coco issues

Results 8 issues of


                                            coco

about the FPS

When I test images using SOLOv2_Light_448_R18_3x model，the cost time is 40ms

can you share the ‘’../Data/falldata/Home/Annotation_files‘’

when generate the training data of the TSTGG，there is no the related ‘’../Data/falldata/Home/Annotation_files”， can you share that？thanks

RuntimeError: Error(s) in loading state_dict for Darknet: Unexpected key(s) in state_dict: "module_list.0.batch_norm_0.num_batches_tracked", "module_list.2.batch_norm_2.num_batches_tracked", "module_list.4.batch_norm_4.num_batches_tracked", "module_list.6.batch_norm_6.num_batches_tracked", "module_list.8.batch_norm_8.num_batches_tracked", "module_list.10.batch_norm_10.num_batches_tracked", "module_list.12.batch_norm_12.num_batches_tracked", "module_list.13.batch_norm_13.num_batches_tracked", "module_list.14.batch_norm_14.num_batches_tracked", "module_list.18.batch_norm_18.num_batches_tracked", "module_list.21.batch_norm_21.num_batches_tracked".

what’s the swap id of the face？

libtorch_cpu.so: cannot open shared object file: No such file or directory

File "./demo/D2Det_demo.py", line 5, in from mmdet.apis import init_detector, inference_detector, show_result_pyplot File "/opt/coco/project/D2Det/demo/../mmdet/apis/__init__.py", line 1, in from .inference import (async_inference_detector, inference_detector, File "/opt/coco/project/D2Det/demo/../mmdet/apis/inference.py", line 11, in from mmdet.core import get_classes...

Yeah, I know,but when I upload the folder, it goes wrong ，The foler format is "\results\VOC2012\Segmentation\comp6_test_cls" . Evaluation errors：Error while evaluating challenge 6. Results were not generated properly.

Yeah, I know,but when I upload the folder, it goes wrong ，The foler format is "\results\VOC2012\Segmentation\comp6_test_cls" . Evaluation errors：Error while evaluating challenge 6. Results were not generated properly. Have your...

train my own datasets

when I train my own dataset, the results is bad，Can you give me some suggestions?

uisng the 1*1 conv instead of the linear of the orginial code, but the result is not good like the paper

expecially, the small objects is very bad, can you give me same advices, thanks!!!!