first commit

app.py

@@ -0,0 +1,148 @@
+import datetime
+import gradio as gr
+import fasttext, torch, clip
+from sentence_transformers import SentenceTransformer, util
+ 
+model_en, preprocess_en = clip.load(model_tag="ViT-B/32")
+model_multi = SentenceTransformer(model_tag="sentence-transformers/clip-ViT-B-32-multilingual-v1")
+
+def prep_examples():
+    example_text1 = "Coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus. Most \
+    people who fall sick with COVID-19 will experience mild to moderate symptoms and recover without special treatment. \
+    However, some will become seriously ill and require medical attention."
+    example_labels1 = "business;;health related;;politics;;climate change"
+
+    example_text2 = "Elephants are"
+    example_labels2 = "big;;small;;strong;;fast;;carnivorous"
+
+    example_text3 = "Elephants"
+    example_labels3 = "are big;;can be very small;;generally not strong enough;;are faster than you think"
+
+    example_text4 = "Dogs are man's best friend"
+    example_labels4 = "positive;;negative;;neutral"
+
+    example_text5 = "Şampiyonlar Ligi’nde 5. hafta oynanan karşılaşmaların ardından sona erdi. Real Madrid, \
+    Inter ve Sporting oynadıkları mücadeleler sonrasında Son 16 turuna yükselmeyi başardı. \
+    Gecenin dev mücadelesinde ise Manchester City, PSG’yi yenerek liderliği garantiledi."
+    example_labels5 = "dünya;;ekonomi;;kültür;;siyaset;;spor;;teknoloji"
+
+    example_text6 = "Letzte Woche gab es einen Selbstmord in einer nahe gelegenen kolonie"
+    example_labels6 = "verbrechen;;tragödie;;stehlen"
+
+    example_text7 = "El autor se perfila, a los 50 años de su muerte, como uno de los grandes de su siglo"
+    example_labels7 = "cultura;;sociedad;;economia;;salud;;deportes"
+
+    example_text8 = "Россия в среду заявила, что военные учения в аннексированном Москвой Крыму закончились \
+    и что солдаты возвращаются в свои гарнизоны, на следующий день после того, как она объявила о первом выводе \
+    войск от границ Украины."
+    example_labels8 = "новости;;комедия"
+
+    example_text9 = "I quattro registi - Federico Fellini, Pier Paolo Pasolini, Bernardo Bertolucci e Vittorio De Sica - \
+    hanno utilizzato stili di ripresa diversi, ma hanno fortemente influenzato le giovani generazioni di registi."
+    example_labels9 = "cinema;;politica;;cibo"
+
+    example_text10 = "Ja, vi elsker dette landet,\
+    som det stiger frem,\
+    furet, værbitt over vannet,\
+    med de tusen hjem.\
+    Og som fedres kamp har hevet\
+    det av nød til seir"
+    example_labels10 = "helse;;sport;;religion;;mat;;patriotisme og nasjonalisme"
+
+    example_text11 = "Amar sonar bangla ami tomay bhalobasi"
+    example_labels11 = "bhalo;;kharap"
+
+    examples = [
+        [example_text1, example_labels1],
+        [example_text2, example_labels2],
+        [example_text3, example_labels3],
+        [example_text4, example_labels4],
+        [example_text5, example_labels5],
+        [example_text6, example_labels6],
+        [example_text7, example_labels7],
+        [example_text8, example_labels8],
+        [example_text9, example_labels9],
+        [example_text10, example_labels10],
+        [example_text11, example_labels11]]
+
+    return examples
+
+def detect_lang(sequence):
+    seq_lang = 'en'
+    
+    sequence = sequence.replace('\n', ' ')
+
+    try:
+        seq_lang = fasttext_model.predict(sequence, k=1)[0][0].split("__label__")[1]
+    except:
+        print("Language detection failed!",
+              "Date:{}, Sequence:{}".format(
+                  str(datetime.datetime.now())))
+
+    return seq_lang
+
+def sequence_to_classify(text, labels):
+	lang = detect_lang(text)
+	if lang == 'en':
+		model = model_en
+		preprocess = preprocess_en
+		hypothesis_template = "This example is {}."
+	else:
+		model = model_multi
+		hypothesis_template = "{}."
+	
+	labels = [hypothesis_template.format(label) for label in labels.split(";;")]
+	
+	if str(type(model)) == "<class 'clip.model.CLIP'>":
+		text_tokens = clip.tokenize(text)
+		text_features = model.encode_text(text_tokens)
+		
+		label_tokens = clip.tokenize(labels)
+		labels_features = model.encode_text(label_tokens)
+	else:    
+		text_features = torch.tensor(model.encode(text))
+		labels_features = torch.tensor(self.model.encode(labels))
+		
+	sim_scores = util.cos_sim(text_features, labels_features)
+    preds = []
+
+	for textlet, sim_score in zip([text], sim_scores):
+		out = []
+		pred = {}
+		for raw_score in sim_score:
+			out.append(raw_score.item() * 100)
+		probs = torch.tensor([out])
+		probs = probs.softmax(dim=-1).cpu().numpy()
+		scores = list(probs.flatten())
+
+		sorted_sl = sorted(zip(scores, candidate_labels), key=lambda t:t[0], reverse=True)  
+
+		pred["labels"] = textlet
+		pred["scores"], pred["labels"] = zip(*sorted_sl)
+		preds.append(pred)
+
+    predicted_labels = preds['labels']
+    predicted_scores = preds['scores']
+    clean_output = {idx: float(predicted_scores.pop(0)) for idx in predicted_labels}
+    print("Date:{}, Sequence:{}, Labels: {}".format(
+        str(datetime.datetime.now()),
+        text,
+        predicted_labels))
+
+    return clean_output
+
+iface = gr.Interface(
+    title="Alternate Zero-shot Multi-label Multilingual NLP Classifier",
+    description="Work in progress.",
+    fn=sequence_to_classify,
+    inputs=[gr.inputs.Textbox(lines=10,
+        label="Please enter the text you would like to classify...",
+        placeholder="Text here..."),
+        gr.inputs.Textbox(lines=2,
+        label="Please enter the candidate labels (separated by 2 consecutive semicolons)...",
+        placeholder="Labels here separated by ;;")],
+    outputs=gr.outputs.Label(num_top_classes=5),
+    #interpretation="default",
+    examples=prep_examples())
+
+iface.launch()

requirements.txt

@@ -0,0 +1,4 @@
+torch
+sentence-transformers
+git+https://github.com/openai/CLIP.git
+fasttext