Update README.md
Browse files
README.md
CHANGED
@@ -83,7 +83,7 @@ This model was trained with one of (see table in intro):
|
|
83 |
|
84 |
All models were trained with a global batch size of 81920 for 64 checkpoint intervals of 203.7M samples for a total of ~13B samples seen over training.
|
85 |
|
86 |
-
For 256x256 models, a slurm script w/ srun below was used on 20 8-GPU nodes (Stability), switching to 40 4-GPU nodes for time on JUWELS.
|
87 |
|
88 |
```
|
89 |
/opt/slurm/sbin/srun --cpu_bind=v --accel-bind=gn python -m training.main \
|
@@ -129,6 +129,8 @@ The models achieve between 70.8 and 71.7 zero-shot top-1 accuracy on ImageNet-1k
|
|
129 |
|
130 |
An initial round of benchmarks have been performed on a wider range of datasets, to be viewable at https://github.com/LAION-AI/CLIP_benchmark/blob/main/benchmark/results.ipynb
|
131 |
|
|
|
|
|
132 |
# Acknowledgements
|
133 |
|
134 |
Acknowledging [stability.ai](https://stability.ai/) and the Gauss Centre for Supercomputing e.V. (http://gauss-centre.eu) for funding this part of work by providing computing time through the John von Neumann Institute for Computing (NIC) on the GCS Supercomputer JUWELS Booster at Jülich Supercomputing Centre (JSC).
|
@@ -137,8 +139,31 @@ Acknowledging [stability.ai](https://stability.ai/) and the Gauss Centre for Sup
|
|
137 |
|
138 |
**BibTeX:**
|
139 |
|
140 |
-
|
141 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
142 |
|
143 |
OpenCLIP software
|
144 |
```bibtex
|
|
|
83 |
|
84 |
All models were trained with a global batch size of 81920 for 64 checkpoint intervals of 203.7M samples for a total of ~13B samples seen over training.
|
85 |
|
86 |
+
For 256x256 models, a slurm script w/ srun below was used on 20 8-GPU (A100 40GB) nodes (Stability), switching to 40 4-GPU nodes for time on JUWELS.
|
87 |
|
88 |
```
|
89 |
/opt/slurm/sbin/srun --cpu_bind=v --accel-bind=gn python -m training.main \
|
|
|
129 |
|
130 |
An initial round of benchmarks have been performed on a wider range of datasets, to be viewable at https://github.com/LAION-AI/CLIP_benchmark/blob/main/benchmark/results.ipynb
|
131 |
|
132 |
+
As part of exploring increased augmentation + regularization, early evalations suggest that `augreg` trained models evaluate well over a wider range of resolutions. This is especially true for the 320x320 LAION-A model, where the augreg run was lower than the non-augreg when evaluated at the train resolution of 320x320 (71.3 vs 71.7), but improves to 72.2 when evaluated at 384x384 (the non-augreg drops to 71.0 at 384x384).
|
133 |
+
|
134 |
# Acknowledgements
|
135 |
|
136 |
Acknowledging [stability.ai](https://stability.ai/) and the Gauss Centre for Supercomputing e.V. (http://gauss-centre.eu) for funding this part of work by providing computing time through the John von Neumann Institute for Computing (NIC) on the GCS Supercomputer JUWELS Booster at Jülich Supercomputing Centre (JSC).
|
|
|
139 |
|
140 |
**BibTeX:**
|
141 |
|
142 |
+
LAION-5B
|
143 |
+
```bibtex
|
144 |
+
@inproceedings{schuhmann2022laionb,
|
145 |
+
title={{LAION}-5B: An open large-scale dataset for training next generation image-text models},
|
146 |
+
author={Christoph Schuhmann and
|
147 |
+
Romain Beaumont and
|
148 |
+
Richard Vencu and
|
149 |
+
Cade W Gordon and
|
150 |
+
Ross Wightman and
|
151 |
+
Mehdi Cherti and
|
152 |
+
Theo Coombes and
|
153 |
+
Aarush Katta and
|
154 |
+
Clayton Mullis and
|
155 |
+
Mitchell Wortsman and
|
156 |
+
Patrick Schramowski and
|
157 |
+
Srivatsa R Kundurthy and
|
158 |
+
Katherine Crowson and
|
159 |
+
Ludwig Schmidt and
|
160 |
+
Robert Kaczmarczyk and
|
161 |
+
Jenia Jitsev},
|
162 |
+
booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
|
163 |
+
year={2022},
|
164 |
+
url={https://openreview.net/forum?id=M3Y74vmsMcY}
|
165 |
+
}
|
166 |
+
```
|
167 |
|
168 |
OpenCLIP software
|
169 |
```bibtex
|