ICIAR2018

ICIAR2018 copied to clipboard

I tried with the pre-trained models, but the outcome is the same for every image. All my test dataset is being labelled as Normal, but I have provide all the...

valentina-paniza

Hi, I tried to use the provided pretrained models to predict on test set provided on BACH website. I added a csv writer, replace "volatile" with "with torch.no_grad()" to fix...

jingweizhang-xyz

I only see the patch-wise model is trained 30 epochs in the paper. Can you also specify the number of epoch used to train image-wise model for researchers to replicate...

CaelynCheung1996

RuntimeError when training image-wise network

1

I encountered this problem when running in mode "0" to train image-wise network after done training patch-wise one. Traceback (most recent call last): File "train.py", line 18, in iw_model.train() File...

CaelynCheung1996

patch-wise model could only reach 68%

1

I've tried to run the patch-wise model for multiple times, but could only reach a maximum accuracy of around 70% and average accuracy around 60%, here's all the hyperparameters I've...

minqz2009

out of memory error

2

------------ Options ------------- batch_size: 64 beta1: 0.9 beta2: 0.999 channels: 1 checkpoints_path: ./checkpoints cuda: True dataset_path: ./dataset debug: False ensemble: 1 epochs: 30 gpu_ids: 1 log_interval: 50 lr: 0.001 network:...

ouceduxzk

ZeroDivisionError while running train.py

3

Have setup the repository on Google Colab and uploaded train, test and validation (of 100 random images from train set) and tried running train.py which resulted in the following error....

TuhinKundu

May I ask if you could disclose the composition of your training and validation sets? I suspect that you only used a clever method to achieve high accuracy, and changing...

giao-cloude