pba

pba copied to clipboard

- I see you have clearly stated that pba has been tested with tensorflow 1.10.0 and 1.11.0 and so is the case with ray which has been tested with 0.7.0...

abhinavankur

Hi PBA Team, Spotted this warning in my IDE when looking through your code: https://github.com/arcelien/pba/blob/a9cc308d936dee488aab7e3582ab7a47167b587a/pba/augmentation_transforms.py#L224 > `getargspec()` has been deprecated since Python 3.0 in favour of `getfullargspec()` It may be...

MichaelMcAleer

when I run train.py there is only one GPU has utilization

3

I have 4 GPUs, when I run train.py with --num_samples 1 --gpu 4，there is only one GPU has utilization. Is it because the model does not support multiple GPUs? But...

csyuan

Can't reproduce the results in the table3

2

Hi, thanks for providing the nice code. I've tried to reproduce the results in table3 with "bash scripts/table_3_rcifar10.sh wrn_28_10". The highest test acc is 87.42% among twice trial, which is...

sherylwang

use for own dataset

24

hello everyone, can you show me any guide to run augmentation on my own dataset.

tienduchoang

Multiple GPU running

2

Does this code work on multi-gpu?

snownus

Eval with the schedules

10

Hi, As I know, in python 3.5.X or python 2.X , 'dict' structure has random keys order. For example, If I do this a = {'one' : 1, 'two' :...

serereuk

Possible unhandled error from worker

1

@arcelien I came across an issue when extending PBA to my own network structure. **The error is like this: ERROR worker.py:1612 -- Possible unhandled error from worker: ray_RayModel:restore_from_object() (pid=49849, host=XXX)...

snownus

Resume pba

2

Is there anyway to pause/resume the pba search? I know that the checkpoints are saved, but how could we resume by command line, for cases when the search is for...

abcp4

Bounding box dataset

1

Hi everyone, did you tried PBA on a dataset with bounding boxes? If not what part of the code should I change to work with this type of data?

MattVil