-
when I load weights coco_lvis_h18_baseline.pth,
the error is ` size mismatch for maps_transform.0.weight: copying a param with shape torch.Size([16, 2, 1, 1]) from checkpoint, the shape in current mo…
-
Hello, the paper mentions several models, one trained on COCO, another on LVIS, a third on GoldG, O365, SBU and CC3M. As far as I understand, without retraining the model, you can download one of the …
-
what is the purpose of CENTERNET.IGNORE_HIGH_FP ?
In the heatmap_focal_loss code, it seems to ignore the loss of high FP ? Isn't the loss of high FP more important?
` if ignore_high_fp > 0:
…
-
class EnvironmentSettings:
def __init__(self):
self.workspace_dir = '' # Base directory for saving network checkpoints.
self.tensorboard_dir = self.workspace_dir + '/tensorbo…
FMZCY updated
2 years ago
-
* decaf2many version: master
* Python version: python3.10
* Operating System: Apple M2
### Description
translate a very large java file
### ERROR
```
return tree.accept(self)
Fil…
-
Would you please explain how instances_train2017_seen_2_oriorder_cat_info.json was generated or provide a link for it?
-
各位大大，
我运行./tools/dist_train.sh configs/pretrain/yolo_world_v2_x_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py 1 --amp这段想进行训练， 结果出现这个报错，是跟我在windows下训练有关系吗。
[W socket.cpp:697] [c10d]…
-
Thank for your excellent work!
I just exported the pytorch model to onnx model without nms, and used deploy/onnx_demo.py for detecting facial features in images. However I found that the results o…
-
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…
-
/!\ PLEASE INCLUDE THE FULL STACKTRACE AND CODE SNIPPET
**Short description**
Hello,
I hope you're doing great.
I am using TFDS on a M1 MAC and try to load LVIS.
**Environment information**
…