Comments (6)
Ah we managed to access the hidden layers by explicitly loading the checkpoint - thanks!
from patents-public-data.
@benzitohhh could you please provide an example for this?
from patents-public-data.
Here's an example using bert-for-tf2 (https://github.com/kpe/bert-for-tf2)
It loads the checkpoint (https://storage.googleapis.com/patents-public-data-github/checkpoint.zip).
out_layer_ndxs
can be set to access whatever layers you need. So below we access the penultimate layer (-2).
import bert
from tensorflow import keras
import tensorflow as tf
MODEL_DIR = "./bert_model" // the downloaded checkpoint
MAX_SEQ_LEN = 256
l_input_ids = keras.layers.Input(shape=(MAX_SEQ_LEN,), dtype='int32')
bert_params = bert.params_from_pretrained_ckpt(MODEL_DIR)
bert_params.out_layer_ndxs = [-2]
l_bert = bert.BertModelLayer.from_params(bert_params, name="bert")
output = l_bert(l_input_ids)
model = keras.Model(inputs=l_input_ids, outputs=output)
model.build(input_shape=(None, MAX_SEQ_LEN))
# A simple input
texts = ["<CLS>", "The", "quick", "brown", "fox", "<SEP>"]
input_ids = [ 2, 1661, 3913, 2494, 4084, 3 ]
padding = [0] * (MAX_SEQ_LEN - len(input_ids))
input_ids_padded = input_ids + padding
result = model.predict([input_ids_padded])
from patents-public-data.
Hi @benzitohhh, thanks for providing the example. However, this seems to be missing the actual line for loading the weights (should be called after model.build):
bert.load_bert_weights(l_bert, model_ckpt)
However, the cls token weights do not seem to be defined in the target model. Did you attempt to redefine them on TF2?
from patents-public-data.
@avivihadar Ah thanks so much. You're totally right, I forgot to actually load the weights. Oooops :)
Maybe I'm misunderstanding, but the CLS token is just the first element in each sequence. So the weights should be there.
We actually have mainly been using bert-as-a-service (although it uses tensorflow1):
https://github.com/hanxiao/bert-as-service
from patents-public-data.
@avivihadar Oh wait, by CLS token, you mean the logits? Yeah we're not using that, we're just interested in getting a patent embedding (vectorisation).
from patents-public-data.
Related Issues (20)
- Expiration date HOT 2
- BERT for Patents yields 1024 element array, but embedding_v1 is 64 element HOT 5
- ResourceExhaustedError while running Document_representation_from_BERT HOT 2
- Empty Tables in the Dataset
- Linking proteins and humangenes annotation preferred name to identifier HOT 9
- Converting Tensorflow Bert for Patent saved model to keras.
- How to access hidden layers? HOT 3
- How to download HOT 5
- BERT-Base
- context tokens
- Generating new Document Embeddings
- Sklearn 1.1.1 Issue HOT 1
- Dataset lacking cited_by data even though its available on the website. HOT 4
- claim_text_extraction.ipynb df = pd.read_csv('./data/20k_G_and_H_publication_numbers.csv') workaround
- Lots of Patents in the latest patent dataset are missing a description
- Missing embedding HOT 1
- lack of "vocab"
- Description and claims are missing for JP patents data.
- Decreasing number of annotations in google patents research in recent batches
- confidence>1 for annotations in google patent research
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from patents-public-data.