AWS Trainium vs NVIDIA CUDA for Medical Image Classification: A Comprehensive Benchmark on ChestX-ray14
Fisher, G. R.
Show abstract
We present a rigorous benchmark comparing AWS Trainium (trn1 instances) and NVIDIA CUDA (g5 instances with A10G GPUs) for training convolutional neural networks on medical image classification. Using the NIH ChestX-ray14 dataset with 112,120 chest radiographs and 14 thoracic disease labels, we evaluate ResNet-50 and ConvNeXt architectures across both platforms. Our key findings are threefold: (1) Trainium achieves virtually identical accuracy to CUDA for compatible architectures (ConvNeXt-Pico: F1=0.8007 vs 0.8027, {Delta}=0.25%), (2) modern CNN architectures using depthwise convolutions and LayerNorm (ConvNeXt-Tiny and larger) fail to compile or load on Trainium due to hardware constraints, and (3) Trainium is 3-5 x more expensive than CUDA for CNN training even with correct instance sizing. We document the substantial porting effort required, including four critical XLA-specific code modifications, and provide guidance for practitioners considering Trainium for computer vision workloads.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A scalable implementation of the recursive least-squares algorithm for training spiking neural networks 94%
- Modernizing the NEURON Simulator for Sustainability, Portability, and Performance 93%
- THINGSvision: a Python toolbox for streamlining the extraction of activations from deep neural networks 93%
Similar papers in this journal
- Deep learning models for COVID-19 chest x-ray classification: Preventing shortcut learning using feature disentanglement 93%
- Compressive Big Data Analytics: An Ensemble Meta-Algorithm for High-dimensional Multisource Datasets 93%
- Small hand-designed convolutional neural networks outperform transfer learning in automated cell shape detection in confluent tissues 93%
Similar papers in this journal
- The Effect of Image Resolution on Automated Classification of Chest X-rays 95%
- Predicting Primary Site of Secondary Liver Cancer with a Neural Estimator of Metastatic Origin (NEMO) 92%
- A 3D CNN Classification Model for Accurate Diagnosis of Coronavirus Disease 2019 using Computed Tomography Images 90%
Similar papers in this journal
- Assisting Scalable Diagnosis Automatically via CT Images in the Combat against COVID-19 92%
- A novel interpretable deep transfer learning combining diverse learnable parameters for improved T2D prediction based on single-cell gene regulatory networks 92%
- WormSwin: Instance segmentation of C. elegans using vision transformer 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.