image-segmentation-keras

image-segmentation-keras copied to clipboard

Accuracy not increasing for 1 class segmentation

2

I want to train segmentation only on 1 class, so I have set ignore_zero_class as True. And I can see in the code that it still picks crossentropy loss. Not...

silvernox-dev

Problems upgrading on Tensorflow>=2.5.0 and CUDA>=11.0

3

I am using your framework for over a year, using an anaconda environment having the following main packages with the **cudatoolkit==10.0**: - python==3.6 - h5py==2.10.0 - Keras==2.2.5 - Keras-Preprocessing==1.1.2 -...

sotomotocross

Tensorflow 2.5.0 compatibility with the package

4

I am trying to make your powerful library with an RTX 3070 Ti. After creating a python 3.8 anaconda environment with CUDA 11.3.1 and cuDNN 8.2.1 The lowest tensorflow version...

sotomotocross

training/validaiton loss/accuracy

3

How can I have the loss and accuracy of the training and validation phase across all epochs? I want to plot them versus epochs. Thanks

Saeid-Sli

I wish to define a custom binary crossentropy loss, in which I plan to apply the binary crossentropy loss on the foreground (1), and on the background(0), and then train...

varungupta31

no meta file generated after the training

3

There are no meta file generated. These are the files generated after 2 epochs. Can someone please help. ``` vgg_unet_1.00001.index vgg_unet_1.00001.data-00000-of-00001 vgg_unet_1.00002.index vgg_unet_1.00002.data-00000-of-00001 ```

sachinkmohan

module 'keras.utils' has no attribute 'get_file'

9

hello @divamgupta I WANT to run your network but as soon as I type: model = pspnet_50_ADE_20K() it shows me that error. I'm stucked pls help.

ranch-hands

VGG32 not giving any predictions after training on same datasets as other models

3

Hello! I am using the various models of this repo for my thesis. I try to predict zebra crossings from aerial images. It has the following setup: 1) I trained...

SjoerdBraaksma

Prediction is different when the model is loaded

8

I have trained a vgg_unet model for segmenting buildings,roads,water bodies and vegetation. The accuracy of the model is 94%. When I get the prediction from the model it is good....

yashkan27

ImportError: cannot import name 'get_config' from 'tensorflow.python.eager.context' (/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/context.py)

4

Hello, I tried running the colab example after changing the lines ` !pip install git+https://github.com/divamgupta/image-segmentation-keras ` to ``` !pip uninstall tensorflow tensorboard tensorboard-data-server tensorflow-datasets tensorflow-estimator tensorflow-gcs-config tensorflow-hub tensorflow-metadata tensorflow-probability keras...

dennex