segmentation_models.pytorch

segmentation_models.pytorch copied to clipboard

Predict on Camvid Example With No Masks

1

Newbie here, anyone willing to share code for making predictions on my test image without masks? Model is well trained, just struggling to code the dataloader so I can make...

ghost

Error running binary_segmentation_intro.ipynb

1

On sagemaker studio, `ml.g4dn.xlarge` instance and pytorch 1.10 kernel, the notebook raises an error at `trainer.fit`: ``` /opt/conda/lib/python3.8/site-packages/torch/_utils.py in reraise(self) 432 # instantiate since we don't know how to 433...

robmarkcole

Output n_class is less than len(class_name) in training?

5

Hi, Thanks for your work. I used your code to train a multi-class segmentation task. I have 10 classes, but after training, the output mask just have 8 classes( using...

ymzlygw

preprocessing fn not working

1

Hello, I am trying to run the following snippet: ```python from segmentation_models_pytorch.encoders import get_preprocessing_fn preprocess_input = get_preprocessing_fn('resnet34', pretrained='imagenet') for img, mask in trainloader: print(x.size()) x = preprocess_input(x) print(x.size()) break ```...

rohan-insitro

Cannot import trained model

3

I have trained two unet++ models and the model format is in **.pth**. A few days ago I can load the model but now I cannot load it anymore. I...

NyanSwanAung

Module not found

3

module 'segmentation_models_pytorch' has no attribute 'utils'

TalhaOmi

Colab notebook not found

3

https://github.com/googlecolab/colabtools/blob/master/examples/binary_segmentation_intro.ipynb linked on readme returns Notebook not found

robmarkcole

Will you update the multiclass seg example?

1

It uses the old repo version and metrics so it wont work with the latest version. Thanks, Sam

davodogster

'EfficientNetEncoder' object has no attribute 'act1' when loading back timm-efficient-b5 weights

2

I trained a model of `timm-efficientnet-b5` with `imagenet` pretrained weights on my custom dataset. The train & val process works good. Then when I loaded it back in another script...

zlyin

qubvel