Mahi-Mai

Like Merveydn said, you'll want to load tensorflow-gpu instead of tensorflow. Additionally, to make a keras model train/use multiple GPU instances instead of the one, first import what you need......

Hello @GusRoth . Did you ever figure this out? If so, would you be willing to share your solutions/code?

@fadishaar84 Here! ``` predictions_smooth = predict_img_with_smooth_windowing( input_img, window_size=window_size, subdivisions=2, # Minimal amount of overlap for windowing. Must be an even number. nb_classes=nb_classes, pred_func=( lambda img_batch_subdiv: model.predict(image_to_neural_input(img_batch_subdiv)) ) ) ``` Try...

So to implement my solution, I used a function for listing files in a directory, and I wrote a small function for stripping the annotation filename: ``` def strip_annotation_filename(file): #...

I just came to the issues to see if there were any options for this! I'd appreciate it if we could format the naming scheme ourselves. All I really need...

Thank you, especially for the swift response! It's been so great to find such a comprehensive, module independent augmentation suite. I'll let you know if I find any solutions to...

I'll have to tweak this script like the other one, but it looks like the color_palette isn't used in this notebook, so I don't need to call it. I took...