joeyslv

is dataset have transform_matrix？unsup_loss_bbox: 0.0000 when i try to train, I wanted to know if it was because of the data set, but my data set was fully trained and calculated on the supervised model？

7

Can you tell me what that transform_matrix means ？Does this label have to be in the dataset？ Because I'm using `browse_dataset.p`yand I can't get my data set through. ``` (arknights)...

I would like to ask the final test with test.py precision, the output of only one precision, this precision is the weight of the teacher model or the weight of...

i modify the `ratios=[1]` to `ratios=[2.444, 3.182, 1.574, 1.721, 0.994, 1.163, 0.751, 0.534]` then have a error like this： ``` 2022-03-29 15:12:23,844 - mmdet - INFO - workflow: [('train', 1)],...

error: legacy-install-failure

4

(swin-t) C:\Users\joeyslv\apex>pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" . WARNING: Disabling all use of wheels due to the use of --build-option / --global-option / --install-option. Using pip 22.0.4 from D:\App\anaconda\envs\swin-t\lib\site-packages\pip (python...

请问一下Dense teacher提出的DPL是否其实只是针对预测的类别分支？

2

在图1中，有Dense Pseudo-label 和 Pseudo-box Label两个分支，分别计算了Ldpl损失和Lbox损失，所以Ldpl其实就是对应教师模型输出分类分支后的sigmoid所做的吗？整个模型还是用了NMS来生成伪框监督回归分支的损失计算？ 3.3 Dense Pseudo-Label Since the learning region is selected, unsupervised learning for regression branch can be easily achieved. 3.3中关于回归的分支的叙述较少，上面说由于选择了学习区域，因此回归分支的学习更容易实现，这个更容易实现指的是什么呢？ 希望作者能够解答一下 感谢

The Threshold Problem of GMM

2

After carefully reading the article 3.4 Temporary consistency using Gaussian Mixture Model (GMM) You use a Gaussian mixture distribution for each category. Each mixture distribution contains a positive and negative...

What is the relationship between samples_per_gpu and workers_per_gpu and sample_ratio？

5

I can only use the default ``` sample_ ratio=[1, 4] samples_ per_ gpu=4 workers_ per_ gpu=4 ``` But to increase the batchsize a bit, `samples_ per_ gpu=8,` when the program...