Update app.py

app.py

@@ -1,16 +1,119 @@
 import gradio as gr
-from setfit import SetFitModel
+import asyncio
+import torch.nn.functional as F
+from torch import nn
+import os
+os.environ['CURL_CA_BUNDLE'] = ''
 
+app = Flask(__name__)
+
+
+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.pth"))
+model.eval()
 
-model = SetFitModel.from_pretrained("johnpaulbin/toxic-gte-small-3")
 
 def inf(inpt):
-    out = model.predict_proba([inpt])
-    
-    if out[0][0] > out[0][1]:
-        return "Not toxic " + str(out[0][0])
+
+    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 output[0][0] > output[0][1]:
+        return "Not toxic " + str(output[0][0])
     else:
-        return "Toxic! " + str(out[0][1])
+        return "Toxic! " + str(output[0][1])
 
 iface = gr.Interface(fn=inf, inputs="text", outputs="text")
 iface.queue(concurrency_count=500).launch()