Inference

[loretoparisi]

Hello, thanks for this project. I was able to correctly train a structshot using the train script. Could you show how to correctly run the inference for an input sequence?
In my understanding, the loading would look like

import os
import torch

from fewnerd.util.word_encoder import BERTWordEncoder
from fewnerd.model.proto import Proto
from fewnerd.model.nnshot import NNShot

# cache dir
cache_dir = os.getenv("cache_dir", "../../models")
model_path = 'structshot-inter-5-5-seed0.pth.tar'
model_name = 'structshot'
pretrain_ckpt = 'bert-base-uncased'
max_length = 100

# BERT word encoder
word_encoder = BERTWordEncoder(
        pretrain_ckpt,
        max_length)

if model_name == 'proto':
    # use dot instead of L2 distance for proto
    model = Proto(word_encoder, dot=True)
elif model_name == 'nnshot':
    model = NNShot(word_encoder, dot=False)
elif model_name == 'structshot':
    model = NNShot(word_encoder, dot=False)

model.load_state_dict(torch.load(os.path.join(cache_dir, model_path)))

but I get some errors on the state dicts (RuntimeError: Error(s) in loading state_dict for NNShot:) in this way...

Thank you in advance!

[yulinchen99]

to load the model properly, you can refer to

Few-NERD/util/framework.py

Line 353 in 84c0b59

for name, param in state_dict.items():

[pratikchhapolika]

@loretoparisi are you able to do inferencing on the trained model?

[loretoparisi]

@loretoparisi are you able to do inferencing on the trained model?

thanks for the question, it was time ago, but I think so with some trick, I have to check the notebook for the code...

[pratikchhapolika]

@loretoparisi are you able to do inferencing on the trained model?

thanks for the question, it was time ago, but I think so with some trick, I have to check the notebook for the code...

Ok. Thanks. Could you please attach your notebook code and data please. @loretoparisi

[pratikchhapolika]

@cyl628 For a single input sequence, how should we write the inference script?

[loretoparisi]

@loretoparisi are you able to do inferencing on the trained model?

thanks for the question, it was time ago, but I think so with some trick, I have to check the notebook for the code...

Ok. Thanks. Could you please attach your notebook code and data please. @loretoparisi

I have something here I will add the inference code there!

[pratikchhapolika]

@loretoparisi are you able to do inferencing on the trained model?

thanks for the question, it was time ago, but I think so with some trick, I have to check the notebook for the code...

Ok. Thanks. Could you please attach your notebook code and data please. @loretoparisi

I have something here I will add the inference code there!

Please add the inference code and how the output looks like for singe input.

[pratikchhapolika]

@loretoparisi are you able to do inferencing on the trained model?

thanks for the question, it was time ago, but I think so with some trick, I have to check the notebook for the code...

Ok. Thanks. Could you please attach your notebook code and data please. @loretoparisi

I have something here I will add the inference code there!

@loretoparisi Have you uploaded the inference script?

[loretoparisi]

@loretoparisi are you able to do inferencing on the trained model?

thanks for the question, it was time ago, but I think so with some trick, I have to check the notebook for the code...

Ok. Thanks. Could you please attach your notebook code and data please. @loretoparisi

I have something here I will add the inference code there!

@loretoparisi Have you uploaded the inference script?

not at this time, I will put it in the repo check updates, thanks.