segmentation_models
segmentation_models copied to clipboard
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
I tried to replicate the example given in a Google Colab Environment. Here is the installation of I followed: ```python !pip install -U albumentations>=0.3.0 --user !pip install -U --pre segmentation-models...
Hi, first of all I would like to thank you for your work @qubvel , the package is awesome and very easy to use. I was trying to use tensorflow...
Added hardcoding of `float32` for the activation layer. This will prevent overriding from the following call: ``` from tensorflow.keras import mixed_precision mixed_precision.set_global_policy('mixed_float16') ``` This can help enable mixed precision training...
Wonderful repository! Thanks! Using -> TF 1.15 I wanted to optimize this repository using the tensorflow model optimization [techniques](https://www.tensorflow.org/model_optimization) but I am having a challenge. After creating the model as...
Please, add support for backbone "Xception v1" for U-Net and Linknet. I need it...
In binary segmentation (camvid).ipynb Example. Link: https://github.com/qubvel/segmentation_models/blob/master/examples/binary%20segmentation%20(camvid).ipynb I'm try to use my custom dataset to find patches. But I didn't getting my masks, when I load data using, provided function...
What kind of data we need to put. When I load list of images using **cv2.imread()** function. Its gives Error!! 
Hi, I've just starting working on semantic segmentation with tensorflow and this package have helped so much, so thanks a lot for the great work! There is just one thing...
Hi, I'm trying to run `multiclass segmentation (camvid).ipynb` example and get an error after running the following block: ``` import segmentation_models as sm ``` Here is the error: ``` ---------------------------------------------------------------------------...