Initial commit

requirements.txt

@@ -1,26 +1,37 @@
 anyio==3.6.2
+certifi==2022.12.7
+charset-normalizer==3.1.0
 click==8.1.3
 fastapi==0.92.0
+filelock==3.9.0
 h11==0.14.0
+huggingface-hub==0.13.1
 idna==3.4
 Jinja2==3.1.2
 joblib==1.2.0
 MarkupSafe==2.1.2
+nltk==3.8.1
 numpy==1.24.2
 nvidia-cublas-cu11==11.10.3.66
 nvidia-cuda-nvrtc-cu11==11.7.99
 nvidia-cuda-runtime-cu11==11.7.99
 nvidia-cudnn-cu11==8.5.0.96
+packaging==23.0
 pandas==1.5.3
 pydantic==1.10.5
 python-dateutil==2.8.2
 python-multipart==0.0.6
 pytz==2022.7.1
+PyYAML==6.0
 regex==2022.10.31
+requests==2.28.2
 six==1.16.0
 sniffio==1.3.0
 starlette==0.25.0
+tokenizers==0.13.2
 torch==1.13.1
 tqdm==4.65.0
+transformers==4.26.1
 typing_extensions==4.5.0
+urllib3==1.26.15
 uvicorn==0.20.0

src/inference.py

@@ -7,6 +7,7 @@ import torch
 
 import dataloader
 from model import Decoder, Encoder, EncoderDecoderModel
+from transformers import AutoModel
 
 with open("model/vocab.pkl", "rb") as vocab:
     words = pickle.load(vocab)
@@ -33,6 +34,8 @@ def inferenceAPI(text: str) -> str:
     decoder.to(device)
 
     # On instancie le modèle
+    model = AutoModel.from_pretrained("EveSa/SummaryProject-LSTM", revision="main")
+    model = AutoModel.PretrainedConfig()
     model = EncoderDecoderModel(encoder, decoder, vectoriser, device)
 
     model.load_state_dict(torch.load("model/model.pt", map_location=device))
@@ -51,6 +54,6 @@ def inferenceAPI(text: str) -> str:
     return vectoriser.decode(output)
 
 
-# if __name__ == "__main__":
-#     # inference()
-#     print(inferenceAPI("If you choose to use these attributes in logged messages, you need to exercise some care. In the above example, for instance, the Formatter has been set up with a format string which expects ‘clientip’ and ‘user’ in the attribute dictionary of the LogRecord. If these are missing, the message will not be logged because a string formatting exception will occur. So in this case, you always need to pass the extra dictionary with these keys."))
+if __name__ == "__main__":
+    # inference()
+    print(inferenceAPI("If you choose to use these attributes in logged messages, you need to exercise some care. In the above example, for instance, the Formatter has been set up with a format string which expects ‘clientip’ and ‘user’ in the attribute dictionary of the LogRecord. If these are missing, the message will not be logged because a string formatting exception will occur. So in this case, you always need to pass the extra dictionary with these keys."))

src/train.py

@@ -194,6 +194,7 @@ if __name__ == "__main__":
 
     torch.save(trained_classifier.state_dict(), "model/model.pt")
     vectoriser.save("model/vocab.pkl")
+    trained_classifier.config.to_json_file("config.json")
 
     print(f"test summary : {vectoriser.decode(dev_dataset[6][1])}")
     print(