Maryam Mahootiha comments

Results 8 comments of


                                            Maryam Mahootiha

Could not use GPU for pycox

Hi Havard, I made a model with pycox as you told before after making model I used the set device to give the model to GPU my cuda is available...

How can I save and load torchtuple model ?

Hi Havard, when I want to save the model I get this error. Do you know what is the problem? File ~/Documents/survival_analysis/survival_estimate.py:52 in model.save_net('mynet.pt') File ~/anaconda3/envs/myenv/lib/python3.9/site-packages/torchtuples/base.py:681 in save_net return torch.save(self.net,...

How can I save and load torchtuple model ?

train_survmodel is a function that I make my net in this function then I fit the model with Logistichazard and finally I return the model after that I try to...

Experience in train/val/test partitions with survival data in real-world datasets

Thanks a lot @glgmartin for the code of calculating AUC with sksurv. I couldn't structure the arrays and this code helped me. Just I can add what is the times...

same survival probabilities from predict_surv_df

There is one strange thing, that when I had validation dataset I got good c-index when validation loss was high and I got bad c-indexes and same probabilities when validation...

Add Zenodo or a relevant citation guidance to get cited for the important work you have done

Completely agree

Use Unet as a net for feeding it to logistichazard

I do not have a large dataset. It contains around 50, 3d images. Not a classifier. I try to train a segmentation model to get the features of the segmented...

.from_pretrained for 3d inputs

``` class EfficientNet3D(nn.Module): """ An EfficientNet model. Most easily loaded with the .from_name or .from_pretrained methods Args: blocks_args (list): A list of BlockArgs to construct blocks global_params (namedtuple): A set...