Add application file

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('imdb-classifier-quantized.onnx')
+input_name = inf_session.get_inputs()[0].name
+output_name = inf_session.get_outputs()[0].name
+
+def imdb_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=imdb_genre, inputs="text", outputs=label)
+iface.launch(inline=False)
+					

genre_types_encoded.json

@@ -0,0 +1 @@
+{"Action": 0, "Adventure": 1, "Drama": 2, "Fantasy": 3, "Horror": 4, "Mystery": 5, "Thriller": 6, "Animation": 7, "Comedy": 8, "Crime": 9, "Sci-Fi": 10, "Romance": 11, "History": 12, "War": 13, "Family": 14, "Biography": 15, "Reality-TV": 16, "Documentary": 17, "Music": 18, "Sport": 19}

imdb-classifier-quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089065acc32db2f73e8e4acd11b3a6f96d5a06071ce337b1671c36118db1f12b
+size 82479871

requirements.txt

@@ -0,0 +1,4 @@
+gradio==3.17.0
+onnxruntime==1.14.0
+torch==1.13.1
+transformers==4.26.0