Download Latest Version
PyText v0.3.3.zip (2.0 MB)
Get an email when there's a new version of PyText
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| pytext_nlp-0.3.3-py3-none-any.whl | 2020-06-08 | 503.4 kB | |
| pytext-nlp-0.3.3.tar.gz | 2020-06-08 | 353.2 kB | |
| PyText v0.3.3.tar.gz | 2020-06-08 | 1.8 MB | |
| PyText v0.3.3.zip | 2020-06-08 | 2.0 MB | |
| README.md | 2020-06-08 | 1.6 kB | |
| Totals: 5 Items | 4.7 MB | 0 | |
New features
- Add XLM-R document classification server + console (#1358)
- MLP layer embed for float tensors and
FloatListSeqTensorizerforList[List[[float]]features. (#1374) - Add
class_accuracyinMultiLabelSoftClassificationMetrics(#1371) - Add an option to skip test run after models have been trained (#1372)
- Support DP in PyText (#1366)
- Support torchscriptify in multi_label_classification_layer (#1350)
- Add custom metric class for reporting Joint model metrics (#1339)
- MultiLabel-MultiClass Model for Joint Sequence Tagging (#1335)
- Scripted tokenizer support for DocModel (#1314)
Bugfixes
- Fixed metric reporter aggregation and output layer for the multi-label classification
- Remove
move_state_dict_to_gpu, which is causing CUDA OOM (#1367) - Fix Flow's default conversion of dict to AttrDict
- Fix bug in
ClassificationOutputLayerthatpad_idxis never respected (#1347) - Serializing/Deserializing type Any: bugfix and simplification (#1344)
- Fix RoBERTa Q&A Training Bug with multiple BoS tokens. (#1343)
Other
- Better error message for misconfigured data fields
- Replace deprecated integer division with floor division operator
- Add informative prints to assert statements (#1360)
- TorchScript: Put dense tensor on the same device with other input tensors (#1361)
- Update PyTorch + ONNX (#1340)
- Update PyTorch + ONNX (#1340)- binary ONNX
- Update PR Template (#1349)
- Reduce memory request for pytext train operator
- Add 'contrib' directory for experimental code (#1333)
