image-segmentation-keras

image-segmentation-keras copied to clipboard

Hello there, I think I have spotted a small mistake in the code. ### TL;DR: `n_classes` should be `np.max(seg_arr) + 1` and not `np.max(seg_arr)` ### How to see the bug:...

gaetanmuck

Hi there. I am at the newest version and using GPU training , libraries are installed as recommended. Yet the libarary is still only using one of my 2 GPUs....

GGDRriedel

* Under TF 2, the output for the first checkpoint is `.00001.index` and `.00001.data-00000-of-00001` rather than `.0`. `get_epoch_number_from_path` now strips path using `os.path.basename` and the `.index` suffix to properly return...

fracpete

If you go ahead and install the package `pip install keras-segmentation`, it installs the package regardless, like I have `h5py-3.7.0` and `keras-segmentation `is installed. However, to get the latest updates...

eyildiz-ugoe

Hi, I need to Deeploy the model(s) to ONNX, is there any way ?

abolfazltorbat

I used to use this repo using callbacks, so I could terminate the training with early stopping. I recently discovered that this is not an option anymore, and the parameter...

fferlito

It seems that the block 5 layer of the "get_vgg_encoder" function in vgg16.py is not being used. Where is this being used?

wangjinhoon

Hello, Please, add my project in the projects list :) https://github.com/rodrigobaguiar/SemanticSegforUSVs/

rodrigobaguiar

is there a way to turn off the print statements by any chance? what I mean by print statements are those: ==================] - 0s 53ms/step | 27/120 [00:02

eyildiz-ugoe

Can I run predictions on command line? So basically, what should I enter as checkpoint? ``` python -m keras_segmentation predict \ --checkpoints_path="path_to_checkpoints" \ --input_path="dataset1/images_prepped_test/" \ --output_path="path_to_predictions" ```

arianaa30