Pycocotools best.pt after COCO train (#1593)

test.py

 import argparse
-import glob
 import json
 import os
 from pathlib import Path
@@ -246,7 +245,7 @@ def test(data,
     # Save JSON
     if save_json and len(jdict):
         w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else ''  # weights
-        anno_json = glob.glob('../coco/annotations/instances_val*.json')[0]  # annotations json
+        anno_json = '../coco/annotations/instances_val2017.json'  # annotations json
         pred_json = str(save_dir / f"{w}_predictions.json")  # predictions json
         print('\nEvaluating pycocotools mAP... saving %s...' % pred_json)
         with open(pred_json, 'w') as f:
@@ -266,7 +265,7 @@ def test(data,
             eval.summarize()
             map, map50 = eval.stats[:2]  # update results (mAP@0.5:0.95, mAP@0.5)
         except Exception as e:
-            print('ERROR: pycocotools unable to run: %s' % e)
+            print(f'pycocotools unable to run: {e}')
 
     # Return results
     if not training:

train.py

@@ -22,6 +22,7 @@ from torch.utils.tensorboard import SummaryWriter
 from tqdm import tqdm
 
 import test  # import test.py to get mAP after each epoch
+from models.experimental import attempt_load
 from models.yolo import Model
 from utils.autoanchor import check_anchors
 from utils.datasets import create_dataloader
@@ -193,9 +194,9 @@ def train(hyp, opt, device, tb_writer=None, wandb=None):
     # Process 0
     if rank in [-1, 0]:
         ema.updates = start_epoch * nb // accumulate  # set EMA updates
-        testloader = create_dataloader(test_path, imgsz_test, total_batch_size, gs, opt,
+        testloader = create_dataloader(test_path, imgsz_test, total_batch_size, gs, opt,  # testloader
                                        hyp=hyp, cache=opt.cache_images and not opt.notest, rect=True,
-                                       rank=-1, world_size=opt.world_size, workers=opt.workers)[0]  # testloader
+                                       rank=-1, world_size=opt.world_size, workers=opt.workers, pad=0.5)[0]
 
         if not opt.resume:
             labels = np.concatenate(dataset.labels, 0)
@@ -385,15 +386,12 @@ def train(hyp, opt, device, tb_writer=None, wandb=None):
 
     if rank in [-1, 0]:
         # Strip optimizers
-        n = opt.name if opt.name.isnumeric() else ''
-        fresults, flast, fbest = save_dir / f'results{n}.txt', wdir / f'last{n}.pt', wdir / f'best{n}.pt'
-        for f1, f2 in zip([wdir / 'last.pt', wdir / 'best.pt', results_file], [flast, fbest, fresults]):
-            if f1.exists():
-                os.rename(f1, f2)  # rename
-                if str(f2).endswith('.pt'):  # is *.pt
-                    strip_optimizer(f2)  # strip optimizer
-                    os.system('gsutil cp %s gs://%s/weights' % (f2, opt.bucket)) if opt.bucket else None  # upload
-        # Finish
+        for f in [last, best]:
+            if f.exists():  # is *.pt
+                strip_optimizer(f)  # strip optimizer
+                os.system('gsutil cp %s gs://%s/weights' % (f, opt.bucket)) if opt.bucket else None  # upload
+
+        # Plots
         if plots:
             plot_results(save_dir=save_dir)  # save as results.png
             if wandb:
@@ -401,6 +399,19 @@ def train(hyp, opt, device, tb_writer=None, wandb=None):
                 wandb.log({"Results": [wandb.Image(str(save_dir / f), caption=f) for f in files
                                        if (save_dir / f).exists()]})
         logger.info('%g epochs completed in %.3f hours.\n' % (epoch - start_epoch + 1, (time.time() - t0) / 3600))
+
+        # Test best.pt
+        if opt.data.endswith('coco.yaml') and nc == 80:  # if COCO
+            results, _, _ = test.test(opt.data,
+                                      batch_size=total_batch_size,
+                                      imgsz=imgsz_test,
+                                      model=attempt_load(best if best.exists() else last, device).half(),
+                                      single_cls=opt.single_cls,
+                                      dataloader=testloader,
+                                      save_dir=save_dir,
+                                      save_json=True,  # use pycocotools
+                                      plots=False)
+
     else:
         dist.destroy_process_group()
 

utils/google_utils.py

@@ -17,7 +17,7 @@ def gsutil_getsize(url=''):
 
 def attempt_download(weights):
     # Attempt to download pretrained weights if not found locally
-    weights = weights.strip().replace("'", '')
+    weights = str(weights).strip().replace("'", '')
     file = Path(weights).name.lower()
 
     msg = weights + ' missing, try downloading from https://github.com/ultralytics/yolov3/releases/'