Download
FixRes is a lightweight yet powerful training methodology for convolutional neural networks (CNNs) that addresses the common train-test resolution discrepancy problem in image classification. Developed by Facebook Research, FixRes improves model generalization by adjusting training and evaluation procedures to better align input resolutions used during different phases. The approach is simple but highly effective, requiring no architectural modifications and working across diverse CNN backbones such as ResNet, ResNeXt, PNASNet, and EfficientNet. FixRes demonstrates that a mismatch between training and testing resolutions often leads to suboptimal accuracy, and fine-tuning the classifier and batch normalization layers at higher test resolutions significantly enhances performance. The repository includes pretrained models, feature embeddings, and evaluation scripts corresponding to the experiments reported in the NeurIPS 2019 paper “Fixing the train-test resolution discrepancy.”
Features
- Corrects resolution mismatch between training and testing phases for CNNs
- Compatible with multiple architectures including ResNet, ResNeXt, PNASNet, and EfficientNet
- Includes pretrained models achieving top ImageNet benchmarks
- Supports CutMix augmentation and improved fine-tuning strategies
- Provides feature extraction and softmax outputs for reproducibility
- Offers scripts for training, fine-tuning, and evaluation at custom resolutions
Project Samples
