Top fairseq issues

Accuracy drop after adding quant_noise to InceptionResnetV1

needs triage question
jmatak picture jmatak·17 Jun 2020·3 Comments

What do the metrics wps, ups and wpb mean in the training logger ?

needs triage question
shahbazsyed picture shahbazsyed·1 Jun 2020·2 Comments
👍1

Can not train with multi-gpus

needs triage question
Jambalaya11 picture Jambalaya11·26 Apr 2020·4 Comments

How to reproduce fine tuning EN-RO with mbart?

documentation
KasparPeterson picture KasparPeterson·24 Apr 2020·4 Comments

fairseq-generate shuffles test data?

needs triage question
ylmeng picture ylmeng·21 Apr 2020·1 Comments
❤1

Runtime error Missing key(s) in state_dict: "decoder.output_projection.weight". when loading NMT models from torch.hub

bug
akhileshgotmare picture akhileshgotmare·20 Apr 2020·7 Comments

CUDA out of Memory when fine-tuning mBART pre-trained CC25 model

needs triage question
gvskalyan picture gvskalyan·30 Mar 2020·8 Comments

Does Dynamic Quantization speed up Fairseq's Transfomer?

question
gvskalyan picture gvskalyan·24 Mar 2020·8 Comments

Cannot load Sentence Encoder: translation_from_pretrained_xlm

bug needs triage
smart-patrol picture smart-patrol·16 Mar 2020·11 Comments

DenoisingDataset EOS token not set properly for MultilingualDenoisingTask when --add-lang-token is set

bug
dkavaler picture dkavaler·6 Mar 2020·6 Comments
👍4
 Previous issues
Next issues