Gasp34

Layer weight shape don't match

2

**Describe the bug** A get the error : Layer weight shape (4, 19, 4, 300) not compatible with provided weight shape (4, 19, 1, 300) **To Reproduce** ``` class ConvNet(nn.Module):...

Masked Auto Encoder, class token and linear probing

1

Hello, If I understand correctly, when doing linear probing, you only train the last FC layer. But in the classification head of the ViT, the last FC layer uses the...

KeyError: 'batchnormalizationv1'

3

Hey :) I'm trying to use kc.convert_model_from_saved_files but I have this keyerror : ``` File "C:\Users\XXXXXXX\Anaconda3\lib\site-packages\deeplift\conversion\kerasapi_conversion.py", line 349, in layer_name_to_conversion_function return name_dict[layer_name.lower()] KeyError: 'batchnormalizationv1' ``` The model is not complicated...

fix propagation and speed up using numba

4

Hey, I think the implementation of the propagation is wrong. I fixed it and I used numba to speed up the script. It works better and it is much faster...

I may be wrong but I think the implementation of the propagation is not as in the paper. I did a pull request here : https://github.com/MingtaoGuo/PatchMatch/pull/3

Inference part

2

Hi, Can you explain how you can get the top-k results as on Figure 4 during the inference part ? Do you compute a distance between the _Dfull_ of all...

MegaDetectorV6 release

6

### Search before asking - [X] I have searched the Pytorch-Wildlife [issues](https://github.com/microsoft/CameraTraps/issues) and found no similar bug report. ### Question Hello, do you have an approximate release date for MegaDetectorV6?...

Change width/weight of an edge

2

Hi, Thanks for the repo ! Can you add the following feature ? I would like to change the width of the edges according to a weight parameter For example...