-
请问一下，在训练完之后，得到了bert分类模型，类别数是self.num_labels。
在测试时，我看代码中是这样处理：先用bert提取测试集的embedding，然后用kmeans聚类，类数是self.num_labels，得到聚类结果以后去和真实标签计算最优匹配。
那么请问测试时为什么不直接对测试集分类呢？直接分类应该也可以得到对应的label
-
Hi,
Thanks for sharing the code!
I'm trying to use the code (encode the shape and pose, then decode) on the FAUST dataset. The meshes doesn't come from a SMPL model (in fact they trained the model…
-
Hi,
I have to admit that your code inspires me a lot and I have definitely stared it.
However, could you explain about this piece of code below in main_road_traffic.py about zscore?
I knew that th…
-
**Hi everybody,
I have included in a Keras model a scattering layer using the following syntax:**
```
import kymatio
from kymatio.keras import Scattering2D
# Model architecture
def Dual…
-
Hi,
I use the following command to train shapenet multiview data (the single-view training works fine)
`python3 train.py --model=sdf_srn --yaml=options/shapenet/sdf_srn.yaml --name=chair --data.shap…
-
Hi! a quick update on the emcee convergence issue. I have the following situation:
1) I am working with flux-calibrated data
2) I have a stellar model with flux computed at the surface of the star
…
-
Hi Colour Team,
I compare Display P3 color profile in my macbook and your models of Display P3, and found that, the Green primary is quite different:
![image](https://user-images.githubusercontent…
-
**Description**
Both #4054 and #4058 show a community desire to be able to use ISIS to work with ORex data. Currently, these kernels are not available within the ISIS ecosystem. This enhancement re…
-
Hi,
I have a question, out of a somehow typical situation:
Right now I am waiting for a whole week already, to see the Structure-from-motion-step completing. - But I still see a match for less than …
esrat updated
3 years ago
-
Good evening Mr Pascariu. My name is Kenzi Lamberto from Indonesia.
I am trying to analyze Japanese and Taiwan mortality using this package for my undergraduate thesis. I found some problem while u…