fix logger

Author: rickycao-qy

__init__.py

@@ -62,7 +62,6 @@ def train(modelWrapper, data, hyp, opt, device):
   cuda = device.type != 'cpu'
   init_seeds(2 + rank)
 
-  print('.......', opt.data)
   with open(opt.data) as f:
     data_dict = yaml.load(f, Loader=yaml.FullLoader)
   with torch_distributed_zero_first(rank):
@@ -159,14 +158,14 @@ def train(modelWrapper, data, hyp, opt, device):
   logger.info('Image sizes %g train, %g test\n'
               'Using %g dataloader workers\nLogging results to %s\n'
               'Starting training for %g epochs...' % (imgsz, imgsz_test, dataloader.num_workers, log_dir, epochs))
-
+  logger.info(('\n' + '%10s' * 8) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'total', 'targets', 'img_size'))
   for epoch in range(start_epoch, epochs):
+    logger.info('Epoch: ' + str(epoch))
     model.train()
 
     mloss = torch.zeros(4, device=device)  # mean losses
     pbar = enumerate(dataloader)
-    logger.info(('\n' + '%10s' * 8) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'total', 'targets', 'img_size'))
-    pbar = tqdm(pbar, total=nb)  # progress bar
+    
     optimizer.zero_grad()
     for i, (imgs, targets, paths, _) in pbar:
         ni = i + nb * epoch  # number integrated batches (since train start)
@@ -206,7 +205,6 @@ def train(modelWrapper, data, hyp, opt, device):
         mem = '%.3gG' % (torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0)  # (GB)
         s = ('%10s' * 2 + '%10.4g' * 6) % (
             '%g/%g' % (epoch, epochs - 1), mem, *mloss, targets.shape[0], imgs.shape[-1])
-        pbar.set_description(s)
 
         # Plot
         if ni < 3:
@@ -215,7 +213,7 @@ def train(modelWrapper, data, hyp, opt, device):
 
 
         # end batch ------------------------------------------------------------------------------------------------
-
+    logger.info(s)
     # Scheduler
     lr = [x['lr'] for x in optimizer.param_groups]  # for tensorboard
     scheduler.step()
@@ -241,7 +239,7 @@ def train(modelWrapper, data, hyp, opt, device):
     fi = fitness(np.array(results).reshape(1, -1))  # weighted combination of [P, R, [email protected], [email protected]]
     if fi > best_fitness:
         best_fitness = fi
-    print('----best map', fi)
+    logger.info('Current Best Map: ' + str(fi))
 
     # Save model
     with open(results_file, 'r') as f:  # create checkpoint

evaluate.py

@@ -86,7 +86,7 @@ def test(data,
     p, r, f1, mp, mr, map50, map, t0, t1 = 0., 0., 0., 0., 0., 0., 0., 0., 0.
     loss = torch.zeros(3, device=device)
     jdict, stats, ap, ap_class = [], [], [], []
-    for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
+    for batch_i, (img, targets, paths, shapes) in enumerate(dataloader):
         img = img.to(device, non_blocking=True)
         img = img.half() if half else img.float()  # uint8 to fp16/32
         img /= 255.0  # 0 - 255 to 0.0 - 1.0
@@ -135,20 +135,6 @@ def test(data,
             # Clip boxes to image bounds
             clip_coords(pred, (height, width))
 
-            # Append to pycocotools JSON dictionary
-            if save_json:
-                # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
-                image_id = Path(paths[si]).stem
-                box = pred[:, :4].clone()  # xyxy
-                scale_coords(img[si].shape[1:], box, shapes[si][0], shapes[si][1])  # to original shape
-                box = xyxy2xywh(box)  # xywh
-                box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
-                for p, b in zip(pred.tolist(), box.tolist()):
-                    jdict.append({'image_id': int(image_id) if image_id.isnumeric() else image_id,
-                                  'category_id': coco91class[int(p[5])],
-                                  'bbox': [round(x, 3) for x in b],
-                                  'score': round(p[4], 5)})
-
             # Assign all predictions as incorrect
             correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device)
             if nl:
@@ -211,31 +197,7 @@ def test(data,
     # Print speeds
     t = tuple(x / seen * 1E3 for x in (t0, t1, t0 + t1)) + (imgsz, imgsz, batch_size)  # tuple
     if not training:
-        print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t)
-
-    # Save JSON
-    if save_json and len(jdict):
-        f = 'detections_val2017_%s_results.json' % \
-            (weights.split(os.sep)[-1].replace('.pt', '') if isinstance(weights, str) else '')  # filename
-        print('\nCOCO mAP with pycocotools... saving %s...' % f)
-        with open(f, 'w') as file:
-            json.dump(jdict, file)
-
-        try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
-            from pycocotools.coco import COCO
-            from pycocotools.cocoeval import COCOeval
-
-            imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files]
-            cocoGt = COCO(glob.glob('../coco/annotations/instances_val*.json')[0])  # initialize COCO ground truth api
-            cocoDt = cocoGt.loadRes(f)  # initialize COCO pred api
-            cocoEval = COCOeval(cocoGt, cocoDt, 'bbox')
-            cocoEval.params.imgIds = imgIds  # image IDs to evaluate
-            cocoEval.evaluate()
-            cocoEval.accumulate()
-            cocoEval.summarize()
-            map, map50 = cocoEval.stats[:2]  # update results ([email protected]:0.95, [email protected])
-        except Exception as e:
-            print('ERROR: pycocotools unable to run: %s' % e)
+        print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t)    
 
     # Return results
     model.float()  # for training

tools/datasets.py

@@ -1001,7 +1001,6 @@ def preprocess(data):
     names, trainRootDir = preprocess_help(data, 'train')
     valnames, valRootDir = preprocess_help(data, 'val')
     testnames, testRootDir = preprocess_help(data, 'test')
-    print('------names', names, valnames, testnames)
     test = val = train = os.path.join(trainRootDir, 'images', 'train')
     if (len(valnames) > 0):
         val = os.path.join(valRootDir, 'images', 'val')