LAMP: Large Deep Nets with Automated Model Parallelism for Image Segmentation. (arXiv:2006.12575v1 [cs.CV])

Deep Learning (DL) models are becoming larger, because the increase in model
size might offer significant accuracy gain. To enable the training of large
deep networks, data parallelism and model parallelism are two well-known
approaches for parallel training. However, data parallelism does not help
reduce memory footprint per device. In this work, we introduce Large deep 3D
ConvNets with Automated Model Parallelism (LAMP) and investigate the impact of
both input’s and deep 3D ConvNets’ size on segmentation accuracy. Through
automated model parallelism, it is feasible to train large deep 3D ConvNets
with a large input patch, even the whole image. Extensive experiments
demonstrate that, facilitated by the automated model parallelism, the
segmentation accuracy can be improved through increasing model size and input
context size, and large input yields significant inference speedup compared
with sliding window of small patches in the inference. Code is

Source link

Related posts

Grab lands $50M from Thailand’s Kasikorn Bank to further its fintech push


Executives say workers in India not ready for AI: Accenture's Paul Daugherty


Preoperative and postoperative prediction of long-term meningioma outcomes.


This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More

Privacy & Cookies Policy


COVID-19 (Coronavirus) is a new illness that is having a major effect on all businesses globally LIVE COVID-19 STATISTICS FOR World