mirrors
/
mmselfsup
mirror of https://github.com/open-mmlab/mmselfsup.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update GETTING_STARTED.md

pull/23/head^2
Xiaohang Zhan 2020-08-08 22:51:29 +08:00 committed by GitHub
parent 7848dac131
commit 5819713971
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
docs/GETTING_STARTED.md
View File

@ -70,12 +70,10 @@ We provide several standard benchmarks to evaluate representation learning. The
### VOC07 Linear SVM & Low-shot Linear SVM ### VOC07 Linear SVM & Low-shot Linear SVM
```shell ```shell
# test by epoch # test by epoch (only applicable to experiments trained with OpenSelfSup)
bash benchmarks/dist_test_svm_epoch.sh ${CONFIG_FILE} ${EPOCH} ${FEAT_LIST} ${GPUS} bash benchmarks/dist_test_svm_epoch.sh ${CONFIG_FILE} ${EPOCH} ${FEAT_LIST} ${GPUS}
# test pretrained model # test a pretrained model (applicable to any pre-trained models)
bash benchmarks/dist_test_svm_pretrain.sh ${CONFIG_FILE} ${PRETRAIN} ${FEAT_LIST} ${GPUS} bash benchmarks/dist_test_svm_pretrain.sh ${CONFIG_FILE} ${PRETRAIN} ${FEAT_LIST} ${GPUS}
# test random init
bash benchmarks/dist_test_svm_pretrain.sh ${CONFIG_FILE} "random" ${FEAT_LIST} ${GPUS}
``` ```
Augments: Augments:
- `${CONFIG_FILE}` the config file of the self-supervised experiment. - `${CONFIG_FILE}` the config file of the self-supervised experiment.
@ -88,7 +86,8 @@ The features, logs and intermediate files generated are saved in `$SVM_WORK_DIR/
- `dist_test_svm_pretrain.sh`: `SVM_WORK_DIR=$WORK_DIR/$PRETRAIN_NAME/`, e.g., if `PRETRAIN=pretrains/odc_r50_v1-5af5dd0c.pth`, then `PRETRAIN_NAME=odc_r50_v1-5af5dd0c.pth`; if `PRETRAIN=random`, then `PRETRAIN_NAME=random`. - `dist_test_svm_pretrain.sh`: `SVM_WORK_DIR=$WORK_DIR/$PRETRAIN_NAME/`, e.g., if `PRETRAIN=pretrains/odc_r50_v1-5af5dd0c.pth`, then `PRETRAIN_NAME=odc_r50_v1-5af5dd0c.pth`; if `PRETRAIN=random`, then `PRETRAIN_NAME=random`.
Notes: Notes:
- The evaluation records are saved in `$SVM_WORK_DIR/logs/eval_svm.log` - The evaluation records are saved in `$SVM_WORK_DIR/logs/eval_svm.log`.
- When using `benchmarks/dist_test_svm_epoch.sh`, DO NOT launch multiple tests of the same experiment with different epochs, since they share the same working directory.
- Linear SVM takes 5 min, low-shot linear SVM takes about 1 hour with 32 CPU cores. If you want to save time, you may delete or comment the low-shot SVM testing command (the last line in the scripts). - Linear SVM takes 5 min, low-shot linear SVM takes about 1 hour with 32 CPU cores. If you want to save time, you may delete or comment the low-shot SVM testing command (the last line in the scripts).
### ImageNet / Places205 Linear Classification ### ImageNet / Places205 Linear Classification