Brandon Truth

icon indicating a website link https://brandonliang.github.io/

icon location New York icon location Talk Data to me

Results 2 issues of Brandon Truth

main.py line 287 defaults = {**train_data_defaults} - SyntaxError: invalid syntax

1 comment

Hi, This is the output on command line: python main.py --dataset cifar10 --model resnet --model-config "{'depth': 44}" --duplicates 32 --cutout -b 64 --epochs 100 --save resnet_44_cutout_m-32-new File "main.py", line 287...

[plugin_event_accumulator.py:323] Found more than one graph event per run, or there was a metagraph containing a graph_def, as well as one or more graph events. Overwriting the graph with the newest event.

1 comment

Hi, I use writer.add_scalar() in a similar fashion as your tutorial, where I add training loss & accuracy for each iteration in each epoch. I am seeing these std output...