image-segmentation-keras icon indicating copy to clipboard operation
image-segmentation-keras copied to clipboard

Implementation of Segnet, FCN, UNet , PSPNet and other models in Keras.

Results 125 image-segmentation-keras issues
Sort by recently updated
recently updated
newest added
trafficstars

Is there a pre-trained MobileNet model available that can be used out of the box without any further training? Just like the 3 pre-trained models (pspnet_50_ADE_20K,pspnet_101_cityscapes and pspnet_101_voc12).

I was implementing the code detailed on "https://github.com/divamgupta/image-segmentation-keras" I am getting the error related to "o such file or directory: '/tmp/vgg_unet_1_config.json" I am using the dataset shared at https://drive.google.com/file/d/0B0d9ZiqAgFkiOHR1NTJhWVJMNEU/view?usp=sharing ....

How can I get the model_config from the models? example: model_config = { "output_height": 96, "input_height": 384, "input_width": 576, "n_classes": 151, "model_class": "resnet50_pspnet", "output_width": 144 }

Hi, First thank you for your fine work, it helped me a lot ! I'm currently working on my own dataset. It features images of animal's skin. This experiment's purpose...

In all of my classifications I hav thishorizontal line on the right edge: ![grafik](https://user-images.githubusercontent.com/48824691/89512949-375b7280-d7d4-11ea-9d15-5eebf245a67a.png) I am putting in slightly bigger images than the network expects since I am working with...

My use case requires me to implement Unet for satellite imagery with additional inputs. So the 6 channels consist of first 3 RGB channels and then 3 channels consisting of...

Hi! First of all I like to thank you about this great project and good code. I am using your project to try to segment some medical images with two...

I followed the tutorial and typed the following code. ```python from keras_segmentation.models.unet import vgg_unet model = vgg_unet(n_classes=51, input_height=416, input_width=608) model.train( train_images = "dataset_path/images_prepped_train/", train_annotations = "dataset_path/annotations_prepped_train/", checkpoints_path = "checkpoints/vgg_unet_1" ,...

I used from keras_segmentation. models. fcn import fcn_8_resnet50 from keras_segmentation. models. fcn import fcn_32_resnet50 from keras_segmentation. models. fcn import fcn_8_mobilenet from keras_segmentation. models. fcn import fcn_32_mobilenet I received the error....