Pantelis Kaniouras
Pantelis Kaniouras
Hi there, I would like to get some advice from you guys regarding on how a prediction should be properly evaluated. I created a U-Net model with resnet34 as backbone...
Good evening. I would like to use a U-Net with a pre-trained ResNet encoder as a multi-task learning neural network with a multi-task weighted loss function. Could you please guide...
Hi guys, I would like to ask you some questions. I am trying to train a UNet model with a ResNet encoder (exactly like the one that you provide in...
Good evening, I am trying to use one of the quick-start templates and I am receiving the following error: ``` (env name) username@username-ubuntu:~/Documents/python_projects/InstaPy$ python my_quickstart.py InstaPy Version: 0.6.11 ._. ._....
Hi, congrats on your work! I am wondering, could your method be applied to a binary semantic segmentation task? I am interested in segmenting roads from aerial imagery, by classifying...
Hi, I have been trying to download the training data for the SpaceNet Road Dataset without success. I tried commands like aws s3 cp s3://spacenet-dataset/SpaceNet_Roads_Competition/SpaceNet_Roads_Sample.tar.gz . in my Ubuntu 18.04,...
I would like to use more than 3 channels/bands per image (not only RGB). How can I do that? What needs to be modified in order for the network to...
Hi, could you please help me change the backbone neural net (to be more specific with a ResNet34 pre-trained on ImageNet) and change the final tasks with 3 classification tasks?...
Hi, thanks for your work. Could you please help me write down a TensorFlow or Keras version of this loss function?
Hi, I am trying to run your demo ("Build graph") and I get the following error: _pickle.UnpicklingError: invalid load key, 'O'. The above exception was the direct cause of the...