-
感谢您的杰出工作!
在configs/pretrain/yolo_world_v2_l_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py这个config文件下
我尝试通过断点了解您的模型,
但在训练过程中,模型并未调用ImagePoolingAttentionModule模块
即论文中提及的“Image-Pool…
-
yolo_world_l_dual_vlpan_2e-4_80e_8gpus_finetune_coco.py文件,我需要微调
_base_ = ( '../../third_party/mmyolo/configs/yolov8/yolov8_l_syncbn_fast_8xb16-500e_coco.py')
custom_imports = dict(
imports=['y…
-
Hi @wondervictor ,I changed the associated config, checkpoint, and img-size in export_onnx.py.
![image](https://github.com/AILab-CVC/YOLO-World/assets/59815166/a9320cc6-19dc-469b-9136-211031244de2)
…
-
Follow the steps in prompt_yolo_world.md to finetune yolo-world-s in coco dataset, the validation map can not improve during the training process. More specifically, the validation map in epoch 5 is …
-
I couldn't find where it imports the various modules of YOLOv8's backbone, nor could I find how the forward computation is specifically performed in the backbone section.
-
If I want to train my own dataset, the situation of the dataset is as follows:
| Dataset Name | Category | Category Name | BBOX | Captions |
|:-------------|:---------:|:-------------:|:-----:|-…
-
_base_ = ('../../third_party/mmyolo/configs/yolov8/'
'yolov8_l_syncbn_fast_8xb16-500e_coco.py')
custom_imports = dict(imports=['yolo_world'], allow_failed_imports=False)
# hyper-paramet…
-
For now I am doing inference on images following the code in the inference.ipynb file. However, I have realised that it uses image paths to be able to make the inference.
However, due to limitatio…
-
When i tried to implement this instruction:
./tools/dist_train.sh configs/pretrain/yolo_world_v2_x_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py 1 --amp
I got this error,
torch.di…
-
我尝试给yolo_world_v2_l_vlpan_bn_2e-4_80e_8gpus_mask-refine_finetune_coco.py中直接添加
mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
data_root='data/mixed_grounding/',
…