set precision=3 in results

Author: KushajveerSingh

results/README.md

@@ -35,5 +35,4 @@ An ImageNet test set of 10,000 images sampled from new images roughly 10 years a
 A collection of 7500 images covering 200 of the 1000 ImageNet classes. Images are naturally occuring adversarial examples that confuse typical ImageNet classifiers. This is a challenging dataset, your typical ResNet-50 will score 0% top-1.
 
 ## TODO
-* Add rank difference, and top-1/top-5 difference from ImageNet-1k validation for the 3 additional test sets
 * Explore adding a reduced version of ImageNet-C (Corruptions) and ImageNet-P (Perturbations) from https://github.com/hendrycks/robustness. The originals are huge and image size specific.

results/generate_csv_results.py

@@ -44,7 +44,7 @@ def diff(csv_file):
     results[csv_file]['top1_diff'] = top1_diff
     results[csv_file]['top5_diff'] = top5_diff
 
-    results[csv_file].to_csv(csv_file, index=False, float_format='%.4f')
+    results[csv_file].to_csv(csv_file, index=False, float_format='%.3f')
 
 for csv_file in results:
     if csv_file != 'results-imagenet.csv': diff(csv_file)