Skip to content

Instantly share code, notes, and snippets.

@eerkaijun

eerkaijun/predictions.py

Created August 14, 2020 14:02
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save eerkaijun/7aa6e306815f7ccbe16c37b99fe7058e to your computer and use it in GitHub Desktop.
Save eerkaijun/7aa6e306815f7ccbe16c37b99fe7058e to your computer and use it in GitHub Desktop.
Download ZIP
Make sentiment predictions on fine tuned BERT model
Raw
predictions.py
tf_batch = tokenizer(pred_sentences, max_length=128, padding=True, truncation=True, return_tensors='tf')
tf_outputs = model(tf_batch)
tf_predictions = tf.nn.softmax(tf_outputs[0], axis=-1)
labels = ['Negative','Positive']
label = tf.argmax(tf_predictions, axis=1)
label = label.numpy()
for i in range(len(pred_sentences)):
print(pred_sentences[i], ": ", labels[label[i]])
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment