saharudra

ValueError: not enough values to unpack (expected 2, got 1) while running the validation step

10

I am trying to run the training on a new datase starting from the pre-trained totaltext model using the following command: ` CUDA_VISIBLE_DEVICES=0 python train.py experiments/seg_detector/totaltext_resnet18_deform_thre.yaml --resume pretrained/totaltext_resnet18 --validate --visualize...

logfile is not showing any runs for the test set. The plots also don't show anything for test set and accuracy.

2

When I run the code, I get the following output: ``` (rn_env) exx@ubuntu:/data/Rudra/RelationNetworks-CLEVR$ python Python 3.6.6 (default, Jun 28 2018, 00:00:00) [GCC 4.8.4] on linux Type "help", "copyright", "credits" or...

Issue with the reconstruction run.

1

The language of the output after running `main_reconstruction.py` doesn't seem to be in English. Not sure where the error is as the value of parameter `lang` in `util.transform_id2word` is set...

Hi, Not sure if this is the right place to ask this question, but I adapted the RN code to train on the CLEVR dataset. I set up the hyperparameters...