Hugging Face's logo

SamuelRx
/
FirstModel

Model card Files
xet
 Community
SamuelRx commited on
Commit
3ff78d4
·
verified ·
1 Parent(s): dade7e4

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. .ipynb_checkpoints/Chapter1-NeuralNetwork-checkpoint.ipynb +266 -0
  2. .ipynb_checkpoints/Chapter1.2-NeuralNetwork-checkpoint.ipynb +158 -0
  3. Chapter1-NeuralNetwork.ipynb +266 -0
  4. Chapter1.1-NeuralNetwork.ipynb +208 -0
  5. Chapter1.2-NeuralNetwork.ipynb +216 -0
.ipynb_checkpoints/Chapter1-NeuralNetwork-checkpoint.ipynb ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 2,
6
+ "id": "2b22b7ad-9329-477a-a8f4-583fb23a8471",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import numpy as np\n",
11
+ "import tensorflow as tf\n",
12
+ "from tensorflow import keras\n",
13
+ "import pandas as pd\n",
14
+ "import matplotlib\n",
15
+ "matplotlib.use(\"TkAgg\")\n",
16
+ "import matplotlib.pyplot as plt"
17
+ ]
18
+ },
19
+ {
20
+ "cell_type": "code",
21
+ "execution_count": 3,
22
+ "id": "8b9896be-f135-4c8d-9c00-c6fe7e444172",
23
+ "metadata": {},
24
+ "outputs": [
25
+ {
26
+ "name": "stdout",
27
+ "output_type": "stream",
28
+ "text": [
29
+ "(60000, 28, 28)\n",
30
+ "uint8\n"
31
+ ]
32
+ }
33
+ ],
34
+ "source": [
35
+ "fashion_mnist = keras.datasets.fashion_mnist\n",
36
+ "\n",
37
+ "(x_train_full, y_train_full), (x_test, y_test) = fashion_mnist.load_data()\n",
38
+ "x_test = x_test / 255.0\n",
39
+ "\n",
40
+ "print(x_train_full.shape)\n",
41
+ "print(x_train_full.dtype)\n",
42
+ "\n",
43
+ "x_valid, x_train = x_train_full[:5000] / 255.0, x_train_full[5000:] / 255.0\n",
44
+ "y_valid, y_train = y_train_full[:5000], y_train_full[5000:]\n",
45
+ "\n",
46
+ "class_names = [\n",
47
+ " \"T-shirt/top\", \"Trouser\", \"Pullover\", \"Dress\", \"Coat\",\n",
48
+ " \"Sandal\", \"Shirt\", \"Sneaker\", \"Bag\", \"Ankle boot\"\n",
49
+ "]"
50
+ ]
51
+ },
52
+ {
53
+ "cell_type": "code",
54
+ "execution_count": 4,
55
+ "id": "c4514be8-3e16-4f63-bea4-adc8e2576e43",
56
+ "metadata": {},
57
+ "outputs": [
58
+ {
59
+ "name": "stderr",
60
+ "output_type": "stream",
61
+ "text": [
62
+ "C:\\Users\\lacer\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\keras\\src\\layers\\reshaping\\flatten.py:37: 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",
63
+ " super().__init__(**kwargs)\n"
64
+ ]
65
+ }
66
+ ],
67
+ "source": [
68
+ "model = keras.models.Sequential()\n",
69
+ "model.add(keras.layers.Flatten(input_shape=(28, 28)))\n",
70
+ "model.add(keras.layers.Dense(300, activation='relu'))\n",
71
+ "model.add(keras.layers.Dense(100, activation='relu'))\n",
72
+ "model.add(keras.layers.Dense(10, activation='softmax'))"
73
+ ]
74
+ },
75
+ {
76
+ "cell_type": "code",
77
+ "execution_count": 6,
78
+ "id": "80db0e8a-cc96-4752-8bec-60315ad34bec",
79
+ "metadata": {},
80
+ "outputs": [
81
+ {
82
+ "name": "stdout",
83
+ "output_type": "stream",
84
+ "text": [
85
+ "WARNING:tensorflow:TensorFlow GPU support is not available on native Windows for TensorFlow >= 2.11. Even if CUDA/cuDNN are installed, GPU will not be used. Please use WSL2 or the TensorFlow-DirectML plugin.\n",
86
+ "Epoch 1/30\n",
87
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.7659 - loss: 0.7165 - val_accuracy: 0.8362 - val_loss: 0.5032\n",
88
+ "Epoch 2/30\n",
89
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8292 - loss: 0.4888 - val_accuracy: 0.8542 - val_loss: 0.4361\n",
90
+ "Epoch 3/30\n",
91
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8441 - loss: 0.4461 - val_accuracy: 0.8642 - val_loss: 0.4142\n",
92
+ "Epoch 4/30\n",
93
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8529 - loss: 0.4180 - val_accuracy: 0.8654 - val_loss: 0.3972\n",
94
+ "Epoch 5/30\n",
95
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8600 - loss: 0.3981 - val_accuracy: 0.8600 - val_loss: 0.3943\n",
96
+ "Epoch 6/30\n",
97
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8655 - loss: 0.3811 - val_accuracy: 0.8694 - val_loss: 0.3724\n",
98
+ "Epoch 7/30\n",
99
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8690 - loss: 0.3680 - val_accuracy: 0.8668 - val_loss: 0.3823\n",
100
+ "Epoch 8/30\n",
101
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8726 - loss: 0.3573 - val_accuracy: 0.8724 - val_loss: 0.3629\n",
102
+ "Epoch 9/30\n",
103
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8777 - loss: 0.3461 - val_accuracy: 0.8768 - val_loss: 0.3452\n",
104
+ "Epoch 10/30\n",
105
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8804 - loss: 0.3365 - val_accuracy: 0.8792 - val_loss: 0.3440\n",
106
+ "Epoch 11/30\n",
107
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8837 - loss: 0.3282 - val_accuracy: 0.8698 - val_loss: 0.3532\n",
108
+ "Epoch 12/30\n",
109
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8858 - loss: 0.3197 - val_accuracy: 0.8814 - val_loss: 0.3315\n",
110
+ "Epoch 13/30\n",
111
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8886 - loss: 0.3127 - val_accuracy: 0.8804 - val_loss: 0.3382\n",
112
+ "Epoch 14/30\n",
113
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8911 - loss: 0.3053 - val_accuracy: 0.8738 - val_loss: 0.3601\n",
114
+ "Epoch 15/30\n",
115
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8923 - loss: 0.2997 - val_accuracy: 0.8816 - val_loss: 0.3278\n",
116
+ "Epoch 16/30\n",
117
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8951 - loss: 0.2938 - val_accuracy: 0.8834 - val_loss: 0.3259\n",
118
+ "Epoch 17/30\n",
119
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8983 - loss: 0.2865 - val_accuracy: 0.8850 - val_loss: 0.3281\n",
120
+ "Epoch 18/30\n",
121
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9000 - loss: 0.2809 - val_accuracy: 0.8832 - val_loss: 0.3194\n",
122
+ "Epoch 19/30\n",
123
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9008 - loss: 0.2760 - val_accuracy: 0.8886 - val_loss: 0.3071\n",
124
+ "Epoch 20/30\n",
125
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9016 - loss: 0.2716 - val_accuracy: 0.8820 - val_loss: 0.3401\n",
126
+ "Epoch 21/30\n",
127
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 2ms/step - accuracy: 0.9035 - loss: 0.2662 - val_accuracy: 0.8890 - val_loss: 0.3063\n",
128
+ "Epoch 22/30\n",
129
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9061 - loss: 0.2614 - val_accuracy: 0.8900 - val_loss: 0.3113\n",
130
+ "Epoch 23/30\n",
131
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9069 - loss: 0.2565 - val_accuracy: 0.8888 - val_loss: 0.3085\n",
132
+ "Epoch 24/30\n",
133
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9091 - loss: 0.2524 - val_accuracy: 0.8842 - val_loss: 0.3263\n",
134
+ "Epoch 25/30\n",
135
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9102 - loss: 0.2487 - val_accuracy: 0.8894 - val_loss: 0.3044\n",
136
+ "Epoch 26/30\n",
137
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9108 - loss: 0.2446 - val_accuracy: 0.8914 - val_loss: 0.2958\n",
138
+ "Epoch 27/30\n",
139
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9133 - loss: 0.2392 - val_accuracy: 0.8788 - val_loss: 0.3307\n",
140
+ "Epoch 28/30\n",
141
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9149 - loss: 0.2362 - val_accuracy: 0.8914 - val_loss: 0.2978\n",
142
+ "Epoch 29/30\n",
143
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9171 - loss: 0.2317 - val_accuracy: 0.8886 - val_loss: 0.3139\n",
144
+ "Epoch 30/30\n",
145
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9177 - loss: 0.2281 - val_accuracy: 0.8922 - val_loss: 0.3038\n"
146
+ ]
147
+ }
148
+ ],
149
+ "source": [
150
+ "model.compile(\n",
151
+ " loss=\"sparse_categorical_crossentropy\",\n",
152
+ " optimizer=\"sgd\",\n",
153
+ " metrics=[\"accuracy\"]\n",
154
+ ")\n",
155
+ "\n",
156
+ "history = model.fit(\n",
157
+ " x_train,\n",
158
+ " y_train,\n",
159
+ " epochs=30 ,\n",
160
+ " validation_data=(x_valid, y_valid)\n",
161
+ ")"
162
+ ]
163
+ },
164
+ {
165
+ "cell_type": "code",
166
+ "execution_count": 8,
167
+ "id": "2a081c04-338c-40e6-89d1-857ec6ca3232",
168
+ "metadata": {},
169
+ "outputs": [],
170
+ "source": [
171
+ "pd.DataFrame(history.history).plot(figsize=(8, 5))\n",
172
+ "plt.grid(True)\n",
173
+ "plt.gca().set_ylim(0, 1)\n",
174
+ "plt.show()\n"
175
+ ]
176
+ },
177
+ {
178
+ "cell_type": "code",
179
+ "execution_count": 9,
180
+ "id": "7cd5d8ac-6a3e-4a92-b4ef-574923bf4b71",
181
+ "metadata": {},
182
+ "outputs": [
183
+ {
184
+ "name": "stdout",
185
+ "output_type": "stream",
186
+ "text": [
187
+ "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - accuracy: 0.8787 - loss: 0.3378\n"
188
+ ]
189
+ },
190
+ {
191
+ "data": {
192
+ "text/plain": [
193
+ "[0.33777710795402527, 0.8787000179290771]"
194
+ ]
195
+ },
196
+ "execution_count": 9,
197
+ "metadata": {},
198
+ "output_type": "execute_result"
199
+ }
200
+ ],
201
+ "source": [
202
+ "model.evaluate(x_test, y_test)\n"
203
+ ]
204
+ },
205
+ {
206
+ "cell_type": "code",
207
+ "execution_count": 12,
208
+ "id": "6d401ab5-a415-4c92-98b6-01ac1c15dd47",
209
+ "metadata": {},
210
+ "outputs": [
211
+ {
212
+ "name": "stdout",
213
+ "output_type": "stream",
214
+ "text": [
215
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step\n",
216
+ "[[0. 0. 0. 0. 0. 0.01 0. 0.03 0. 0.95]\n",
217
+ " [0. 0. 1. 0. 0. 0. 0. 0. 0. 0. ]\n",
218
+ " [0. 1. 0. 0. 0. 0. 0. 0. 0. 0. ]]\n",
219
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step\n",
220
+ "[9 2 1]\n",
221
+ "['Ankle boot' 'Pullover' 'Trouser']\n"
222
+ ]
223
+ }
224
+ ],
225
+ "source": [
226
+ "x_new = x_test[:3]\n",
227
+ "y_proba = model.predict(x_new)\n",
228
+ "print(y_proba.round(2))\n",
229
+ "\n",
230
+ "y_pred = model.predict(x_new).argmax(axis=1)\n",
231
+ "print(y_pred)\n",
232
+ "\n",
233
+ "print(np.array(class_names)[y_pred])\n"
234
+ ]
235
+ },
236
+ {
237
+ "cell_type": "code",
238
+ "execution_count": null,
239
+ "id": "5b476174-b4af-43fb-b1f4-8b182c3af14d",
240
+ "metadata": {},
241
+ "outputs": [],
242
+ "source": []
243
+ }
244
+ ],
245
+ "metadata": {
246
+ "kernelspec": {
247
+ "display_name": "Python 3",
248
+ "language": "python",
249
+ "name": "python3"
250
+ },
251
+ "language_info": {
252
+ "codemirror_mode": {
253
+ "name": "ipython",
254
+ "version": 3
255
+ },
256
+ "file_extension": ".py",
257
+ "mimetype": "text/x-python",
258
+ "name": "python",
259
+ "nbconvert_exporter": "python",
260
+ "pygments_lexer": "ipython3",
261
+ "version": "3.12.10"
262
+ }
263
+ },
264
+ "nbformat": 4,
265
+ "nbformat_minor": 5
266
+ }
.ipynb_checkpoints/Chapter1.2-NeuralNetwork-checkpoint.ipynb ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "177faf3e-cec4-4a9f-a613-4c8838af30c1",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "#No keras existem os modelos de redes neurais estaticos, funcionais e dinamicmos. Neste notebook lidaresmos com dinamico"
11
+ ]
12
+ },
13
+ {
14
+ "cell_type": "code",
15
+ "execution_count": null,
16
+ "id": "ef8dbd4c-3443-4a5f-b8e1-99b6f0d958b6",
17
+ "metadata": {},
18
+ "outputs": [],
19
+ "source": [
20
+ "from sklearn.datasets import fetch_california_housing\n",
21
+ "from sklearn.model_selection import train_test_split\n",
22
+ "from sklearn.preprocessing import StandardScaler\n",
23
+ "\n",
24
+ "import numpy as np\n",
25
+ "import tensorflow as tf\n",
26
+ "from tensorflow import keras\n",
27
+ "import pandas as pd\n",
28
+ "import matplotlib\n",
29
+ "matplotlib.use(\"TkAgg\")\n",
30
+ "import matplotlib.pyplot as plt"
31
+ ]
32
+ },
33
+ {
34
+ "cell_type": "code",
35
+ "execution_count": null,
36
+ "id": "09438fbc-8705-4712-8111-078a22cf8d1d",
37
+ "metadata": {},
38
+ "outputs": [],
39
+ "source": [
40
+ "housing = fetch_california_housing()\n",
41
+ "x_train_full, x_test, y_train_full, y_test = train_test_split(housing.data,housing.target)\n",
42
+ "x_train, x_valid, y_train, y_valid = train_test_split(x_train_full, y_train_full)\n",
43
+ "\n",
44
+ "scaler=StandardScaler()\n",
45
+ "x_train = scaler.fit_transform(x_train)\n",
46
+ "x_valid = scaler.transform(x_valid)\n",
47
+ "x_test=scaler.transform(x_test)"
48
+ ]
49
+ },
50
+ {
51
+ "cell_type": "code",
52
+ "execution_count": null,
53
+ "id": "0e80a374-8f22-40cd-ad12-f15898142f6b",
54
+ "metadata": {},
55
+ "outputs": [],
56
+ "source": [
57
+ "class WideAndDeepModel(keras.Model):\n",
58
+ " def __init__(self, units=30, activation=\"relu\", **kwargs):\n",
59
+ " super().__init__(**kwargs) \n",
60
+ " self.hidden1 = keras.layers.Dense(units, activation=activation)\n",
61
+ " self.hidden2 = keras.layers.Dense(units, activation=activation)\n",
62
+ " self.main_output = keras.layers.Dense(1)\n",
63
+ " self.aux_output = keras.layers.Dense(1)\n",
64
+ " def call(self, inputs):\n",
65
+ " input_A, input_B = inputs\n",
66
+ " hidden1 = self.hidden1(input_B)\n",
67
+ " hidden2 = self.hidden2(hidden1)\n",
68
+ " concat = keras.layers.concatenate([input_A, hidden2])\n",
69
+ " main_output = self.main_output(concat)\n",
70
+ " aux_output = self.aux_output(hidden2)\n",
71
+ " return main_output, aux_output"
72
+ ]
73
+ },
74
+ {
75
+ "cell_type": "code",
76
+ "execution_count": null,
77
+ "id": "3a81c2b8-4e95-453a-8d1a-4ba132bd483b",
78
+ "metadata": {},
79
+ "outputs": [],
80
+ "source": [
81
+ "model = WideAndDeepModel()\n",
82
+ "\n",
83
+ "model.compile(\n",
84
+ " loss=[\"mse\", \"mse\"], # uma loss para cada saída\n",
85
+ " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n",
86
+ " loss_weights=[0.8, 0.2] # opcional: peso de cada saída\n",
87
+ ")\n",
88
+ "\n",
89
+ "# Os targets precisam ser tuplas/listas correspondentes às saídas\n",
90
+ "history = model.fit(\n",
91
+ " (x_train_A, x_train_B), # entradas\n",
92
+ " (y_train, y_train), # targets: main_output e aux_output\n",
93
+ " epochs=20,\n",
94
+ " validation_data=((x_valid_A, x_valid_B), (y_valid, y_valid))\n",
95
+ ")\n",
96
+ "\n",
97
+ "# Avaliar\n",
98
+ "mse_test = model.evaluate((x_test_A, x_test_B), (y_test, y_test))\n",
99
+ "\n",
100
+ "# Predição\n",
101
+ "y_pred_main, y_pred_aux = model.predict((x_new_A, x_new_B))\n",
102
+ "print(y_pred_main)\n",
103
+ "\n",
104
+ "model.save(\"my_keras_model.h5\") #Salvando modelo, legal isso"
105
+ ]
106
+ },
107
+ {
108
+ "cell_type": "code",
109
+ "execution_count": null,
110
+ "id": "044977e1-310c-4f39-9e46-303c86bfbd0f",
111
+ "metadata": {},
112
+ "outputs": [],
113
+ "source": [
114
+ "model = keras.models.load_model(\"my_keras_model.h5\")"
115
+ ]
116
+ },
117
+ {
118
+ "cell_type": "code",
119
+ "execution_count": null,
120
+ "id": "079566ef-1c0c-400a-aeba-253ba01d1d5c",
121
+ "metadata": {},
122
+ "outputs": [],
123
+ "source": [
124
+ "checkpoint_cb = keras.callbacs.ModelCheckpoint(\"my_keras_model.h5\")\n",
125
+ "history = model.fit(x_train, y_train, epochs = 10, callbacks = [checkpoint_cb])"
126
+ ]
127
+ },
128
+ {
129
+ "cell_type": "code",
130
+ "execution_count": null,
131
+ "id": "8b95335e-9efc-44d9-8b6f-9cf8c6929dc7",
132
+ "metadata": {},
133
+ "outputs": [],
134
+ "source": []
135
+ }
136
+ ],
137
+ "metadata": {
138
+ "kernelspec": {
139
+ "display_name": "Python 3",
140
+ "language": "python",
141
+ "name": "python3"
142
+ },
143
+ "language_info": {
144
+ "codemirror_mode": {
145
+ "name": "ipython",
146
+ "version": 3
147
+ },
148
+ "file_extension": ".py",
149
+ "mimetype": "text/x-python",
150
+ "name": "python",
151
+ "nbconvert_exporter": "python",
152
+ "pygments_lexer": "ipython3",
153
+ "version": "3.12.10"
154
+ }
155
+ },
156
+ "nbformat": 4,
157
+ "nbformat_minor": 5
158
+ }
Chapter1-NeuralNetwork.ipynb ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 2,
6
+ "id": "2b22b7ad-9329-477a-a8f4-583fb23a8471",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import numpy as np\n",
11
+ "import tensorflow as tf\n",
12
+ "from tensorflow import keras\n",
13
+ "import pandas as pd\n",
14
+ "import matplotlib\n",
15
+ "matplotlib.use(\"TkAgg\")\n",
16
+ "import matplotlib.pyplot as plt"
17
+ ]
18
+ },
19
+ {
20
+ "cell_type": "code",
21
+ "execution_count": 3,
22
+ "id": "8b9896be-f135-4c8d-9c00-c6fe7e444172",
23
+ "metadata": {},
24
+ "outputs": [
25
+ {
26
+ "name": "stdout",
27
+ "output_type": "stream",
28
+ "text": [
29
+ "(60000, 28, 28)\n",
30
+ "uint8\n"
31
+ ]
32
+ }
33
+ ],
34
+ "source": [
35
+ "fashion_mnist = keras.datasets.fashion_mnist\n",
36
+ "\n",
37
+ "(x_train_full, y_train_full), (x_test, y_test) = fashion_mnist.load_data()\n",
38
+ "x_test = x_test / 255.0\n",
39
+ "\n",
40
+ "print(x_train_full.shape)\n",
41
+ "print(x_train_full.dtype)\n",
42
+ "\n",
43
+ "x_valid, x_train = x_train_full[:5000] / 255.0, x_train_full[5000:] / 255.0\n",
44
+ "y_valid, y_train = y_train_full[:5000], y_train_full[5000:]\n",
45
+ "\n",
46
+ "class_names = [\n",
47
+ " \"T-shirt/top\", \"Trouser\", \"Pullover\", \"Dress\", \"Coat\",\n",
48
+ " \"Sandal\", \"Shirt\", \"Sneaker\", \"Bag\", \"Ankle boot\"\n",
49
+ "]"
50
+ ]
51
+ },
52
+ {
53
+ "cell_type": "code",
54
+ "execution_count": 4,
55
+ "id": "c4514be8-3e16-4f63-bea4-adc8e2576e43",
56
+ "metadata": {},
57
+ "outputs": [
58
+ {
59
+ "name": "stderr",
60
+ "output_type": "stream",
61
+ "text": [
62
+ "C:\\Users\\lacer\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\keras\\src\\layers\\reshaping\\flatten.py:37: 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",
63
+ " super().__init__(**kwargs)\n"
64
+ ]
65
+ }
66
+ ],
67
+ "source": [
68
+ "model = keras.models.Sequential()\n",
69
+ "model.add(keras.layers.Flatten(input_shape=(28, 28)))\n",
70
+ "model.add(keras.layers.Dense(300, activation='relu'))\n",
71
+ "model.add(keras.layers.Dense(100, activation='relu'))\n",
72
+ "model.add(keras.layers.Dense(10, activation='softmax'))"
73
+ ]
74
+ },
75
+ {
76
+ "cell_type": "code",
77
+ "execution_count": 6,
78
+ "id": "80db0e8a-cc96-4752-8bec-60315ad34bec",
79
+ "metadata": {},
80
+ "outputs": [
81
+ {
82
+ "name": "stdout",
83
+ "output_type": "stream",
84
+ "text": [
85
+ "WARNING:tensorflow:TensorFlow GPU support is not available on native Windows for TensorFlow >= 2.11. Even if CUDA/cuDNN are installed, GPU will not be used. Please use WSL2 or the TensorFlow-DirectML plugin.\n",
86
+ "Epoch 1/30\n",
87
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.7659 - loss: 0.7165 - val_accuracy: 0.8362 - val_loss: 0.5032\n",
88
+ "Epoch 2/30\n",
89
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8292 - loss: 0.4888 - val_accuracy: 0.8542 - val_loss: 0.4361\n",
90
+ "Epoch 3/30\n",
91
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8441 - loss: 0.4461 - val_accuracy: 0.8642 - val_loss: 0.4142\n",
92
+ "Epoch 4/30\n",
93
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8529 - loss: 0.4180 - val_accuracy: 0.8654 - val_loss: 0.3972\n",
94
+ "Epoch 5/30\n",
95
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8600 - loss: 0.3981 - val_accuracy: 0.8600 - val_loss: 0.3943\n",
96
+ "Epoch 6/30\n",
97
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8655 - loss: 0.3811 - val_accuracy: 0.8694 - val_loss: 0.3724\n",
98
+ "Epoch 7/30\n",
99
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8690 - loss: 0.3680 - val_accuracy: 0.8668 - val_loss: 0.3823\n",
100
+ "Epoch 8/30\n",
101
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8726 - loss: 0.3573 - val_accuracy: 0.8724 - val_loss: 0.3629\n",
102
+ "Epoch 9/30\n",
103
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.8777 - loss: 0.3461 - val_accuracy: 0.8768 - val_loss: 0.3452\n",
104
+ "Epoch 10/30\n",
105
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8804 - loss: 0.3365 - val_accuracy: 0.8792 - val_loss: 0.3440\n",
106
+ "Epoch 11/30\n",
107
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8837 - loss: 0.3282 - val_accuracy: 0.8698 - val_loss: 0.3532\n",
108
+ "Epoch 12/30\n",
109
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8858 - loss: 0.3197 - val_accuracy: 0.8814 - val_loss: 0.3315\n",
110
+ "Epoch 13/30\n",
111
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8886 - loss: 0.3127 - val_accuracy: 0.8804 - val_loss: 0.3382\n",
112
+ "Epoch 14/30\n",
113
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8911 - loss: 0.3053 - val_accuracy: 0.8738 - val_loss: 0.3601\n",
114
+ "Epoch 15/30\n",
115
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8923 - loss: 0.2997 - val_accuracy: 0.8816 - val_loss: 0.3278\n",
116
+ "Epoch 16/30\n",
117
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8951 - loss: 0.2938 - val_accuracy: 0.8834 - val_loss: 0.3259\n",
118
+ "Epoch 17/30\n",
119
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.8983 - loss: 0.2865 - val_accuracy: 0.8850 - val_loss: 0.3281\n",
120
+ "Epoch 18/30\n",
121
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9000 - loss: 0.2809 - val_accuracy: 0.8832 - val_loss: 0.3194\n",
122
+ "Epoch 19/30\n",
123
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9008 - loss: 0.2760 - val_accuracy: 0.8886 - val_loss: 0.3071\n",
124
+ "Epoch 20/30\n",
125
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9016 - loss: 0.2716 - val_accuracy: 0.8820 - val_loss: 0.3401\n",
126
+ "Epoch 21/30\n",
127
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 2ms/step - accuracy: 0.9035 - loss: 0.2662 - val_accuracy: 0.8890 - val_loss: 0.3063\n",
128
+ "Epoch 22/30\n",
129
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9061 - loss: 0.2614 - val_accuracy: 0.8900 - val_loss: 0.3113\n",
130
+ "Epoch 23/30\n",
131
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9069 - loss: 0.2565 - val_accuracy: 0.8888 - val_loss: 0.3085\n",
132
+ "Epoch 24/30\n",
133
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 3ms/step - accuracy: 0.9091 - loss: 0.2524 - val_accuracy: 0.8842 - val_loss: 0.3263\n",
134
+ "Epoch 25/30\n",
135
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9102 - loss: 0.2487 - val_accuracy: 0.8894 - val_loss: 0.3044\n",
136
+ "Epoch 26/30\n",
137
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9108 - loss: 0.2446 - val_accuracy: 0.8914 - val_loss: 0.2958\n",
138
+ "Epoch 27/30\n",
139
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9133 - loss: 0.2392 - val_accuracy: 0.8788 - val_loss: 0.3307\n",
140
+ "Epoch 28/30\n",
141
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9149 - loss: 0.2362 - val_accuracy: 0.8914 - val_loss: 0.2978\n",
142
+ "Epoch 29/30\n",
143
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9171 - loss: 0.2317 - val_accuracy: 0.8886 - val_loss: 0.3139\n",
144
+ "Epoch 30/30\n",
145
+ "\u001b[1m1719/1719\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 3ms/step - accuracy: 0.9177 - loss: 0.2281 - val_accuracy: 0.8922 - val_loss: 0.3038\n"
146
+ ]
147
+ }
148
+ ],
149
+ "source": [
150
+ "model.compile(\n",
151
+ " loss=\"sparse_categorical_crossentropy\",\n",
152
+ " optimizer=\"sgd\",\n",
153
+ " metrics=[\"accuracy\"]\n",
154
+ ")\n",
155
+ "\n",
156
+ "history = model.fit(\n",
157
+ " x_train,\n",
158
+ " y_train,\n",
159
+ " epochs=30 ,\n",
160
+ " validation_data=(x_valid, y_valid)\n",
161
+ ")"
162
+ ]
163
+ },
164
+ {
165
+ "cell_type": "code",
166
+ "execution_count": 8,
167
+ "id": "2a081c04-338c-40e6-89d1-857ec6ca3232",
168
+ "metadata": {},
169
+ "outputs": [],
170
+ "source": [
171
+ "pd.DataFrame(history.history).plot(figsize=(8, 5))\n",
172
+ "plt.grid(True)\n",
173
+ "plt.gca().set_ylim(0, 1)\n",
174
+ "plt.show()\n"
175
+ ]
176
+ },
177
+ {
178
+ "cell_type": "code",
179
+ "execution_count": 9,
180
+ "id": "7cd5d8ac-6a3e-4a92-b4ef-574923bf4b71",
181
+ "metadata": {},
182
+ "outputs": [
183
+ {
184
+ "name": "stdout",
185
+ "output_type": "stream",
186
+ "text": [
187
+ "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - accuracy: 0.8787 - loss: 0.3378\n"
188
+ ]
189
+ },
190
+ {
191
+ "data": {
192
+ "text/plain": [
193
+ "[0.33777710795402527, 0.8787000179290771]"
194
+ ]
195
+ },
196
+ "execution_count": 9,
197
+ "metadata": {},
198
+ "output_type": "execute_result"
199
+ }
200
+ ],
201
+ "source": [
202
+ "model.evaluate(x_test, y_test)\n"
203
+ ]
204
+ },
205
+ {
206
+ "cell_type": "code",
207
+ "execution_count": 12,
208
+ "id": "6d401ab5-a415-4c92-98b6-01ac1c15dd47",
209
+ "metadata": {},
210
+ "outputs": [
211
+ {
212
+ "name": "stdout",
213
+ "output_type": "stream",
214
+ "text": [
215
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step\n",
216
+ "[[0. 0. 0. 0. 0. 0.01 0. 0.03 0. 0.95]\n",
217
+ " [0. 0. 1. 0. 0. 0. 0. 0. 0. 0. ]\n",
218
+ " [0. 1. 0. 0. 0. 0. 0. 0. 0. 0. ]]\n",
219
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step\n",
220
+ "[9 2 1]\n",
221
+ "['Ankle boot' 'Pullover' 'Trouser']\n"
222
+ ]
223
+ }
224
+ ],
225
+ "source": [
226
+ "x_new = x_test[:3]\n",
227
+ "y_proba = model.predict(x_new)\n",
228
+ "print(y_proba.round(2))\n",
229
+ "\n",
230
+ "y_pred = model.predict(x_new).argmax(axis=1)\n",
231
+ "print(y_pred)\n",
232
+ "\n",
233
+ "print(np.array(class_names)[y_pred])\n"
234
+ ]
235
+ },
236
+ {
237
+ "cell_type": "code",
238
+ "execution_count": null,
239
+ "id": "5b476174-b4af-43fb-b1f4-8b182c3af14d",
240
+ "metadata": {},
241
+ "outputs": [],
242
+ "source": []
243
+ }
244
+ ],
245
+ "metadata": {
246
+ "kernelspec": {
247
+ "display_name": "Python 3",
248
+ "language": "python",
249
+ "name": "python3"
250
+ },
251
+ "language_info": {
252
+ "codemirror_mode": {
253
+ "name": "ipython",
254
+ "version": 3
255
+ },
256
+ "file_extension": ".py",
257
+ "mimetype": "text/x-python",
258
+ "name": "python",
259
+ "nbconvert_exporter": "python",
260
+ "pygments_lexer": "ipython3",
261
+ "version": "3.12.10"
262
+ }
263
+ },
264
+ "nbformat": 4,
265
+ "nbformat_minor": 5
266
+ }
Chapter1.1-NeuralNetwork.ipynb ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 4,
6
+ "id": "4d62143b-6a33-4c02-8b1d-3d48d1256737",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "from sklearn.datasets import fetch_california_housing\n",
11
+ "from sklearn.model_selection import train_test_split\n",
12
+ "from sklearn.preprocessing import StandardScaler\n",
13
+ "\n",
14
+ "import numpy as np\n",
15
+ "import tensorflow as tf\n",
16
+ "from tensorflow import keras\n",
17
+ "import pandas as pd\n",
18
+ "import matplotlib\n",
19
+ "matplotlib.use(\"TkAgg\")\n",
20
+ "import matplotlib.pyplot as plt"
21
+ ]
22
+ },
23
+ {
24
+ "cell_type": "code",
25
+ "execution_count": 14,
26
+ "id": "d77530d4-e76b-4958-961e-a08bb19a7977",
27
+ "metadata": {},
28
+ "outputs": [],
29
+ "source": [
30
+ "housing = fetch_california_housing()\n",
31
+ "x_train_full, x_test, y_train_full, y_test = train_test_split(housing.data,housing.target)\n",
32
+ "x_train, x_valid, y_train, y_valid = train_test_split(x_train_full, y_train_full)\n",
33
+ "\n",
34
+ "scaler=StandardScaler()\n",
35
+ "x_train = scaler.fit_transform(x_train)\n",
36
+ "x_valid = scaler.transform(x_valid)\n",
37
+ "x_test=scaler.transform(x_test)"
38
+ ]
39
+ },
40
+ {
41
+ "cell_type": "code",
42
+ "execution_count": null,
43
+ "id": "55bd5b4b-8f34-4ade-89b3-35cfcbe61d7d",
44
+ "metadata": {},
45
+ "outputs": [],
46
+ "source": [
47
+ "model = keras.models.Sequential([keras.layers.Dense(30, activation = \"relu\", input_shape=x_train.shape[1:]), keras.layers.Dense(1)])\n"
48
+ ]
49
+ },
50
+ {
51
+ "cell_type": "code",
52
+ "execution_count": null,
53
+ "id": "736db746-f0b9-4a4b-b90f-6ae3cda03447",
54
+ "metadata": {
55
+ "scrolled": true
56
+ },
57
+ "outputs": [],
58
+ "source": [
59
+ "input_ = keras.layers.Input(shape=x_train.shape[1:])\n",
60
+ "hidden1 = keras.layers.Dense(30, activation=\"relu\")(input_)\n",
61
+ "hidden2 = keras.layers.Dense(30, activation=\"relu\")(hidden1)\n",
62
+ "concat = keras.layers.Concatenate()([input_,hidden2])\n",
63
+ "output = keras.layers.Dense(1)(concat)\n",
64
+ "model = keras.Model(inputs=[input_], outputs=[output])\n"
65
+ ]
66
+ },
67
+ {
68
+ "cell_type": "code",
69
+ "execution_count": 16,
70
+ "id": "af7e711e-d8df-44d6-bf50-70ee09ee2ae6",
71
+ "metadata": {},
72
+ "outputs": [
73
+ {
74
+ "name": "stdout",
75
+ "output_type": "stream",
76
+ "text": [
77
+ "Epoch 1/20\n",
78
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 1.7751 - val_loss: 1.3058\n",
79
+ "Epoch 2/20\n",
80
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.8318 - val_loss: 0.8696\n",
81
+ "Epoch 3/20\n",
82
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.7257 - val_loss: 0.7567\n",
83
+ "Epoch 4/20\n",
84
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.6701 - val_loss: 0.6548\n",
85
+ "Epoch 5/20\n",
86
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.6205 - val_loss: 0.6165\n",
87
+ "Epoch 6/20\n",
88
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.5843 - val_loss: 0.5791\n",
89
+ "Epoch 7/20\n",
90
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.5507 - val_loss: 0.5629\n",
91
+ "Epoch 8/20\n",
92
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.5270 - val_loss: 0.5499\n",
93
+ "Epoch 9/20\n",
94
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.5061 - val_loss: 0.5127\n",
95
+ "Epoch 10/20\n",
96
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.4899 - val_loss: 0.4930\n",
97
+ "Epoch 11/20\n",
98
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.4746 - val_loss: 0.4816\n",
99
+ "Epoch 12/20\n",
100
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.4634 - val_loss: 0.4685\n",
101
+ "Epoch 13/20\n",
102
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.4539 - val_loss: 0.4632\n",
103
+ "Epoch 14/20\n",
104
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.4478 - val_loss: 0.4546\n",
105
+ "Epoch 15/20\n",
106
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.4418 - val_loss: 0.4485\n",
107
+ "Epoch 16/20\n",
108
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.4374 - val_loss: 0.4442\n",
109
+ "Epoch 17/20\n",
110
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.4337 - val_loss: 0.4400\n",
111
+ "Epoch 18/20\n",
112
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.4304 - val_loss: 0.4377\n",
113
+ "Epoch 19/20\n",
114
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.4274 - val_loss: 0.4378\n",
115
+ "Epoch 20/20\n",
116
+ "\u001b[1m363/363\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.4257 - val_loss: 0.4346\n",
117
+ "\u001b[1m162/162\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.4405\n",
118
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 108ms/step\n",
119
+ "[[1.3971645]\n",
120
+ " [3.2480707]\n",
121
+ " [2.94071 ]]\n"
122
+ ]
123
+ }
124
+ ],
125
+ "source": [
126
+ "x_train_A, x_train_B = x_train[:, :5], x_train[:, 5:]\n",
127
+ "x_valid_A, x_valid_B = x_valid[:, :5], x_valid[:, 5:]\n",
128
+ "x_test_A, x_test_B = x_test[:, :5], x_test[:, 5:]\n",
129
+ "x_new_A, x_new_B = x_test_A[:3], x_test_B[:3]\n",
130
+ "\n",
131
+ "# Construir modelo\n",
132
+ "input_A = keras.layers.Input(shape=[5], name=\"wide_input\")\n",
133
+ "input_B = keras.layers.Input(shape=[3], name=\"deep_input\")\n",
134
+ "\n",
135
+ "hidden1 = keras.layers.Dense(30, activation=\"relu\")(input_B)\n",
136
+ "hidden2 = keras.layers.Dense(30, activation=\"relu\")(hidden1)\n",
137
+ "\n",
138
+ "concat = keras.layers.Concatenate()([input_A, hidden2])\n",
139
+ "output = keras.layers.Dense(1, name=\"output\")(concat)\n",
140
+ "\n",
141
+ "model = keras.Model(inputs=[input_A, input_B], outputs=[output])\n",
142
+ "\n",
143
+ "# Compilar\n",
144
+ "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(learning_rate=1e-3))\n",
145
+ "\n",
146
+ "# Treinar\n",
147
+ "history = model.fit(\n",
148
+ " (x_train_A, x_train_B), y_train,\n",
149
+ " epochs=20,\n",
150
+ " validation_data=((x_valid_A, x_valid_B), y_valid)\n",
151
+ ")\n",
152
+ "\n",
153
+ "# Avaliar\n",
154
+ "mse_test = model.evaluate((x_test_A, x_test_B), y_test)\n",
155
+ "\n",
156
+ "# Predizer\n",
157
+ "y_pred = model.predict((x_new_A, x_new_B))\n",
158
+ "print(y_pred)"
159
+ ]
160
+ },
161
+ {
162
+ "cell_type": "code",
163
+ "execution_count": null,
164
+ "id": "7835c49d-10bf-44cb-a90b-1cb808ce0be7",
165
+ "metadata": {},
166
+ "outputs": [],
167
+ "source": [
168
+ "model.compile(loss=\"mean_squared_error\", optimizer=\"adam\")\n",
169
+ "history = model.fit(x_train, y_train, epochs=20, validation_data=(x_valid, y_valid))\n",
170
+ "mse_test = model.evaluate(x_test, y_test)\n",
171
+ "\n",
172
+ "x_new = x_test[:3]\n",
173
+ "y_pred = model.predict(x_new)\n",
174
+ "\n",
175
+ "print(y_pred)"
176
+ ]
177
+ },
178
+ {
179
+ "cell_type": "code",
180
+ "execution_count": null,
181
+ "id": "f052ffc0-841f-4044-a40d-7c57216e0dc6",
182
+ "metadata": {},
183
+ "outputs": [],
184
+ "source": []
185
+ }
186
+ ],
187
+ "metadata": {
188
+ "kernelspec": {
189
+ "display_name": "Python 3",
190
+ "language": "python",
191
+ "name": "python3"
192
+ },
193
+ "language_info": {
194
+ "codemirror_mode": {
195
+ "name": "ipython",
196
+ "version": 3
197
+ },
198
+ "file_extension": ".py",
199
+ "mimetype": "text/x-python",
200
+ "name": "python",
201
+ "nbconvert_exporter": "python",
202
+ "pygments_lexer": "ipython3",
203
+ "version": "3.12.10"
204
+ }
205
+ },
206
+ "nbformat": 4,
207
+ "nbformat_minor": 5
208
+ }
Chapter1.2-NeuralNetwork.ipynb ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "177faf3e-cec4-4a9f-a613-4c8838af30c1",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "#No keras existem os modelos de redes neurais estaticos, funcionais e dinamicmos. Neste notebook lidaresmos com dinamico"
11
+ ]
12
+ },
13
+ {
14
+ "cell_type": "code",
15
+ "execution_count": null,
16
+ "id": "ef8dbd4c-3443-4a5f-b8e1-99b6f0d958b6",
17
+ "metadata": {},
18
+ "outputs": [],
19
+ "source": [
20
+ "from sklearn.datasets import fetch_california_housing\n",
21
+ "from sklearn.model_selection import train_test_split\n",
22
+ "from sklearn.preprocessing import StandardScaler\n",
23
+ "\n",
24
+ "import numpy as np\n",
25
+ "import tensorflow as tf\n",
26
+ "from tensorflow import keras\n",
27
+ "import pandas as pd\n",
28
+ "import matplotlib\n",
29
+ "matplotlib.use(\"TkAgg\")\n",
30
+ "import matplotlib.pyplot as plt"
31
+ ]
32
+ },
33
+ {
34
+ "cell_type": "code",
35
+ "execution_count": 3,
36
+ "id": "8b95335e-9efc-44d9-8b6f-9cf8c6929dc7",
37
+ "metadata": {},
38
+ "outputs": [
39
+ {
40
+ "data": {
41
+ "application/vnd.jupyter.widget-view+json": {
42
+ "model_id": "7c30100467c14c088b36a2be435e0014",
43
+ "version_major": 2,
44
+ "version_minor": 0
45
+ },
46
+ "text/plain": [
47
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
48
+ ]
49
+ },
50
+ "metadata": {},
51
+ "output_type": "display_data"
52
+ },
53
+ {
54
+ "ename": "RepositoryNotFoundError",
55
+ "evalue": "401 Client Error. (Request ID: Root=1-69d2b972-0d1155714c67789b4cfd9781;b40739f2-40be-43b8-8a63-57d36b83342d)\n\nRepository Not Found for url: https://huggingface.co/api/models/SamuelRx/FirstModel/preupload/main.\nPlease make sure you specified the correct `repo_id` and `repo_type`.\nIf you are trying to access a private or gated repo, make sure you are authenticated and your token has the required permissions.\nFor more details, see https://huggingface.co/docs/huggingface_hub/authentication\nInvalid username or password.\nNote: Creating a commit assumes that the repo already exists on the Huggingface Hub. Please use `create_repo` if it's not the case.",
56
+ "output_type": "error",
57
+ "traceback": [
58
+ "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
59
+ "\u001b[31mHTTPStatusError\u001b[39m Traceback (most recent call last)",
60
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\huggingface_hub\\utils\\_http.py:761\u001b[39m, in \u001b[36mhf_raise_for_status\u001b[39m\u001b[34m(response, endpoint_name)\u001b[39m\n\u001b[32m 760\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m761\u001b[39m \u001b[43mresponse\u001b[49m\u001b[43m.\u001b[49m\u001b[43mraise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 762\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m httpx.HTTPStatusError \u001b[38;5;28;01mas\u001b[39;00m e:\n",
61
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\httpx\\_models.py:829\u001b[39m, in \u001b[36mResponse.raise_for_status\u001b[39m\u001b[34m(self)\u001b[39m\n\u001b[32m 828\u001b[39m message = message.format(\u001b[38;5;28mself\u001b[39m, error_type=error_type)\n\u001b[32m--> \u001b[39m\u001b[32m829\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m HTTPStatusError(message, request=request, response=\u001b[38;5;28mself\u001b[39m)\n",
62
+ "\u001b[31mHTTPStatusError\u001b[39m: Client error '401 Unauthorized' for url 'https://huggingface.co/api/models/SamuelRx/FirstModel/preupload/main'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/401",
63
+ "\nThe above exception was the direct cause of the following exception:\n",
64
+ "\u001b[31mRepositoryNotFoundError\u001b[39m Traceback (most recent call last)",
65
+ "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[3]\u001b[39m\u001b[32m, line 7\u001b[39m\n\u001b[32m 4\u001b[39m login()\n\u001b[32m 6\u001b[39m \u001b[38;5;66;03m# Push your model files\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m7\u001b[39m \u001b[43mupload_folder\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfolder_path\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m.\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mSamuelRx/FirstModel\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmodel\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
66
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\huggingface_hub\\utils\\_validators.py:88\u001b[39m, in \u001b[36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m 84\u001b[39m validate_repo_id(arg_value)\n\u001b[32m 86\u001b[39m kwargs = smoothly_deprecate_legacy_arguments(fn_name=fn.\u001b[34m__name__\u001b[39m, kwargs=kwargs)\n\u001b[32m---> \u001b[39m\u001b[32m88\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
67
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\huggingface_hub\\hf_api.py:1932\u001b[39m, in \u001b[36mfuture_compatible.<locals>._inner\u001b[39m\u001b[34m(self, *args, **kwargs)\u001b[39m\n\u001b[32m 1929\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m.run_as_future(fn, \u001b[38;5;28mself\u001b[39m, *args, **kwargs)\n\u001b[32m 1931\u001b[39m \u001b[38;5;66;03m# Otherwise, call the function normally\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1932\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
68
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\huggingface_hub\\hf_api.py:5376\u001b[39m, in \u001b[36mHfApi.upload_folder\u001b[39m\u001b[34m(self, repo_id, folder_path, path_in_repo, commit_message, commit_description, token, repo_type, revision, create_pr, parent_commit, allow_patterns, ignore_patterns, delete_patterns, run_as_future)\u001b[39m\n\u001b[32m 5372\u001b[39m commit_operations = delete_operations + add_operations\n\u001b[32m 5374\u001b[39m commit_message = commit_message \u001b[38;5;129;01mor\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mUpload folder using huggingface_hub\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m-> \u001b[39m\u001b[32m5376\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mcreate_commit\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 5377\u001b[39m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 5378\u001b[39m \u001b[43m \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 5379\u001b[39m \u001b[43m \u001b[49m\u001b[43moperations\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcommit_operations\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 5380\u001b[39m \u001b[43m \u001b[49m\u001b[43mcommit_message\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcommit_message\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 5381\u001b[39m \u001b[43m \u001b[49m\u001b[43mcommit_description\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcommit_description\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 5382\u001b[39m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 5383\u001b[39m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 5384\u001b[39m \u001b[43m \u001b[49m\u001b[43mcreate_pr\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcreate_pr\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 5385\u001b[39m \u001b[43m \u001b[49m\u001b[43mparent_commit\u001b[49m\u001b[43m=\u001b[49m\u001b[43mparent_commit\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 5386\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
69
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\huggingface_hub\\utils\\_validators.py:88\u001b[39m, in \u001b[36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m 84\u001b[39m validate_repo_id(arg_value)\n\u001b[32m 86\u001b[39m kwargs = smoothly_deprecate_legacy_arguments(fn_name=fn.\u001b[34m__name__\u001b[39m, kwargs=kwargs)\n\u001b[32m---> \u001b[39m\u001b[32m88\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
70
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\huggingface_hub\\hf_api.py:1932\u001b[39m, in \u001b[36mfuture_compatible.<locals>._inner\u001b[39m\u001b[34m(self, *args, **kwargs)\u001b[39m\n\u001b[32m 1929\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m.run_as_future(fn, \u001b[38;5;28mself\u001b[39m, *args, **kwargs)\n\u001b[32m 1931\u001b[39m \u001b[38;5;66;03m# Otherwise, call the function normally\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1932\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
71
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\huggingface_hub\\hf_api.py:4688\u001b[39m, in \u001b[36mHfApi.create_commit\u001b[39m\u001b[34m(self, repo_id, operations, commit_message, commit_description, token, repo_type, revision, create_pr, num_threads, parent_commit, run_as_future, _hot_reload)\u001b[39m\n\u001b[32m 4685\u001b[39m \u001b[38;5;66;03m# If updating twice the same file or update then delete a file in a single commit\u001b[39;00m\n\u001b[32m 4686\u001b[39m _warn_on_overwriting_operations(operations)\n\u001b[32m-> \u001b[39m\u001b[32m4688\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mpreupload_lfs_files\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 4689\u001b[39m \u001b[43m \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4690\u001b[39m \u001b[43m \u001b[49m\u001b[43madditions\u001b[49m\u001b[43m=\u001b[49m\u001b[43madditions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4691\u001b[39m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4692\u001b[39m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4693\u001b[39m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[43m=\u001b[49m\u001b[43munquoted_revision\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# first-class methods take unquoted revision\u001b[39;49;00m\n\u001b[32m 4694\u001b[39m \u001b[43m \u001b[49m\u001b[43mcreate_pr\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcreate_pr\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4695\u001b[39m \u001b[43m \u001b[49m\u001b[43mnum_threads\u001b[49m\u001b[43m=\u001b[49m\u001b[43mnum_threads\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4696\u001b[39m \u001b[43m \u001b[49m\u001b[43mfree_memory\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# do not remove `CommitOperationAdd.path_or_fileobj` on LFS files for \"normal\" users\u001b[39;49;00m\n\u001b[32m 4697\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 4699\u001b[39m files_to_copy = _fetch_files_to_copy(\n\u001b[32m 4700\u001b[39m copies=copies,\n\u001b[32m 4701\u001b[39m repo_type=repo_type,\n\u001b[32m (...)\u001b[39m\u001b[32m 4705\u001b[39m endpoint=\u001b[38;5;28mself\u001b[39m.endpoint,\n\u001b[32m 4706\u001b[39m )\n\u001b[32m 4707\u001b[39m \u001b[38;5;66;03m# Remove no-op operations (files that have not changed)\u001b[39;00m\n",
72
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\huggingface_hub\\hf_api.py:4915\u001b[39m, in \u001b[36mHfApi.preupload_lfs_files\u001b[39m\u001b[34m(self, repo_id, additions, token, repo_type, revision, create_pr, num_threads, free_memory, gitignore_content)\u001b[39m\n\u001b[32m 4913\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(additions_no_upload_mode) > \u001b[32m0\u001b[39m:\n\u001b[32m 4914\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m-> \u001b[39m\u001b[32m4915\u001b[39m \u001b[43m_fetch_upload_modes\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 4916\u001b[39m \u001b[43m \u001b[49m\u001b[43madditions\u001b[49m\u001b[43m=\u001b[49m\u001b[43madditions_no_upload_mode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4917\u001b[39m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4918\u001b[39m \u001b[43m \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4919\u001b[39m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[43m=\u001b[49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4920\u001b[39m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4921\u001b[39m \u001b[43m \u001b[49m\u001b[43mendpoint\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mendpoint\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4922\u001b[39m \u001b[43m \u001b[49m\u001b[43mcreate_pr\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcreate_pr\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m 4923\u001b[39m \u001b[43m \u001b[49m\u001b[43mgitignore_content\u001b[49m\u001b[43m=\u001b[49m\u001b[43mgitignore_content\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 4924\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 4925\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m RepositoryNotFoundError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m 4926\u001b[39m e.append_to_message(_CREATE_COMMIT_NO_REPO_ERROR_MESSAGE)\n",
73
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\huggingface_hub\\utils\\_validators.py:88\u001b[39m, in \u001b[36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m 84\u001b[39m validate_repo_id(arg_value)\n\u001b[32m 86\u001b[39m kwargs = smoothly_deprecate_legacy_arguments(fn_name=fn.\u001b[34m__name__\u001b[39m, kwargs=kwargs)\n\u001b[32m---> \u001b[39m\u001b[32m88\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
74
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\huggingface_hub\\_commit_api.py:760\u001b[39m, in \u001b[36m_fetch_upload_modes\u001b[39m\u001b[34m(additions, repo_type, repo_id, headers, revision, endpoint, create_pr, gitignore_content)\u001b[39m\n\u001b[32m 751\u001b[39m payload[\u001b[33m\"\u001b[39m\u001b[33mgitIgnore\u001b[39m\u001b[33m\"\u001b[39m] = gitignore_content\n\u001b[32m 753\u001b[39m resp = http_backoff(\n\u001b[32m 754\u001b[39m \u001b[33m\"\u001b[39m\u001b[33mPOST\u001b[39m\u001b[33m\"\u001b[39m,\n\u001b[32m 755\u001b[39m \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mendpoint\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m/api/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrepo_type\u001b[38;5;132;01m}\u001b[39;00m\u001b[33ms/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrepo_id\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m/preupload/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrevision\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m,\n\u001b[32m (...)\u001b[39m\u001b[32m 758\u001b[39m params={\u001b[33m\"\u001b[39m\u001b[33mcreate_pr\u001b[39m\u001b[33m\"\u001b[39m: \u001b[33m\"\u001b[39m\u001b[33m1\u001b[39m\u001b[33m\"\u001b[39m} \u001b[38;5;28;01mif\u001b[39;00m create_pr \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[32m 759\u001b[39m )\n\u001b[32m--> \u001b[39m\u001b[32m760\u001b[39m \u001b[43mhf_raise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresp\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 761\u001b[39m preupload_info = _validate_preupload_info(resp.json())\n\u001b[32m 762\u001b[39m upload_modes.update(**{file[\u001b[33m\"\u001b[39m\u001b[33mpath\u001b[39m\u001b[33m\"\u001b[39m]: file[\u001b[33m\"\u001b[39m\u001b[33muploadMode\u001b[39m\u001b[33m\"\u001b[39m] \u001b[38;5;28;01mfor\u001b[39;00m file \u001b[38;5;129;01min\u001b[39;00m preupload_info[\u001b[33m\"\u001b[39m\u001b[33mfiles\u001b[39m\u001b[33m\"\u001b[39m]})\n",
75
+ "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python312\\site-packages\\huggingface_hub\\utils\\_http.py:847\u001b[39m, in \u001b[36mhf_raise_for_status\u001b[39m\u001b[34m(response, endpoint_name)\u001b[39m\n\u001b[32m 845\u001b[39m repo_err.repo_type = repo_type\n\u001b[32m 846\u001b[39m repo_err.repo_id = repo_id\n\u001b[32m--> \u001b[39m\u001b[32m847\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m repo_err \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01me\u001b[39;00m\n\u001b[32m 849\u001b[39m \u001b[38;5;28;01melif\u001b[39;00m response.status_code == \u001b[32m400\u001b[39m:\n\u001b[32m 850\u001b[39m message = (\n\u001b[32m 851\u001b[39m \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[33mBad request for \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mendpoint_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m endpoint:\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m endpoint_name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[33mBad request:\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m 852\u001b[39m )\n",
76
+ "\u001b[31mRepositoryNotFoundError\u001b[39m: 401 Client Error. (Request ID: Root=1-69d2b972-0d1155714c67789b4cfd9781;b40739f2-40be-43b8-8a63-57d36b83342d)\n\nRepository Not Found for url: https://huggingface.co/api/models/SamuelRx/FirstModel/preupload/main.\nPlease make sure you specified the correct `repo_id` and `repo_type`.\nIf you are trying to access a private or gated repo, make sure you are authenticated and your token has the required permissions.\nFor more details, see https://huggingface.co/docs/huggingface_hub/authentication\nInvalid username or password.\nNote: Creating a commit assumes that the repo already exists on the Huggingface Hub. Please use `create_repo` if it's not the case."
77
+ ]
78
+ }
79
+ ],
80
+ "source": [
81
+ "from huggingface_hub import login, upload_folder\n",
82
+ "\n",
83
+ "# (optional) Login with your Hugging Face credentials\n",
84
+ "login()\n",
85
+ "\n",
86
+ "# Push your model files\n",
87
+ "upload_folder(folder_path=\".\", repo_id=\"SamuelRx/FirstModel\", repo_type=\"model\")\n",
88
+ "\n"
89
+ ]
90
+ },
91
+ {
92
+ "cell_type": "code",
93
+ "execution_count": null,
94
+ "id": "09438fbc-8705-4712-8111-078a22cf8d1d",
95
+ "metadata": {},
96
+ "outputs": [],
97
+ "source": [
98
+ "housing = fetch_california_housing()\n",
99
+ "x_train_full, x_test, y_train_full, y_test = train_test_split(housing.data,housing.target)\n",
100
+ "x_train, x_valid, y_train, y_valid = train_test_split(x_train_full, y_train_full)\n",
101
+ "\n",
102
+ "scaler=StandardScaler()\n",
103
+ "x_train = scaler.fit_transform(x_train)\n",
104
+ "x_valid = scaler.transform(x_valid)\n",
105
+ "x_test=scaler.transform(x_test)"
106
+ ]
107
+ },
108
+ {
109
+ "cell_type": "code",
110
+ "execution_count": null,
111
+ "id": "0e80a374-8f22-40cd-ad12-f15898142f6b",
112
+ "metadata": {},
113
+ "outputs": [],
114
+ "source": [
115
+ "class WideAndDeepModel(keras.Model):\n",
116
+ " def __init__(self, units=30, activation=\"relu\", **kwargs):\n",
117
+ " super().__init__(**kwargs) \n",
118
+ " self.hidden1 = keras.layers.Dense(units, activation=activation)\n",
119
+ " self.hidden2 = keras.layers.Dense(units, activation=activation)\n",
120
+ " self.main_output = keras.layers.Dense(1)\n",
121
+ " self.aux_output = keras.layers.Dense(1)\n",
122
+ " def call(self, inputs):\n",
123
+ " input_A, input_B = inputs\n",
124
+ " hidden1 = self.hidden1(input_B)\n",
125
+ " hidden2 = self.hidden2(hidden1)\n",
126
+ " concat = keras.layers.concatenate([input_A, hidden2])\n",
127
+ " main_output = self.main_output(concat)\n",
128
+ " aux_output = self.aux_output(hidden2)\n",
129
+ " return main_output, aux_output"
130
+ ]
131
+ },
132
+ {
133
+ "cell_type": "code",
134
+ "execution_count": null,
135
+ "id": "3a81c2b8-4e95-453a-8d1a-4ba132bd483b",
136
+ "metadata": {},
137
+ "outputs": [],
138
+ "source": [
139
+ "model = WideAndDeepModel()\n",
140
+ "\n",
141
+ "model.compile(\n",
142
+ " loss=[\"mse\", \"mse\"], # uma loss para cada saída\n",
143
+ " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n",
144
+ " loss_weights=[0.8, 0.2] # opcional: peso de cada saída\n",
145
+ ")\n",
146
+ "\n",
147
+ "# Os targets precisam ser tuplas/listas correspondentes às saídas\n",
148
+ "history = model.fit(\n",
149
+ " (x_train_A, x_train_B), # entradas\n",
150
+ " (y_train, y_train), # targets: main_output e aux_output\n",
151
+ " epochs=20,\n",
152
+ " validation_data=((x_valid_A, x_valid_B), (y_valid, y_valid))\n",
153
+ ")\n",
154
+ "\n",
155
+ "# Avaliar\n",
156
+ "mse_test = model.evaluate((x_test_A, x_test_B), (y_test, y_test))\n",
157
+ "\n",
158
+ "# Predição\n",
159
+ "y_pred_main, y_pred_aux = model.predict((x_new_A, x_new_B))\n",
160
+ "print(y_pred_main)\n",
161
+ "\n",
162
+ "model.save(\"my_keras_model.h5\") #Salvando modelo, legal isso"
163
+ ]
164
+ },
165
+ {
166
+ "cell_type": "code",
167
+ "execution_count": null,
168
+ "id": "044977e1-310c-4f39-9e46-303c86bfbd0f",
169
+ "metadata": {},
170
+ "outputs": [],
171
+ "source": [
172
+ "model = keras.models.load_model(\"my_keras_model.h5\")"
173
+ ]
174
+ },
175
+ {
176
+ "cell_type": "code",
177
+ "execution_count": null,
178
+ "id": "079566ef-1c0c-400a-aeba-253ba01d1d5c",
179
+ "metadata": {},
180
+ "outputs": [],
181
+ "source": [
182
+ "checkpoint_cb = keras.callbacs.ModelCheckpoint(\"my_keras_model.h5\")\n",
183
+ "history = model.fit(x_train, y_train, epochs = 10, callbacks = [checkpoint_cb])"
184
+ ]
185
+ },
186
+ {
187
+ "cell_type": "code",
188
+ "execution_count": null,
189
+ "id": "cda6a722-d453-4544-a92f-42f3f2b6d131",
190
+ "metadata": {},
191
+ "outputs": [],
192
+ "source": []
193
+ }
194
+ ],
195
+ "metadata": {
196
+ "kernelspec": {
197
+ "display_name": "Python 3",
198
+ "language": "python",
199
+ "name": "python3"
200
+ },
201
+ "language_info": {
202
+ "codemirror_mode": {
203
+ "name": "ipython",
204
+ "version": 3
205
+ },
206
+ "file_extension": ".py",
207
+ "mimetype": "text/x-python",
208
+ "name": "python",
209
+ "nbconvert_exporter": "python",
210
+ "pygments_lexer": "ipython3",
211
+ "version": "3.12.10"
212
+ }
213
+ },
214
+ "nbformat": 4,
215
+ "nbformat_minor": 5
216
+ }