Sey Eeet

Here is a simple steps to get tensorflow (keras) model from onnx and it throws this error: `ValueError: Input 0 is incompatible with layer model: expected shape=(None, 3, 60, 60),...

can I use it for video?

3

Im following the example [here](https://github.com/albumentations-team/albumentations_examples/blob/master/notebooks/example.ipynb) regarding how to apply it on images. Can I use it on video data? or I have to apply it frame by frame? for example...

Can you please let me know how can I visualize the results as you display in the project page. I mean the code that is used for rendering out the...

any plan to support video augmentation?

just a suggestion

4

Hi I like to start with thanking you for such a great work with a lot of great implementations. I have a small suggestion. I suggest for all your codes/modules...

when you said `You can then set a fixed unary potential in the following way`, what does unary means exactly?

I notice that the results for miou does not match with miou that I manually compute. here is an example, lets say pres and labels are two lists including the...

it would be nice if we can add an option to `eval_semantic_segmentation` and `calc_semantic_segmentation_confusion` for the cases that we have ignore labels. for example in voc pascal segmentation, we have...

what image size has been used for the final segmentation training when we want to training the model on all the acquired labels? Also, can you please clarify if we...