From 3d9a65bace5dd1ac7d7c761ccacba9c2dbbbe5e9 Mon Sep 17 00:00:00 2001 From: NanoCode012 Date: Sun, 26 Jul 2020 00:24:39 +0700 Subject: [PATCH] --notest bug fix (#518) * Fix missing results_file and fi when notest passed * Update train.py reverting previous changes and removing functionality from 'if not opt.notest or final_epoch: # Calculate mAP' loop. Co-authored-by: Glenn Jocher --- train.py | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/train.py b/train.py index bfed25d4cf68..086ae2665228 100644 --- a/train.py +++ b/train.py @@ -346,24 +346,24 @@ def train(hyp, tb_writer, opt, device): dataloader=testloader, save_dir=log_dir) - # Write - with open(results_file, 'a') as f: - f.write(s + '%10.4g' * 7 % results + '\n') # P, R, mAP, F1, test_losses=(GIoU, obj, cls) - if len(opt.name) and opt.bucket: - os.system('gsutil cp %s gs://%s/results/results%s.txt' % (results_file, opt.bucket, opt.name)) - - # Tensorboard - if tb_writer: - tags = ['train/giou_loss', 'train/obj_loss', 'train/cls_loss', - 'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', - 'val/giou_loss', 'val/obj_loss', 'val/cls_loss'] - for x, tag in zip(list(mloss[:-1]) + list(results), tags): - tb_writer.add_scalar(tag, x, epoch) - - # Update best mAP - fi = fitness(np.array(results).reshape(1, -1)) # fitness_i = weighted combination of [P, R, mAP, F1] - if fi > best_fitness: - best_fitness = fi + # Write + with open(results_file, 'a') as f: + f.write(s + '%10.4g' * 7 % results + '\n') # P, R, mAP, F1, test_losses=(GIoU, obj, cls) + if len(opt.name) and opt.bucket: + os.system('gsutil cp %s gs://%s/results/results%s.txt' % (results_file, opt.bucket, opt.name)) + + # Tensorboard + if tb_writer: + tags = ['train/giou_loss', 'train/obj_loss', 'train/cls_loss', + 'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', + 'val/giou_loss', 'val/obj_loss', 'val/cls_loss'] + for x, tag in zip(list(mloss[:-1]) + list(results), tags): + tb_writer.add_scalar(tag, x, epoch) + + # Update best mAP + fi = fitness(np.array(results).reshape(1, -1)) # fitness_i = weighted combination of [P, R, mAP, F1] + if fi > best_fitness: + best_fitness = fi # Save model save = (not opt.nosave) or (final_epoch and not opt.evolve)