+tSnqKiooKSkhN/97nd89KMf7V594IHwe/AKb2r5FREREenIT3/6Ux5++GEAtm/fzoIFC5g3bx6jR48GoLCwEICnn36ahQsXtr2uoKDgmMt+//vfj9/vB6Cmpobrr7+ejRs3YowhFou1Lffmm28mEAgcsr7rrruOP/7xj9x44428/PLL3HPPPd1+rwM+/GqqMxERETkpHEcL7YmwaNEinn76aV5++WWysrIoLy9nxowZrFu37riXYYxpu93c3HzIY9nZ2W23v/WtbzF//nwefvhhtm7dSnl5+VGXe+ONN/Ke97yHjIwM3v/+97eF4+4Y8H1+A5rqTERERKRTNTU1FBQUkJWVxbp161iyZAnNzc0sXryYLVu2ALR1e7jwwgv5xS9+0fba1m4PpaWlrF27lmQy2daC3Nm6hg4dCsDvf//7tvsvvPBCfvWrX7UNimtdX1lZGWVlZdx6663ceOONPfJ+B3741VRnIiIiIp26+OKLicfjTJw4ka9+9auceeaZlJSUsGDBAt773vcyffp0rr76agC++c1vsn//fqZMmcL06dN57rnnAPjBD37Au9/9bubOncuQIUM6XdeXv/xlvva1rzFz5sxDZn/4+Mc/zogRI5g2bRrTp0/n3nvvbXvsQx/6EMOHD2fixIk98n4HfreHtssbq9uDiIiIyOHC4TCPPfZYh49dcsklh/wdiUS4++67j3jeVVddxVVXXXXE/e1bdwHOOussNmzY0Pb3rbfeCkAgEODOO+/kzjvvPGIZL774Ip/4xCeO+T6O14APv61Tnanbg4iIiMjJZfbs2WRnZ3PHHXf02DIHfPjVVGciIiIiJ6dly5b1+DIHfp9fTXUmIiIiIikDPvwGNdWZiIiI9GPWqoGuq7pSdwM+/B7s9qANS0RERPqXjIwMqqqqFIC7wFpLVVUVGRkZab1u4Pf5bW35VbcHERER6WeGDRvGjh07qKio6OuinHDNzc1pB9VjycjIYNiwYWm9ZuCHXw14ExERkX4qGAy2XUJ4oFu0aBEzZ87s62J4oNuDTwPeRERERMQZ8OHXGIPfqOVXRERERDwQfgEXftXyKyIiIuJ5xwy/xpi7jDH7jDGr2t1XaIx5yhizMfW74MQWs3v8Poip5VdERETE846n5ff3wMWH3fdV4Blr7TjgmdTf/ZbPaKozERERETmO8GutXQxUH3b35cDdqdt3A1f0bLF6lt8YdXsQEREREczxTKpsjBkFPGqtnZL6+4C1Nj912wD7W//u4LU3ATcBlJaWzl64cGGPFDwdn3u2nqklQT42Ndzr6z5Z1dfXE4lE+roYJw3VV/pUZ+lRfaVPdZYe1Vf6VGfp6c36mj9//jJr7ZyOHuv2PL/WWmuM6TRBW2sXAAsA5syZY8vLy7u7yrQFn/8nxYNKKS+f0evrPlktWrSIvvhfnaxUX+lTnaVH9ZU+1Vl6VF/pU52lp7/UV1dne9hrjBkCkPq9r+eK1PP8RgPeRERERKTr4fcR4PrU7euBv/VMcU4Mv08D3kRERETk+KY6uw94GRhvjNlhjPkY8APgQmPMRuCC1N/9lhvwppZfEREREa87Zp9fa+21nTx0fg+X5YRx3R7U8isiIiLidd64wpsPEprqTERERMTzvBF+NeBNRERERPBK+PWhi1yIiIiIiEfCrzHE1fIrIiIi4nkeCb8a8CYiIiIiXgm/PjTVmYiIiIh4JPwaXeRCRERERLwUfjXgTURERMTzvBF+fRrwJiIiIiJeCb8GYmr5FREREfE8b4RfH2r5FRERERGPhF8NeBMRERERPBN+DTFNdSYiIiLieR4Jv2r5FRERERGvhF+fm+rMWgVgERERES/zRvg17ndCMz6IiIiIeJo3wm/qXepCFyIiIiLe5o3wa1zTb0zTnYmIiIh4mifCbyDV7UGD3kRERES8zRPht7Xbg6Y7ExEREfE2T4Rfn1p+RURERASPhF/N9iAiIiIi4JXw69OANxERERHxSPhtG/Cmll8RERERT/NE+G0b8KaWXxERERFP80b41YA3ERE
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 864x432 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {
|
||
|
|
"needs_background": "light"
|
||
|
|
},
|
||
|
|
"output_type": "display_data"
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"NUMBER OF HIDDEN LAYERS = 1\n",
|
||
|
|
"HIDDEN LAYER SIZES = (286,)\n",
|
||
|
|
"REGULARIZATION = 0.001\n",
|
||
|
|
"\n",
|
||
|
|
"50 EPOCHS\n",
|
||
|
|
"train_accuracy = 63.91%\n",
|
||
|
|
"val_accuracy = 59.62%\n",
|
||
|
|
"test_accuracy = 68.34%\n",
|
||
|
|
"\n",
|
||
|
|
"200 EPOCHS\n",
|
||
|
|
"train_accuracy = 86.05%\n",
|
||
|
|
"val_accuracy = 59.62%\n",
|
||
|
|
"test_accuracy = 77.99%\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 864x432 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {
|
||
|
|
"needs_background": "light"
|
||
|
|
},
|
||
|
|
"output_type": "display_data"
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"NUMBER OF HIDDEN LAYERS = 2\n",
|
||
|
|
"HIDDEN LAYER SIZES = (437, 46)\n",
|
||
|
|
"REGULARIZATION = 0.1\n",
|
||
|
|
"\n",
|
||
|
|
"50 EPOCHS\n",
|
||
|
|
"train_accuracy = 66.85%\n",
|
||
|
|
"val_accuracy = 67.31%\n",
|
||
|
|
"test_accuracy = 68.34%\n",
|
||
|
|
"\n",
|
||
|
|
"200 EPOCHS\n",
|
||
|
|
"train_accuracy = 84.63%\n",
|
||
|
|
"val_accuracy = 67.31%\n",
|
||
|
|
"test_accuracy = 75.29%\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 864x432 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {
|
||
|
|
"needs_background": "light"
|
||
|
|
},
|
||
|
|
"output_type": "display_data"
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"NUMBER OF HIDDEN LAYERS = 2\n",
|
||
|
|
"HIDDEN LAYER SIZES = (437, 46)\n",
|
||
|
|
"REGULARIZATION = 0.001\n",
|
||
|
|
"\n",
|
||
|
|
"50 EPOCHS\n",
|
||
|
|
"train_accuracy = 64.22%\n",
|
||
|
|
"val_accuracy = 61.54%\n",
|
||
|
|
"test_accuracy = 72.59%\n",
|
||
|
|
"\n",
|
||
|
|
"200 EPOCHS\n",
|
||
|
|
"train_accuracy = 86.25%\n",
|
||
|
|
"val_accuracy = 61.54%\n",
|
||
|
|
"test_accuracy = 78.76%\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAsMAAAFzCAYAAADbrgSqAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAABq3UlEQVR4nO3dd3iT1/3+8fex5L1tsBm22XvvEUJM9iaD7AXZXWnT3W93fmmTNm3apEmz9yK7TUN2gAQSIIwwA4QNZhkweG+d3x9HBtvY2AKDDLpf16UL6dGjR0cH2b519HnOMdZaRERERERCUViwGyAiIiIiEiwKwyIiIiISshSGRURERCRkKQyLiIiISMhSGBYRERGRkKUwLCIiIiIhyxusJ27Tpo3t3LlzUJ67uLiY2NjYoDz38Uj9FTj1WWDUX4FTnwVG/RUY9Vfg1GeBOdb9tXDhwt3W2rYN3Re0MNy5c2cWLFgQlOeeOXMm2dnZQXnu45H6K3Dqs8CovwKnPguM+isw6q/Aqc8Cc6z7yxizqbH7VCYhIiIiIiFLYVhEREREQpbCsIiIiIiErCZrho0xUcDnQKR//zestb+vt89k4D5gq3/TQ9baJ1u2qSIiIiIntsrKSnJycigrKwt2U46qxMREVq5c2eLHjYqKIiMjg/Dw8GY/pjkn0JUDp1pri4wx4cBsY8z71tq59fZ71Vr7/QDaKyIiIiK15OTkEB8fT+fOnTHGBLs5R01hYSHx8fEtekxrLXv27CEnJ4cuXbo0+3FNlklYp8h/M9x/sYfXTBERERFpTFlZGampqSd0ED5ajDGkpqYGPKrerJphY4zHGLMYyAU+ttbOa2C3S40xS40xbxhjMgNqhYiIiIgAKAgfgcPpO2Nt8wd5jTFJwNvAD6y1y2ttTwWKrLXlxpjbgCustac28PhbgVsB0tPTh02dOjXgBreEoqIi4uLigvLcxyP1V+DUZ4FRfwVOfRYY9Vdg1F+Ba6k+S0xMpHv37i3QosPXvn17tm/fflSfo7q6Go/Hc1SOvXbtWvLz8+tsmzBhwkJr7fCG9g8oDAMYY34HlFhr/9bI/R4gz1qbeKjjDB8+3GrRjeOD+itw6rPAqL8Cpz4LjPorMOqvwLVUn61cuZI+ffoceYOOQFxcHEVFRU3veASORs1wjYb60BjTaBhuskzCGNPWPyKMMSYaOANYVW+f9rVuXgi0/OmBIiIiInLMWGv52c9+Rv/+/RkwYACvvvoqANu3b2f8+PEMHjyY/v37M2vWLKqrq5k8efL+ff/xj38EufXN15zZJNoDz/lHfMOA16y17xpj7gIWWGvfAe4wxlwIVAF5wOSj1WARERGRUPDH/63gm20FLXrMvh0S+P0F/Zq171tvvcXixYtZsmQJu3fvZsSIEYwfP56XX36Zs846i1//+tdUV1dTUlLC4sWL2bp1K8uXuyraffv2tWi7j6Ymw7C1dikwpIHtv6t1/VfAr1q2aS2vtKKaeRv2sKfUF+ymiIiIiLRqs2fP5qqrrsLj8ZCens4pp5zC/PnzGTFiBDfeeCOVlZVcdNFFDB48mK5du7J+/Xp+8IMfcN5553HmmWcGu/nN1pyR4RPG3pIKJj8znyn9I7g02I0REREROYTmjuAea+PHj+fzzz9n2rRpTJ48mR//+Mdcf/31LFmyhA8//JBHH32U1157jaeffjrYTW2WkFqOOTbSZf+yqiA3RERERKSVO/nkk3n11Veprq5m165dfP7554wcOZJNmzaRnp7OLbfcws0338yiRYvYvXs3Pp+PSy+9lLvvvptFixYFu/nNFlIjw3H7w7DWDBERERE5lIsvvpg5c+YwaNAgjDH89a9/pV27djz33HPcd999hIeHExcXx/PPP8/WrVuZMmUKPp8rRb3nnnuC3PrmC6kw7AkzxER4KFUYFhEREWlQzbRqxhjuu+8+7rvvvjr333DDDdxwww0HPe54Gg2uLaTKJMCVSpSqTEJERERECMEwHB/pVZmEiIiIiAAhGIbjoryUVge7FSIiIiLSGoRcGI6N0MiwiIiIiDghF4bjolQzLCIiIiJOyIVh1QyLiIiISI2QC8NuNgmFYREREREJwTCsMgkRERGR4Kqqaj1hLPTCcKSXagvlVZpSQkRERKS+iy66iGHDhtGvXz8ef/xxAD744AOGDh3KoEGDOO200wC3OMeUKVMYMGAAAwcO5M033wQgLi5u/7HeeOMNJk+eDMDkyZO5/fbbGTVqFL/97W/56quvGDNmDEOGDGHs2LGsXr0agOrqan7605/Sv39/Bg4cyL/+9S+mT5/ORRddtP+4H3/8MRdffHGLvN6QWoEODizJXFRWRWScJ8itEREREWnE+7+EHcta9pjtBsA59x5yl6effpqUlBRKS0sZMWIEEydO5JZbbuHzzz+nS5cu5OXlAfD//t//IzExkWXLXBv37t3b5NPn5OTw5ZdfUlJSgrWWWbNm4fV6+eSTT/i///s/3nzzTR5//HE2btzI4sWL8Xq95OXlkZyczHe/+1127dpF27ZteeaZZ7jxxhuPvD8I5TBcXkVqXGSQWyMiIiLSujz44IO8/fbbAGzZsoXHH3+c8ePH06VLFwBSUlIA+OSTT5g6der+xyUnJzd57MsuuwyPxw1G5ufnc8MNN7BmzRqMMVRWVu4/7u23347X663zfNdddx0vvvgiU6ZMYc6cOTz//PMt8npDLwxHHQjDIiIiIq1WEyO4R8PMmTP55JNPmDNnDjExMWRnZzN48GBWrVrV7GMYY/ZfLysrq3NfbGzs/uu//e1vmTBhAm+//TYbN24kOzv7kMedMmUKF1xwAVFRUVx22WX7w/KRCsmaYXBlEiIiIiJyQH5+PsnJycTExLBq1Srmzp1LWVkZn3/+ORs2bADYXyZxxhln8PDDD+9/bE2ZRHp6OitXrsTn8+0fYW7suTp27AjAs88+u3/7GWecwWOPPbb/JLua5+vQoQMdOnTg7rvvZsqUKS32mkM3DGtkWERERKSOs88+m6qqKvr06cMvf/lLRo8eTdu2bXn88ce55JJLGDRoEFdccQUAv/nNb9i7dy/9+/dn0KBBzJgxA4B7772X888/n7Fjx9K+fftGn+vnP/85v/rVrxgyZEid2SVuvvlmsrKyGDhwIIMGDeLll1/ef98111xDZmYmffr0abHXrDIJEREREQEgMjKS999/v8H7zjnnnDq34+LieO655w7ab9KkSUyaNOmg7bVHfwHGjBnDt99+u//23XffDYDX6+X+++/n/vvvP+gYs2fP5pZbbmnydQQi5MJwvEaGRURERI47w4YNIzY2lr///e8tetyQC8OxqhkWEREROe4sXLjwqBw35GqGYyI8GDQyLCIiIiIhGIaNMUR5FYZFRESkdbLWBrsJx63D6buQC8MA0V6jMgkRERFpdaKiotizZ48C8WGw1rJnzx6ioqICelzI1QwDGhkWERGRVikjI4OcnBx27doV7KYcVWVlZQGH1uaIiooiIyMjoMeEZBiO9hiFYREREWl1wsPD9y97fCKbOXMmQ4YMCXYzgBAtk9DIsIiIiIhAiIZh1QyLiIiICIRyGNbIsIiIiEjIC8kwrDIJEREREYGQDcNuZFjTloiIiIiEtpAMw9FesBZKKqqD3RQRERERCaKQDMNRHgNAsUolREREREJaSIbhaK8Lw4UKwyIiIiIhLUTDsPtX06uJiIiIhLYmw7AxJsoY85UxZokxZoUx5o8N7BNpjHnVGLPWGDPPGNP5qLS2hdSMDGtGCREREZHQ1pyR4XLgVGvtIGAwcLYxZnS9fW4C9lpruwP/AP7Soq1sYVE1I8MKwyIiIiIhrckwbJ0i/81w/6X+nGQTgef8198ATjPGmBZrZQvbPzKsMgkRERGRkNasmmFjjMcYsxjIBT621s6rt0tHYAuAtbYKyAdSW7CdLSpKZRIiIiIiAphAFp4wxiQBbwM/sNYur7V9OXC2tTbHf3sdMMpau7ve428FbgVIT08fNnXq1CN+AYdjb0ERd35pmNQjnPO7RQSlDceToqIi4uLigt2M44r6LDDqr8CpzwKj/gqM+it
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 864x432 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {
|
||
|
|
"needs_background": "light"
|
||
|
|
},
|
||
|
|
"output_type": "display_data"
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"NUMBER OF HIDDEN LAYERS = 3\n",
|
||
|
|
"HIDDEN LAYER SIZES = (2166, 286, 38)\n",
|
||
|
|
"REGULARIZATION = 0.1\n",
|
||
|
|
"\n",
|
||
|
|
"50 EPOCHS\n",
|
||
|
|
"train_accuracy = 56.48%\n",
|
||
|
|
"val_accuracy = 59.62%\n",
|
||
|
|
"test_accuracy = 64.48%\n",
|
||
|
|
"\n",
|
||
|
|
"200 EPOCHS\n",
|
||
|
|
"train_accuracy = 76.48%\n",
|
||
|
|
"val_accuracy = 59.62%\n",
|
||
|
|
"test_accuracy = 77.61%\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 864x432 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {
|
||
|
|
"needs_background": "light"
|
||
|
|
},
|
||
|
|
"output_type": "display_data"
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"NUMBER OF HIDDEN LAYERS = 3\n",
|
||
|
|
"HIDDEN LAYER SIZES = (2166, 286, 38)\n",
|
||
|
|
"REGULARIZATION = 0.001\n",
|
||
|
|
"\n",
|
||
|
|
"50 EPOCHS\n",
|
||
|
|
"train_accuracy = 56.51%\n",
|
||
|
|
"val_accuracy = 57.69%\n",
|
||
|
|
"test_accuracy = 67.57%\n",
|
||
|
|
"\n",
|
||
|
|
"200 EPOCHS\n",
|
||
|
|
"train_accuracy = 83.33%\n",
|
||
|
|
"val_accuracy = 57.69%\n",
|
||
|
|
"test_accuracy = 76.83%\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 864x432 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {
|
||
|
|
"needs_background": "light"
|
||
|
|
},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"for result in all_results:\n",
|
||
|
|
" print_result(result)\n",
|
||
|
|
" get_plot(result)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 42,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 1440x720 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {
|
||
|
|
"needs_background": "light"
|
||
|
|
},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"f = plt.figure()\n",
|
||
|
|
"f.set_figwidth(20)\n",
|
||
|
|
"f.set_figheight(10)\n",
|
||
|
|
"\n",
|
||
|
|
"for result in all_results:\n",
|
||
|
|
" if result['regularization'] == 0.1:\n",
|
||
|
|
" plt.plot(result['accuracy_curve'], label=f\"{result['num_layers']} hidden layers\")\n",
|
||
|
|
"\n",
|
||
|
|
"plt.legend(loc='best')\n",
|
||
|
|
"plt.xlabel('number of iterations')\n",
|
||
|
|
"plt.title('accuracy for regularization = 0.1')\n",
|
||
|
|
"plt.grid()\n",
|
||
|
|
"plt.show()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 43,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAABIEAAAJcCAYAAABuRrQKAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOzddXyVdfvA8c99Yt3dBQw2tgEjRjsakQYxUbAbUR/z+Sl2YD0oigUWKKFIKUp3bTBgLGDd3R3n/v1xn/XZSEXl+3699oKd+3v3Yey+znVdX0mWZQRBEARBEARBEARBEIR/N9XVPgBBEARBEARBEARBEAThzyeCQIIgCIIgCIIgCIIgCNcAEQQSBEEQBEEQBEEQBEG4BoggkCAIgiAIgiAIgiAIwjVABIEEQRAEQRAEQRAEQRCuASIIJAiCIAiCIAiCIAiCcA0QQSBBEARBEP50kiQ5S5K0V5KkckmS3rvax3OxJEmSJUnqfonrekmSVCFJkvoKH9MISZLir+Q2BUEQBEH4dxNBIEEQBEEQ/gr3AQWAlSzLT17tg/krybKcJsuyhSzLjZeznfaBKFmW98my3PPyj/DKkSRpjCRJcZIkVUmStEuSJO8uxvrox1Tp1xnbbvlCSZJyJEkqkyRpuSRJxq2WvSpJ0mlJkhokSVr0J56SIAiCIPyriCCQIAiCIFyjJMVf9buANxAjy7J8sStKkqS5EmOuhr/rcf0ZJElyAH4G/g+wAyKA1V2s8gNwArAHXgDWSZLkqN/WBOBZYAzKe8cPeLnVugnA08CWK3sWgiAIgvDvJoJAgiAIgnAVSZL0rCRJifoyqRhJkma0W36vJEmxrZaH6l/3lCTpZ0mS8iVJKpQk6WP964skSfq+1fo++gwSjf773ZIkvS5J0gGgCvCTJGl+q30kSZJ0f7tjmCZJUpQ+IyNRkqSJkiTdKElSZLtxT0iStMHAOX4N3Ak8rS+LGitJkrEkSR9KkpSl//qwKdNDkqRwSZIyJEl6RpKkHGCFgW3OkyTpgCRJH0iSVAgs0m/zXUmS0iRJypUkaZkkSaat1nlakqRs/f7uaZ1Zo78u97Tb/v5O7tkNkiSd0F+P9NaZKK2u992SJKUBO1vfA0mShuivQdNXjSRJKfp1B0mSdEiSpBL9cX4sSZKRftle/S5O6te7qek6tdp3gP48SiRJOiNJ0tTW90CSpKWSJG3R3+cjkiR1M3R+l2EmcEaW5bWyLNcAi4A+kiT1MnAN/YFQ4CVZlqtlWf4JOA3M0g+5E/hKluUzsiwXA68C85rWl2X5G1mWfwPKr/A5CIIgCMK/mggCCYIgCMLVlQiMAKxRMh2+lyTJFUCSpBtRHqTvAKyAqUChpPSW2QykAj6AO/DjRexzLkp5lqV+G3nAZP0+5gMftAo2DQK+Bf4D2AAjgRRgI+ArSVJAu+1+235nsizPA1YC7+jLorajZH4MBvoCfYBBwH9breaCkk3irT9WQ8KAJMAZeB14C/DXb7M7ynV5UX8eE4EngLH6ZeFdXJ/zqUS5JzbADcCDkiRNbzfmOiAAmND6RVmWD+mvgQVgCxxByYgBaAQWAg7AEJQsmIf0643Uj+mjX79Nho0kSVpgE/AH4AQ8CqyUJKl1udjNKO8xW5RMmtc7O0F9IKmzr2c7Wa03cLLVuVaivL97dzI2SZbl1kGck63GttmW/u/OkiTZd3bMgiAIgiCcnwgCCYIgCMJVpM+ayJJlWad/sD+HEhABuAclcHJMViTIspyqX+4G/EeW5UpZlmtkWTaYtdKJr/UZFg2yLNfLsrxFluVE/T72oAQSRujH3g0sl2V5m/4YM2VZjpNluRal1Od2AEmSeqMEpDZf4DHcBrwiy3KeLMv5KMGJua2W61CyRGplWa7uZBtZsix/JMtyA1CDEixaKMtykT648AZK4ANgDrBCf95VKMG1SyLL8m5Zlk/rr8cplCDOde2GLdLfm86OHWAJSibLC/rtRsqyfFh/X1KAzwxstzODAQvgLVmW62RZ3olyL25pNWa9LMtH9ddrJUqwrLNztOni661OVrMAStu9VooSbLzYse2XN/3d0LYEQRAEQbhAIggkCIIgCFeRJEl36EutSiRJKgGCUDJBADxRMina8wRS9Q/zlyK93TFcL0nSYUmSivTHMOkCjgHgG+BWSZIklADOGn1w6EK4oWQhNUnVv9YkX19S1JXW5+EImAGRra7lVv3rTftL72TdiyJJUpikNDTOlySpFHiAlut1QdvXl9yFA7fKsqzTv+YvSdJmSd8MGSWI1X67nXED0pu2pZeKkg3VJKfV36tQAi1XUgVKNllrVhgu2Trf2PbLm/4uyr8EQRAE4TKIIJAgCIIgXCWSMnPSF8AjgL0syzZANCDph6QDhvq2pANekuGmw5UowZAmLgbGNDdn1vfh+Ql4F3DWH8OvF3AMyLJ8GKhDyRq6FfjO0LhOZKGUejXx0r/W4Ri70HpMAVAN9G6VsWKtL7sCyAY8Wo33bLetC7luTVahlMN5yrJsDSyj5Xqd9/glSRqB0uNmmizLZa0WfQrEAT1kWbYCnjew3c5kAZ5S20bfXkDmBa7f/hgruvh6vpPVzqCU9jVtwxzlvXOmk7F+kiS1zuzp02psm23p/54ry3LhpZyPIAiCIAgKEQQSBEEQhKvHHCVYkA8gSdJ8lEygJl8CT0mS1F9SdNcHjo6iBDXekiTJXJIkE0mShunXiQJGSpLkJUmSNfDceY7BCDDWH0ODJEnXA+NbLf8KmC8pU3+rJElyb9fo91vgY6D+IkvSfgD+K0mSo6TMKvUi8P151umUPgPmC5R+Rk4A+mNt6smzRn8eAZIkmaHMYNVaFDBTkiQzSWkWfXcXu7MEimRZrtH3TLr1Qo9TkiRP/bHcIcvyWQPbLQMq9Nf4wXbLc1FmyTLkCEp2z9OSJGklSQoHpnBxvaKaNfUt6uTrjU5WWw8ESZI0S5IkE5R7ekqW5TgD2z+Lcs1f0r9/ZwAhKAFJUN5Xd0uSFChJkg1Kv6ivm9bXn6MJyu+yGv021JdyroIgCIJwLRFBIEEQBEG4SmRZjgHeAw6hPOAHAwdaLV+L0rx3FUoZzC+AnSzLjSgP+N2BNCADuEm/zjaUXj2ngEjO06NH3zvnMZTARDFKQGNjq+VH0TeLRunLsoe2GTzfoQSuLjaA8xrKFOKnUGaFOq5/7XI8g9Lw+LC+nGo70BNAP5PUEmBX0xj9Ok3lax+gZDXlopS5rexiPw8Br0iSVI4S6FhzEcc4BqWR9bpWmTVN2S9PoVz/cpSAVvvp1RcB3+jL3ea0XiDLch3Ke+J6lKyoT1ACTR0CMH8WfW+nWSjv2WKUxt1NPZmQlNnalrVa5WZggH7sW8Bs/TaQZXkr8A7K/UpDKW17qdW6X6Bkft2C0lOpmrY9pQRBEARBMECS5QvJthYEQRAEQehIUqZgzwNCZVk+d7WP50LpZzWLBowvo7eSIAiCIAjCP4rIBBIEQRAE4XI8CBz7JwSAJEmaIUmSsSRJtsDbwCYRABIEQRAE4VpiqKGkIAiCIAjCeUmSlILSuHj61T2SC3Y/Sl+ZRpSytoeu6tEIgiAIgiD8xUQ5mCAIgiAIgiAIgiAIwjVAlIMJgiAIgiAIgiAIgiBcA65aOZiDg4Ps4+NztXZ/RVVWVmJubn61D0O4CsS9v7aJ+3/tEvf+2ibu/7VL3Ptrm7j/1y5x769d/9R7HxkZWSDLsqOhZVctCOTj40NERMTV2v0VtXv3bsLDw6/2YQhXgbj31zZx/69d4t5f28T9v3aJe39tE/f/2iXu/bXrn3rvJUlK7WyZKAcTBEEQBEEQBEEQBEG4BoggkCAIgiAIgiAIgiAIwjVABIEEQRAEQRAEQRAEQRCuAVetJ5Ah9fX1ZGRkUFNTc7UP5aJYW1sTGxt7tQ/jb8HExAQPDw+0Wu3VPhRBEARBEARBEARBEFr5WwWBMjIysLS0xMfHB0mSrvbhXLDy8nIsLS2v9mFcdbIsU1hYSEZGBr6+vlf7cARBEARBEARBEARBaOVvVQ5WU1ODvb39PyoAJLSQJAl7e/t/XCaXIAiCIAi
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 1440x720 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {
|
||
|
|
"needs_background": "light"
|
||
|
|
},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"f = plt.figure(figsize=(20,10))\n",
|
||
|
|
"f.set_figwidth(20)\n",
|
||
|
|
"f.set_figheight(10)\n",
|
||
|
|
"\n",
|
||
|
|
"for result in all_results:\n",
|
||
|
|
" if result['regularization'] == 0.001:\n",
|
||
|
|
" plt.plot(result['accuracy_curve'], label=f\"{result['num_layers']} hidden layers\")\n",
|
||
|
|
"\n",
|
||
|
|
"plt.legend(loc='best')\n",
|
||
|
|
"plt.xlabel('number of iterations')\n",
|
||
|
|
"plt.title('accuracy for regularization = 0.001')\n",
|
||
|
|
"plt.grid()\n",
|
||
|
|
"plt.show()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 46,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"No artists with labels found to put in legend. Note that artists whose label start with an underscore are ignored when legend() is called with no argument.\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 1008x576 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {
|
||
|
|
"needs_background": "light"
|
||
|
|
},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"data = {\n",
|
||
|
|
" '1 hidden layer,\\nalpha=0.1' : 226,\n",
|
||
|
|
" '1 hidden layer,\\nalpha=0.001' : 241,\n",
|
||
|
|
" '3 hidden layers,\\nalpha=0.1' : 331,\n",
|
||
|
|
" '3 hidden layers,\\nalpha=0.001' : 319,\n",
|
||
|
|
" '5 hidden layers,\\nalpha=0.1' : 2801,\n",
|
||
|
|
" '5 hidden layers,\\nalpha=0.001' : 2640\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"f = plt.figure(figsize=(14,8))\n",
|
||
|
|
"\n",
|
||
|
|
"plt.barh(list(data.keys()), list(data.values()))\n",
|
||
|
|
"\n",
|
||
|
|
"plt.legend(loc='best')\n",
|
||
|
|
"plt.xlabel('time [s]')\n",
|
||
|
|
"plt.xticks(np.arange(0, 2900, step=200))\n",
|
||
|
|
"plt.grid()\n",
|
||
|
|
"plt.show()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 53,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 1008x576 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {
|
||
|
|
"needs_background": "light"
|
||
|
|
},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"f = plt.figure(figsize=(14,8))\n",
|
||
|
|
"\n",
|
||
|
|
"X_axis = np.arange(len(list(data.keys())))\n",
|
||
|
|
"\n",
|
||
|
|
"Ytrain = [result['full_train_accuracy'] for result in all_results]\n",
|
||
|
|
"Yval = [result['full_val_accuracy'] for result in all_results]\n",
|
||
|
|
"Ytest = [result['full_test_accuracy'] for result in all_results]\n",
|
||
|
|
"\n",
|
||
|
|
"plt.bar(X_axis - 0.2, Ytrain, 0.2, label='train')\n",
|
||
|
|
"plt.bar(X_axis, Yval, 0.2, label='val')\n",
|
||
|
|
"plt.bar(X_axis + 0.2, Ytest, 0.2, label='test')\n",
|
||
|
|
"\n",
|
||
|
|
"plt.xticks(X_axis, list(data.keys()))\n",
|
||
|
|
"plt.yticks(np.arange(0, 1, step=0.1))\n",
|
||
|
|
"plt.legend(loc='best')\n",
|
||
|
|
"plt.title('Accuracy')\n",
|
||
|
|
"plt.grid()\n",
|
||
|
|
"plt.show()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": null,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": []
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"kernelspec": {
|
||
|
|
"display_name": "Python 3.10.5 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": "3.10.5"
|
||
|
|
},
|
||
|
|
"orig_nbformat": 4,
|
||
|
|
"vscode": {
|
||
|
|
"interpreter": {
|
||
|
|
"hash": "7e1998ff7f8aa20ada591c520b972326324e5ea05489af9e422744c7c09f6dad"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 2
|
||
|
|
}
|