Spaces:
Runtime error
Runtime error
File size: 3,698 Bytes
58627d4 38cf82b 58627d4 38cf82b 5efb4cb 38cf82b 58627d4 38cf82b 825a6ae 38cf82b 58627d4 38cf82b 58627d4 17692e5 |
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 |
import gradio as gr
import asyncio
import torch.nn.functional as F
from torch import nn
import os
os.environ['CURL_CA_BUNDLE'] = ''
from sentence_transformers import SentenceTransformer
sentencemodel = SentenceTransformer('johnpaulbin/toxic-gte-small-3')
USE_GPU = False
""" Use torchMoji to predict emojis from a single text input
"""
import numpy as np
import emoji, json
from torchmoji.global_variables import PRETRAINED_PATH, VOCAB_PATH
from torchmoji.sentence_tokenizer import SentenceTokenizer
from torchmoji.model_def import torchmoji_emojis
import torch
# Emoji map in emoji_overview.png
EMOJIS = ":joy: :unamused: :weary: :sob: :heart_eyes: \
:pensive: :ok_hand: :blush: :heart: :smirk: \
:grin: :notes: :flushed: :100: :sleeping: \
:relieved: :relaxed: :raised_hands: :two_hearts: :expressionless: \
:sweat_smile: :pray: :confused: :kissing_heart: :heartbeat: \
:neutral_face: :information_desk_person: :disappointed: :see_no_evil: :tired_face: \
:v: :sunglasses: :rage: :thumbsup: :cry: \
:sleepy: :yum: :triumph: :hand: :mask: \
:clap: :eyes: :gun: :persevere: :smiling_imp: \
:sweat: :broken_heart: :yellow_heart: :musical_note: :speak_no_evil: \
:wink: :skull: :confounded: :smile: :stuck_out_tongue_winking_eye: \
:angry: :no_good: :muscle: :facepunch: :purple_heart: \
:sparkling_heart: :blue_heart: :grimacing: :sparkles:".split(' ')
def top_elements(array, k):
ind = np.argpartition(array, -k)[-k:]
return ind[np.argsort(array[ind])][::-1]
with open("vocabulary.json", 'r') as f:
vocabulary = json.load(f)
st = SentenceTokenizer(vocabulary, 100)
emojimodel = torchmoji_emojis("pytorch_model.bin")
if USE_GPU:
emojimodel.to("cuda:0")
def deepmojify(sentence, top_n=5, prob_only=False):
list_emojis = []
def top_elements(array, k):
ind = np.argpartition(array, -k)[-k:]
return ind[np.argsort(array[ind])][::-1]
tokenized, _, _ = st.tokenize_sentences([sentence])
tokenized = np.array(tokenized).astype(int) # convert to float first
if USE_GPU:
tokenized = torch.tensor(tokenized).cuda() # then convert to PyTorch tensor
prob = emojimodel.forward(tokenized)[0]
if not USE_GPU:
prob = torch.tensor(prob)
if prob_only:
return prob
emoji_ids = top_elements(prob.cpu().numpy(), top_n)
emojis = map(lambda x: EMOJIS[x], emoji_ids)
list_emojis.append(emoji.emojize(f"{' '.join(emojis)}", language='alias'))
# returning the emojis as a list named as list_emojis
return list_emojis, prob
model = nn.Sequential(
nn.Linear(448, 300), # Increase the number of neurons
nn.ReLU(),
nn.BatchNorm1d(300), # Batch normalization
nn.Linear(300, 300), # Increase the number of neurons
nn.ReLU(),
nn.BatchNorm1d(300), # Batch normalization
nn.Linear(300, 200), # Increase the number of neurons
nn.ReLU(),
nn.BatchNorm1d(200), # Batch normalization
nn.Linear(200, 125), # Increase the number of neurons
nn.ReLU(),
nn.BatchNorm1d(125), # Batch normalization
nn.Linear(125, 2),
nn.Dropout(0.05) # Dropout
)
model.load_state_dict(torch.load("large-tuned.pth", map_location=torch.device('cpu')), strict=False)
model.eval()
def inf(inpt):
TEXT = inpt.lower()
probs = deepmojify(TEXT, prob_only=True)
embedding = sentencemodel.encode(TEXT, convert_to_tensor=True)
INPUT = torch.cat((probs, embedding))
output = F.softmax(model(INPUT.view(1, -1)), dim=1)
if not output[0][1] > 0.4:
return "Not toxic " + str(output[0][0])
else:
return "Toxic! " + str(output[0][1])
iface = gr.Interface(fn=inf, inputs="text", outputs="text")
iface.queue(concurrency_count=500).launch() |