Code Monkey home page Code Monkey logo

Comments (3)

avivihadar avatar avivihadar commented on May 21, 2024

Thank you again for this great work @wetherbeei, could you please advise how to extract the activations of the intermediate layers of BERT?

from patents-public-data.

wetherbeei avatar wetherbeei commented on May 21, 2024

@robert-srebrovic

from patents-public-data.

avivihadar avatar avivihadar commented on May 21, 2024

Hi @robert-srebrovic, thanks for supporting this repo! my goal is to load the cls embeddings (including intermediate layers). So far I've attempted to use the bert-for-tf2 package. However, it seems like some of the layers defined here are missing from the target model when attempting to load it:

l_input_ids  = keras.layers.Input(shape=(MAX_SEQ_LENGTH,), dtype='int32')

bert_params = bert.params_from_pretrained_ckpt(MODEL_DIR)
l_bert = bert.BertModelLayer.from_params(bert_params, name="bert")

output = l_bert(l_input_ids)
model_chk = keras.Model(inputs=l_input_ids, outputs=output)
model_chk.build(input_shape=(None, MAX_SEQ_LENGTH))
bert.load_bert_weights(l_bert, model_ckpt)

Specifically, the following weights are missing:

bert/pooler/dense/bias
bert/pooler/dense/kernel
cls/predictions/output_bias
cls/predictions/transform/LayerNorm/beta
cls/predictions/transform/LayerNorm/gamma
cls/predictions/transform/dense/bias
cls/predictions/transform/dense/kernel
cls/seq_relationship/output_bias
cls/seq_relationship/output_weights

Could you please advise what would be the best way to reintroduce the missing layers?

from patents-public-data.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.