Upload 5 files

README.md

@@ -1,10 +1,10 @@
 ---
-title: Mutilabel Tv Series Classifier
-emoji: 🏃
-colorFrom: red
-colorTo: indigo
+title: Multilabel MDB TV Series Classifier
+emoji: 🏢
+colorFrom: purple
+colorTo: pink
 sdk: gradio
-sdk_version: 4.12.0
+sdk_version: 3.39.0
 app_file: app.py
 pinned: false
 license: mit

Tv_Series-classifier-quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85696e6c038bdd44c0b547ecb1389ea763d68ce018ad229e423fa70b57536524
+size 82496318

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+import onnxruntime as rt
+from transformers import AutoTokenizer
+import torch, json
+
+tokenizer = AutoTokenizer.from_pretrained("distilroberta-base")
+
+with open("genre_types_encoded.json", "r") as fp:
+  encode_genre_types = json.load(fp)
+
+genres = list(encode_genre_types.keys())
+
+inf_session = rt.InferenceSession('Tv_Series-classifier-quantized.onnx')
+input_name = inf_session.get_inputs()[0].name
+output_name = inf_session.get_outputs()[0].name
+
+def classify_book_genre(description):
+  input_ids = tokenizer(description)['input_ids'][:512]
+  logits = inf_session.run([output_name], {input_name: [input_ids]})[0]
+  logits = torch.FloatTensor(logits)
+  probs = torch.sigmoid(logits)[0]
+  return dict(zip(genres, map(float, probs))) 
+
+label = gr.outputs.Label(num_top_classes=5)
+iface = gr.Interface(fn=classify_book_genre, inputs="text", outputs=label)
+iface.launch(inline=False)
+					

genre_types_encoded.json

@@ -0,0 +1 @@
+{"Action": 0, "Adventure": 1, "Drama": 2, "Comedy": 3, "Thriller": 4, "Sci-Fi": 5, "Mystery": 6, "Completed": 7, "Romance": 8, "Animation": 9, "Crime": 10, "Fantasy": 11, "Western": 12, "Sport": 13, "Horror": 14, "Music": 15, "Post-production": 16, "Filming": 17, "War": 18, "History": 19, "Biography": 20, "Family": 21, "37 min": 22, "Game-Show": 23, "Reality-TV": 24, "Short": 25, "Documentary": 26, "Musical": 27}