Spaces:
Runtime error
Runtime error
File size: 3,362 Bytes
14b8594 860860a 14b8594 860860a 14b8594 860860a 14b8594 860860a 14b8594 860860a 14b8594 860860a 14b8594 860860a 14b8594 860860a 14b8594 860860a 14b8594 |
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 |
from transformers.pipelines.image_segmentation import Predictions
from transformers import DistilBertForSequenceClassification, DistilBertTokenizer
import unidecode, re, unicodedata
from bs4 import BeautifulSoup
from urllib.request import urlopen
from urllib.parse import urlparse
from sklearn.metrics import confusion_matrix, accuracy_score
import torch.nn.functional as F
import gradio as gr
import torch
def check_by_title(title):
model = DistilBertForSequenceClassification.from_pretrained(".")
tokenizer = DistilBertTokenizer.from_pretrained(".")
test_encodings = tokenizer.encode_plus(
title,
truncation=True,
padding=True,
max_length=512,
return_tensors="pt"
)
model1=[]
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
test_input_ids = test_encodings["input_ids"].to(device)
test_attention_mask = test_encodings["attention_mask"].to(device)
with torch.no_grad():
model1= model.to(device)
model1.eval()
outputs= model1( test_input_ids, attention_mask=test_attention_mask)
logits = outputs.logits
predicted_labels = torch.argmax(logits, dim=1)
probabilities = F.softmax(logits, dim=1)
confidence_score_title = torch.max(probabilities, dim=1).values.tolist()
predicted_labels = torch.argmax(outputs.logits, dim=1)
label_mapping = {1: "SFW", 0: "NSFW"} # 1:True 0:false
predicted_label_title = label_mapping[predicted_labels.item()]
return predicted_label_title, confidence_score_title
def check_by_content(normalized_content_with_style):
test_encodings = tokenizer.encode_plus(
normalized_content_with_style,
truncation=True,
padding=True,
max_length=512,
return_tensors="pt"
)
model1=[]
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
test_input_ids = test_encodings["input_ids"].to(device)
test_attention_mask = test_encodings["attention_mask"].to(device)
with torch.no_grad():
model1= model.to(device)
model1.eval()
outputs= model1( test_input_ids, attention_mask=test_attention_mask)
logits = outputs.logits
predicted_labels = torch.argmax(logits, dim=1)
probabilities = F.softmax(logits, dim=1)
confidence_scores_content = torch.max(probabilities, dim=1).values.tolist()
label_mapping = {1: "SFW", 0: "NSFW"} # 1:True 0:false
predicted_label_content = label_mapping[predicted_labels.item()]
return predicted_label_content, confidence_scores_content
def predict_2(title, normalized_content_with_style):
predicted_label_title, confidence_score_title = check_by_title(title)
predicted_label_content, confidence_scores_content = check_by_content(normalized_content_with_style)
return predicted_label_title, confidence_score_title, predicted_label_content, confidence_scores_content
demo = gr.Interface(
fn=predict_2,
inputs=[
gr.inputs.Textbox(label="Title", placeholder="Enter title"),
gr.inputs.Textbox(label="Content", placeholder="enter Content"),
],
outputs= [
gr.outputs.Textbox(label="Title_prediction"),
gr.outputs.Textbox(label="Title_confidence_score"),
gr.outputs.Textbox(label="Content_prediction"),
gr.outputs.Textbox(label="content_confidence_score"),
#gr.outputs.Textbox(label="Description").style(show_copy_button=True)
],
)
demo.launch() |