David Beauchemin

Perfect! We will keep you updated.

Hi @crtnx, I will start, this week or so, a fine-tuning process for the three countries provided and will release a new model and a new table with performance. Also,...

@crtnx Ohh I did not know that. Do your best to get most countries on the list! We will work with that. There is no rush.

Updates: 11/08: Yeah, performance is not as good as expected after a fine-tuning procedure. It barely reaches 80%. I think there is not enough data. I will try another training...

@crtnx So far, there is a regression in the parser performance for non PO boxes address of about 10%. Also, both models' performances on PO box addresses are not as...

Hi @ml5ah, I only used ONNX once, and it was not a successful experience (it was my initial idea to handle Deepparse weights). If I recall right, the bottleneck was...

I've looked at [PyTorch doc](https://pytorch.org/docs/stable/onnx.html), and it still seems like you need to provide a batch-a-like dataset for the export. If you come up with a method that can export...

It seems like a float typing error (it converts some into a float and others into a long float). LSTM parameters are LongTensor, and it may be there the problem.

@ml5ah this post might be useful https://stackoverflow.com/questions/57299674/trouble-converting-lstm-pytorch-model-to-onnx.

@ml5ah I've just added the `save_model_weights` method to the AddressParser class into dev. It saves the PyTorch state dictionary into a pickle format. If you need to use the model...