Downloads · 30 days
0
GAN-Diffusion
f1avj0/GAN-Diffusion
GAN-Diffusion is a machine learning model from f1avj0. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as afl-3.0.
Final project for HPML Spring 23 at NYU The project we decided to work with is about the optimization of diffusion networks. As we will see in the latter sections of the report, the main idea of the project revolves a…
Access
Public
Updated Dec 8, 2023
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pdf171 KB · 55%
At a glance
- License
- afl-3.0
- Access
- Public
- Created
- Dec 8, 2023
- Updated
- Dec 8, 2023
- SHA
- 80e3438d
Model card
From the Hugging Face model README
Final project for HPML Spring 23 at NYU The project we decided to work with is about the optimization of diffusion networks. As we will see in the latter sections of the report, the main idea of the project revolves around the possible ways to optimize the training of diffusion networks, by making use of PyTorch Profiling.
RESULTS:
The convolutional backpropagation is the main bottleneck.
Having AMP vs no AMP sped up the CPU runtime for 1 GPU, it also slightly improved losses.
2 GPUs gave a slight speedup compared to 1 GPU
On 2 GPUs, AMP didn’t improve runtimes
The convolutional backpropagation is the main bottleneck.
In two GPUs, data is parallelized, so the model spends less time on backprop.
Stats: 1-1 GPU with AMP : CPU 28.3 CUDA 25.5 Total runtime - 502 2-1 GPU w/out AMP : CPU 42.4 CUDA 41.09 Total runtime - 428 3-2 GPUs with AMP : CPU 39.7 CUDA 25.4 Total runtime - 572 3-2 GPUs w/out AMP : CPU 38.2 CUDA 25.3 Total runtime - 559
- License
- afl-3.0
- Created
- Dec 8, 2023
- Updated
- Dec 8, 2023