Malik Hashmat comments

Results 19 comments of


                                            Malik Hashmat

Video dataset support

Hi, Is there any update regarding this?

Inquiry Regarding Model Open Sourcing

Will the weights of Vim-S also be released?

Finetuning on specific datasets

Thank you for explaining. I was specifically talking about using specific datasets for finetuning that are mentioned in the readme. So for that i can just update the json file

Semantic Segmentation Code.

Hi. Thanks for sharing your work, Is there any timeline oof when the segmentation/detection code & pretrained weights will be available?

How to train the model with my own data.

Is the model file in the nets folder complete?

How to train the model with my own data.

So all the proposed design changes in the proposed model are not currently reflected in the model file?

Where is DWConv used in the LightM-UNet model?

Running the model with `model = LightMUNet( spatial_dims=3, init_filters=32, in_channels=1, out_channels=14, blocks_down=[1, 2, 2, 2], blocks_up=[1, 1, 1], )` gives around 6 million parameters

Where is DWConv used in the LightM-UNet model?

So the current model does not reflect the one mentioned in the paper? Even the initial and final layers don't have DWConv. Even with these changes, the model size is...

Where is DWConv used in the LightM-UNet model?

Response from the author regarding this issue will be appreciated.

Where is DWConv used in the LightM-UNet model?

So when will the correct code be uploaded?