update links
Browse files
app.py
CHANGED
|
@@ -16,8 +16,8 @@ Check out the original, longstanding issue [here](https://github.com/huggingface
|
|
| 16 |
evaluation. I encountered this issue specifically while training [RoBERTa-base-DReiFT](https://huggingface.co/MarioBarbeque/RoBERTa-base-DReiFT) for multilabel \
|
| 17 |
text classification of 805 labeled medical conditions based on drug reviews. The [following workaround](https://github.com/johngrahamreynolds/FixedMetricsForHF) was
|
| 18 |
created to address this - follow the link to view the source! To see each of these abstracted classes at work independently, view the 🤗 Space I've constructed for each:
|
| 19 |
-
[
|
| 20 |
-
[`FixedRecall
|
| 21 |
|
| 22 |
This Space shows how one can instantiate these custom `evaluate.Metric`s, each with their own unique methodology for averaging across labels, before `combine`-ing them into a
|
| 23 |
HF `evaluate.CombinedEvaluations` object. From here, we can easily compute each of the metrics simultaneously using `compute`. \n
|
|
|
|
| 16 |
evaluation. I encountered this issue specifically while training [RoBERTa-base-DReiFT](https://huggingface.co/MarioBarbeque/RoBERTa-base-DReiFT) for multilabel \
|
| 17 |
text classification of 805 labeled medical conditions based on drug reviews. The [following workaround](https://github.com/johngrahamreynolds/FixedMetricsForHF) was
|
| 18 |
created to address this - follow the link to view the source! To see each of these abstracted classes at work independently, view the 🤗 Space I've constructed for each:
|
| 19 |
+
[FixedF1📈](https://huggingface.co/spaces/MarioBarbeque/FixedF1), [FixedPrecision🎯](https://huggingface.co/spaces/MarioBarbeque/FixedPrecision),
|
| 20 |
+
[`FixedRecall`📉](https://huggingface.co/spaces/MarioBarbeque/FixedRecall).\n
|
| 21 |
|
| 22 |
This Space shows how one can instantiate these custom `evaluate.Metric`s, each with their own unique methodology for averaging across labels, before `combine`-ing them into a
|
| 23 |
HF `evaluate.CombinedEvaluations` object. From here, we can easily compute each of the metrics simultaneously using `compute`. \n
|