Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
|
|
4 years ago | |
|---|---|---|
| .. | ||
| src | 4 years ago | |
| Readme.md | 4 years ago | |
| eval.py | 4 years ago | |
| mindpsore_hub_conf.py | 4 years ago | |
An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS). To save computational cost, most of existing NAS algorithms often train and evaluate intermediate neural architectures on a small proxy dataset with limited training epochs. But it is difficult to expect an accurate performance estimation of an architecture in such a coarse evaluation way. This paper advocates a new neural architecture evaluation scheme, which aims to determine which architecture would perform better instead of accurately predict the absolute architecture performance. Therefore, we propose a \textbf{relativistic} architecture performance predictor in NAS (ReNAS). We encode neural architectures into feature tensors, and further refining the representations with the predictor. The proposed relativistic performance predictor can be deployed in discrete searching methods to search for the desired architectures without additional evaluation. Experimental results on NAS-Bench-101 dataset suggests that, sampling 424 ($0.1%$ of the entire search space) neural architectures and their corresponding validation performance is already enough for learning an accurate architecture performance predictor. The accuracies of our searched neural architectures on NAS-Bench-101 and NAS-Bench-201 datasets are higher than that of the state-of-the-art methods and show the priority of the proposed method.
Paper: Yixing Xu, Yunhe Wang, Kai Han, Yehui Tang, Shangling Jui, Chunjing Xu, Chang Xu. ReNAS: Relativistic Evaluation of Neural Architecture Search. Submitted to CVPR 2021.
The mixed precision training method accelerates the deep learning neural network training process by using both the single-precision and half-precision data formats, and maintains the network precision achieved by the single-precision training at the same time. Mixed precision training can accelerate the computation process, reduce memory usage, and enable a larger model or batch size to be trained on specific hardware.
For FP16 operators, if the input data type is FP32, the backend of MindSpore will automatically handle it with reduced precision. Users could check the reduced-precision operators by enabling INFO log and then searching ‘reduce precision’.
├── ReNAS
├── Readme.md # descriptions about adversarial-pruning # shell script for evaluation with CPU, GPU or Ascend
├── src
│ ├──loss.py # parameter configuration
│ ├──dataset.py # creating dataset
│ ├──nasnet.py # Pruned ResNet architecture
├── eval.py # evaluation script
To Be Done
After installing MindSpore via the official website, you can start evaluation as follows:
# infer example
Ascend: python eval.py --dataset_path path/to/cifar10 --platform Ascend --checkpoint_path [CHECKPOINT_PATH]
GPU: python eval.py --dataset_path path/to/cifar10 --platform GPU --checkpoint_path [CHECKPOINT_PATH]
CPU: python eval.py --dataset_path path/to/cifar10 --platform CPU --checkpoint_path [CHECKPOINT_PATH]
checkpoint can be produced in training process.
result: {'acc': 0.9411057692307693} ckpt= ./resnet50-imgnet-0.65x-80.24.ckpt
| Parameters | |
|---|---|
| Model Version | NASBench101-Net |
| uploaded Date | 03/27/2021 (month/day/year) ; |
| MindSpore Version | 0.6.0-alpha |
| Dataset | CIFAR-10 |
| Parameters (M) | 4.44 |
| FLOPs (G) | 1.9 |
| Accuracy (Top1) | 94.11 |
In dataset.py, we set the seed inside “create_dataset" function. We also use random seed in train.py.
Please check the official homepage.
MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
C++ Python Text Unity3D Asset C other