fastai users   fastai dev


Developer chat ( 17 18 19 20 21 22 23 24 25 26 27 28 ) (543)

This is a chat thread for fastai v1 developers. Use it like a Slack or IRC channel. You can keep it open in a separate tab or window and see comments in real time, or check it from time to time to see what’s going on. If…

About the fastai dev category ( 2 3 ) (42)
How to use multiple gpus (18)
Multilingual ULMFiT ( 2 3 ) (45)
Mixed precision training ( 2 ) (23)
Multilabel classification with ULMFiT in Fastai v1 ( 2 ) (22)
Mixup data augmentation (20)
Beginning of NLP ( 2 3 4 5 ) (94)
PyTorch V1.0 Stable Release for Linux & Windows (7)
Making predictions in v1 ( 2 3 4 ) (62)
What is the pct_start mean? (7)
Anyone explored Rapids.ai yet? (13)
Experiments on using Redis as DataSet for fast.ai for huge datasets (6)
Fastai.structure generate a ModuleNootFound error in crestle.ai (2)
Is fastai_v1 broken for the latest release 1.0.21 (and latest pytorch) (8)
Mixup learner prediction throws reduction argument error (2)
Segmentation Dataset for run length encoding (20)
Adding SentencePieceTokenizer to fastai.text.data (8)
Tabular : Dimension out of range (expected to be in range of [-1, 0], but got 1) (8)
Using process_one instead of process in pre-processing (2)
Metric dependant gpu memory utilization (1)
CSV Logger Callback? ( 2 ) (21)
Creating an out of memory tabular dataset (9)
Cannot use SqueezeNet with create_cnn (18)
Does DataLoader have multithreading memory leak issues? (5)
Storing lists of Path objects creates Memory issues (?!) (1)
Add a use_partial_data to the data block api (2)
Text_classifier_learner give error Could not infer dtype of NoneType (6)
Bug TextClasDataBunch in v.1.0.28? (9)
Deploy fastai text model to golang (1)