Abhishek Shivkumar comments

Results 13 comments of


                                            Abhishek Shivkumar

Getting loss_bbox = nan while training on caltech dataset

Ho can we identify which images in our dataset is causing this problem?

Continuously increasing RAM with Pre-training

We have a a custom dataloder that loads images and text from a parquet file.

Continuously increasing RAM with Pre-training

We have 1 Million images stored on disk and we have prepared the JSON file as described in the Github read me page. The Dataloader we have loads the json...

Continuously increasing RAM with Pre-training

We ended up using the `pretrain_dataset.py` file and formatted the data as a json file exactly as mentioned in the readme file. Even then we see the RAM utilization go...

Continuously increasing RAM with Pre-training

We are happy to follow any other debugging steps to make this a success please. - thanks

RuntimeWarning: invalid value encountered in less

Did anyone figure out the reason @ChaoWangHS ? I am getting the same error too and it seems to be happening for specific batch sizes.

skvideo.io.vreader always capturing the same, fixed frame

Has this been solved? I still see the same problem with version scikit-video==1.1.11

UnpicklingError in both py2 and py3

Anyone managed to solve this?

Continuously increasing RAM with Pre-training

Thanks, will take a look

Different results between demo_syncnet.py and run_syncnet.py

Any update on this please?