Interested in Machine Learning, Deep Learning and Data Science in general
-
NVIDIA
- San Jose, CA
- http://titu1994.github.io/
Highlights
- Pro
- 13 discussions answered
Block or Report
Block or report titu1994
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned Loading
-
Neural-Style-Transfer Public
Keras Implementation of Neural Style Transfer from the paper "A Neural Algorithm of Artistic Style" (http://arxiv.org/abs/1508.06576) in Keras 2.0+
-
-
Keras-Classification-Models Public
Collection of Keras models used for classification
-
neural-image-assessment Public
Implementation of NIMA: Neural Image Assessment in Keras
751 contributions in the last year
Less
More
Activity overview
Contributed to
NVIDIA/NeMo,
titu1994/lambda_networks_pt,
titu1994/Keras-ResNeXt
and 5 other
repositories
Loading
Contribution activity
December 2021
Created 4 commits in 1 repository
Created a pull request in NVIDIA/NeMo that received 3 comments
Fix for Stalled ASR training/eval on Pytorch 1.10+ (multigpu/multinode)
Bugfix Training / inference stalls on multi gpu / multi node on Pytorch 1.10+ This happens because the ASR models attempt to adaptively increase t…
+59
−23
•
3
comments
Opened 2 other pull requests in 1 repository
NVIDIA/NeMo
1
merged
1
open
Reviewed 11 pull requests in 1 repository
NVIDIA/NeMo
11 pull requests
- Asr fr
- fix bucketing list bug.
- Replacing outdated exports scripts
- Refactored prepare_for_export calls to ensure input size of example i…
- Fixing the bucketing_batch_size bug.
- Add aishell and fisher dataset processing scripts for ASR
- Initial refactor
- adding german conformer ctc and rnnt
- Fix megatron_gpt_ckpt_to_nemo.py with torch distributed
- Adding adaptive bucketing for tarred datasets.
- (1) O2-style mixed precision recipe, (2) Persistent layer-norm, (3) Grade scale hysteresis, (4) gradient_as_bucket_view