pytorch/examples

Low training accuracy using pre-trained model

Open

#889 建立於 2021年3月4日

在 GitHub 查看
 (2 留言) (0 反應) (0 負責人)Python (21,634 star) (9,429 fork)batch import
help wantedvision

描述

Hello, I am trying to evaluate a pre-trained mobilenetv2 model from torchvision on the ImageNet training dataset using this script. To do so, I modify lines 235-237 to perform validation on the train loader instead of the val loader:

    if args.evaluate:
        validate(train_loader, model, criterion, args)
        return

Everything else is left untouched. The command I use to run is: python imagenet_train_example.py -a mobilenet_v2 -j 16 -b 1024 -e --pretrained /data/ImageNet However, the results are lower than expected: Acc@1 2.926 Acc@5 15.079 Loss 11.795791

貢獻者指南

技術棧
python
領域
machine learning
議題類型
bug
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
3
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
under 1 hour
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
needs maintainer response
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
needs investigation
前置要求
PythonPyTorchImageNet dataset
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
30
研究方向
The issue is in imagenet train example.py, lines 235-237, where the user modified the script to evaluate on the training set instead of the validation set. The low accuracy suggests a mismatch between training preprocessing (including data augmentation) and the expected input for the pre trained model. Investigate the data transforms for the training loader (which typically include random crops and horizontal flips) versus the validation loader (center crop only). The fix likely involves using the validation loader for evaluation, or applying validation style transforms if evaluating on the training set. No linked PRs or comments provide further direction.