Official PyTorch Implementation

Tal Ridnik, Hussam Lawen, Asaf Noy, Itamar Friedman

DAMO Academy, Alibaba Group


Many deep learning models, developed in recent years, reach higher
ImageNet accuracy than ResNet50, with fewer or comparable FLOPS count.
While FLOPs are often seen as a proxy for network efficiency, when
measuring actual GPU training and inference throughput, vanilla
ResNet50 is usually significantly faster than its recent competitors,
offering better throughput-accuracy trade-off. In this work, we
introduce a series of architecture modifications that aim to boost
neural networks' accuracy, while retaining their GPU training and
inference efficiency. We first demonstrate and discuss the bottlenecks
induced by FLOPs-optimizations. We then suggest alternative designs
that better utilize GPU structure and assets. Finally, we introduce a
new family of GPU-dedicated models, called TResNet, which achieve
better accuracy and efficiency than previous ConvNets. Using a TResNet
model, with similar GPU throughput to ResNet50, we reach 80.7%
top-1 accuracy on ImageNet. Our TResNet models also transfer well and
achieve state-of-the-art accuracy on competitive datasets such as
Stanford cars (96.0%), CIFAR-10 (99.0%), CIFAR-100 (91.5%) and
Oxford-Flowers (99.1%)

Main Results

TResNet Models

TResNet models accuracy and GPU throughput on ImageNet, compared to ResNet50. All measurements were done on Nvidia V100 GPU, with mixed precision. All models are trained on input resolution of 224.

Models Top Training Speed
Top Inference Speed
Max Train Batch Size Top-1 Acc.
ResNet50 805 2830 288 79.0
EfficientNetB1 440 2740 196 79.2
TResNet-M 730 2930 512 80.7
TResNet-L 345 1390 316 81.4
TResNet-XL 250 1060 240 82.0

Comparison To Other Networks

Comparison of ResNet50 to top modern networks, with similar top-1 ImageNet accuracy.
All measurements were done on Nvidia V100 GPU with mixed precision. For gaining optimal speeds, training and inference were measured on 90% of maximal possible batch size.
Except TResNet-M, all the models' ImageNet scores were taken from the public repository, which specialized in providing top implementations for modern networks. Except EfficientNet-B1, which has input resolution of 240, all other models have input resolution of 224.

Model Top Training Speed
Top Inference Speed
Top-1 Acc. Flops[G]
ResNet50 805 2830 79.0 4.1
ResNet50-D 600 2670 79.3 4.4
ResNeXt50 490 1940 78.5 4.3
EfficientNetB1 440 2740 79.2 0.6
SEResNeXt50 400 1770 79.0 4.3
MixNet-L 400 1400 79.0 0.5
TResNet-M 730 2930 80.7 5.5

Transfer Learning SotA Results

Comparison of TResNet to state-of-the-art models on transfer learning datasets (only ImageNet-based transfer learning results). Models inference speed is measured on a mixed precision V100 GPU. Since no official implementation of Gpipe was provided, its inference speed is unknown

Dataset Model Top-1
CIFAR-10 Gpipe 99.0 - 480
TResNet-XL 99.0 1060 224
CIFAR-100 EfficientNet-B7 91.7 70 600
TResNet-XL 91.5 1060 224
Stanford Cars EfficientNet-B7 94.7 70 600
TResNet-L 96.0 500 368
Oxford-Flowers EfficientNet-B7 98.8 70 600
TResNet-L 99.1 500 368

Reproduce Results

We provide code for reproducing the validation top-1 score of TResNet
models on ImageNet (input resolution 224). First, download pretrained
models from

Then, run the script. For example, for tresnet_m run:

python -m \
--val_dir=/path/to/imagenet_val_folder \
--model_path=/model/path/to/tresnet_m.pth \


    title={TResNet: High Performance GPU-Dedicated Architecture},
    author={Tal Ridnik and Hussam Lawen and Asaf Noy and Itamar Friedman},


Feel free to contact me if there are any questions or issues (Tal
Ridnik, [email protected]).