dsuthar-nvidia

sparsity.prune_low_magnitude fails with mixed precision policy mixed_float16

6

**Describe the bug** When using `tf.keras.mixed_precision.experimental.Policy("mixed_float16", loss_scale="dynamic")` the `sparsity.prune_low_magnitude` fails in tensor type conversion with the error `Tensor conversion requested dtype float32 for Tensor with dtype float16: `. Things work...

tf.keras.metrics.MeanIoU API is practically unusable without a threshold

19

Please make sure that this is a bug. As per our [GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md), we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub. tag:bug_template **System information**...