judycpChen

cannot write mode F as PNG

3

  I ran into this problem when I was running main.py. How do I fix it

I have a problem when I perform "sh scripts/single_branch_pretraining_coco_pvt_v2_b2_li.sh" .  And I added "WEIGHT_DECAY_BIAS: 0.0001" in the config file single_branch_pretraining_coco_pvt_v2_b2_li.yaml,now it runs successfully. I was wondering if "WEIGHT_DECAY_BIAS" should...

I cannot find the dictory '../new_annotations/final_split_voc_1_shot_instances_train2014 .json'

1

I cannot find the dictory 'new_annotations/final_split_voc_1_shot_instances_train2014 .json'.How can I generate it?I don't find the script to generate it.

你好，我运行python setup.py build develop时报错：ImportError: cannot import name 'deform_conv_cuda' from partially initialize module ‘mmdet.ops.dcn'

Result question

1

Why my test result on visdrone2019 is different from paper? 

NotImplementError

6

I find a error: NotImplementedError: SPCONV_FILTER_HWIO is deprecated. use SPCONV_SAVED_WEIGHT_LAYOUT instead. How can I work it out?

I followed the steps of the detection direction configuration, why is the detection result poor after training?

I would like to know if the accuracy values output from each epoch during training are the results obtained from testing on the validation set

There is a lack of annotations in your test set, is it missing comments in the test set? How can I test it?