Update CUSTOMIZED_PRETRAIN.md

BradyFU-patch-1
YifanXu 2023-10-20 22:54:10 +08:00 committed by GitHub
parent ecc2370593
commit 0df94e5b47
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions

View File

@ -14,7 +14,7 @@ Here we add a new dataset ``coco_grounding_train_for_obj365``.
**2. Acquire customized config files**
You can modified upon the [official pretraining config file](configs/pretrain/mq-glip-t.yaml) to get a customized config file. Here we provide an [example](configs/pretrain/mq-glip-t_coco.yaml). You customize your own needs following the "``NOTE``" in the file.
You can modified upon the [official pretraining config file](configs/pretrain/mq-glip-t.yaml) to get a customized config file. Here we provide an [example](configs/pretrain/mq-glip-t_coco.yaml). You can customize your own needs following the "``NOTE``" in the file.
Make sure to use correct ``DATASETS.TRAIN`` and ``VISION_QUERY.QUERY_BANK_PATH``.
@ -37,4 +37,4 @@ You can specify ``VISION_QUERY.MAX_QUERY_NUMBER`` (number of queries for each ca
**4. Conduct modulated pretraining**
```
python -m torch.distributed.launch --nproc_per_node=8 tools/train_net.py --config-file configs/pretrain/mq-glip-t_coco.yaml --use-tensorboard OUTPUT_DIR 'OUTPUT/MQ-GLIP-TINY-COCO/'
```
```