Semantic-Segmentation-Suite icon indicating copy to clipboard operation
Semantic-Segmentation-Suite copied to clipboard

Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!

Results 82 Semantic-Segmentation-Suite issues
Sort by recently updated
recently updated
newest added

When i download the the pretrained-weights in get_pretrained_checkpoints.py. The browser tell me 'the xml file does not appear to have any style information associated with it'. I don't know if...

Hello, Firstly, thank you for making the source code of the suite open source. I have a problem regarding the time taken for prediction. It is just above 2 seconds...

im new to this field . In this repo, there are frontend models. if i use them, am i doing fine-tuning ? or transfer learning? for example, if i use...

Hey Georg, I have do not fully comprehend your AdapNet implementation, specifically lines 119 through 124: 119 `net = ResNetBlock_1(net, filters_1=128, filters_2=512)` 121 `skip_connection = ConvBlock(net, n_filters=12, kernel_size=[1, 1])` 124...

I wnat to the train going on, I need to set 1?

hello i'm korean student. yesterday i tried to run train.py and latest_model_DeepLabV3_CamVid.ckpt was made. and to try to run test.py, i tried this command "python test.py --models DeepLabV3 --checkpoint_path checkpoints/latest_model_DeepLabV3_CamVid.ckpt....

tried all of the files in the checkpoints folder: model.ckpt.index model.ckpt.meta checkpoint model.ckpt.data-00000-of-00001 none of them work: Semantic-Segmentation-Suite/checkpoints/0295/model.ckpt.data-00000-of-00001: Data loss: not an sstable (bad magic number): perhaps your file is...

Bug report ### Information ## Please specify the following information when submitting an issue: - **What are your command line arguments?:** Command line args: CUDA_VISIBLE_DEVICES=0 python -m pdb train.py --num_epochs...

Hello, What are versions you are using for the different libraries and pip

Excuse me, why do I train normally? Val IOU is over 94%, but the label I predicted is all black. Some people say that the output is pixel category. How...