File size: 7,931 Bytes
35abf20 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<center>\n",
"\n",
"## [S. Mussard](https://sites.google.com/view/cv-stphane-mussard/accueil \"Homepage\")\n",
"\n",
"# UM6P\n",
"\n",
"# Natural Language Processing: LOGIT\n",
"\n",
"\n",
"<center> <a href=\"https://www.fgses-um6p.ma/\"><img src=\"UM6P.png\",style=\"float: left; max-width: 500px; width: 20\" />\n",
"\n",
"\n",
"\n",
"<div align=\"center\"> \n",
"<a href=\"https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html\"><img src=\"http://scikit-learn.org/stable/_static/scikit-learn-logo-small.png\" style=\"max-width: 180px; display: inline\" alt=\"Scikit-Learn\"/></a>\n",
"</div>\n",
"<div align=\"center\"> <a href=\"https://www.python.org/\"><img src=\"https://upload.wikimedia.org/wikipedia/commons/thumb/f/f8/Python_logo_and_wordmark.svg/390px-Python_logo_and_wordmark.svg.png\" style=\"max-width: 150px; display: inline\" alt=\"Python\"/></a> \n",
"</div>\n",
" \n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<div align=\"center\">\n",
"\n",
"## Sentiment Analysis"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"# Importation \n",
"\n",
"%matplotlib inline \n",
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"from sklearn import metrics\n",
"import torch\n",
"from torch.utils.data import Dataset, DataLoader\n",
"from transformers import AutoModel, AutoTokenizer\n",
"from transformers import AutoModelForSequenceClassification, AutoTokenizer\n",
"\n",
"import gradio as gr\n",
"from gradio.components import Label"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Some weights of the model checkpoint at ./poids were not used when initializing RobertaModel: ['classifier.out_proj.weight', 'classifier.dense.bias', 'classifier.out_proj.bias', 'classifier.dense.weight']\n",
"- This IS expected if you are initializing RobertaModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
"- This IS NOT expected if you are initializing RobertaModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
"Some weights of RobertaModel were not initialized from the model checkpoint at ./poids and are newly initialized: ['roberta.pooler.dense.weight', 'roberta.pooler.dense.bias']\n",
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
]
}
],
"source": [
"path = \"./weights\"\n",
"model = AutoModel.from_pretrained(path, trust_remote_code=True)\n",
"class CamembertClass(torch.nn.Module):\n",
" def __init__(self):\n",
" super(CamembertClass, self).__init__()\n",
" self.l1 = model\n",
" self.dropout = torch.nn.Dropout(0.1)\n",
" self.pre_classifier = torch.nn.Linear(1024, 1024)\n",
" self.classifier = torch.nn.Linear(1024, 3)\n",
"\n",
" def forward(self, input_ids, attention_mask, token_type_ids):\n",
" output_1 = self.l1(input_ids=input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids)\n",
" hidden_state = output_1[0]\n",
" pooler = hidden_state[:, 0]\n",
" pooler = self.pre_classifier(pooler)\n",
" pooler = torch.nn.ReLU()(pooler)\n",
" pooler = self.dropout(pooler)\n",
" output = self.classifier(pooler)\n",
" return output"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"#model_gradio = CamembertClass()\n",
"path = \"./pytorch_model.bin\"\n",
"model = torch.load(path, map_location=\"cpu\")\n",
"path_tokenizer = \"./\"\n",
"tokenizer = AutoTokenizer.from_pretrained(path_tokenizer)\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"#pip install pydantic==1.10.7"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running on local URL: http://127.0.0.1:7860\n",
"Running on public URL: https://93ecddda8853b625c0.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"https://93ecddda8853b625c0.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": []
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.eval() # Mettez votre modèle en mode évaluation\n",
"\n",
"# Fonction d'inférence pour Gradio\n",
"def predict(text):\n",
" inputs = tokenizer(text, return_tensors=\"pt\", padding=True, truncation=True, max_length=512)\n",
" \n",
" # Extract necessary inputs for the model\n",
" input_ids = inputs['input_ids']\n",
" attention_mask = inputs['attention_mask']\n",
" token_type_ids = inputs.get('token_type_ids', None) # Some models do not use segment IDs\n",
" \n",
" # Make prediction\n",
" with torch.no_grad():\n",
" # Directly use outputs if your model returns logits directly\n",
" logits = model(input_ids=input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids)\n",
"\n",
" \n",
" # Convert logits to probabilities\n",
" probabilities = torch.softmax(logits, dim=1).detach().cpu().numpy()[0]\n",
" # Replace the following with your actual classes\n",
" classes = ['Negative Sentiment', 'Positive Sentiment']\n",
" return {classes[i]: float(probabilities[i]) for i in range(len(classes))}\n",
"\n",
"# Création de l'interface Gradio\n",
"iface = gr.Interface(fn=predict,\n",
" inputs=gr.components.Textbox(placeholder=\"Enter your text here...\"),\n",
" outputs=gr.components.Label(num_top_classes=2))\n",
"iface.launch(share=True)\n"
]
}
],
"metadata": {
"hide_input": false,
"kernelspec": {
"display_name": "Python 3",
"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": "3.7.8"
},
"toc": {
"base_numbering": 1,
"nav_menu": {
"height": "244px",
"width": "252px"
},
"number_sections": true,
"sideBar": true,
"skip_h1_title": false,
"title_cell": "Table of Contents",
"title_sidebar": "Contents",
"toc_cell": false,
"toc_position": {},
"toc_section_display": "block",
"toc_window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 1
}
|