Improve mAP0.5-0.95

Two changes provided
1. Added limit on the maximum number of detections for each image likewise pycocotools
2. Rework process_batch function

Changes ultralytics#2 solved issue ultralytics#4251
I also independently encountered the problem described in issue ultralytics#4251 that the values for the same thresholds do not match when changing the limits in the torch.linspace function.
These changes solve this problem.

Currently during validation yolov5x.pt model the following results were obtained:
from yolov5 validation
               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100%|██████████| 157/157 [01:07<00:00,  2.33it/s]
                 all       5000      36335      0.743      0.626      0.682      0.506
from pycocotools
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.505
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.685

These results are very close, although not completely pass the competition issue ultralytics#2258.
I think it's problem with false positive bboxes matched ignored criteria, but this is not actual for custom datasets and does not require an additional solution.

val.py

@@ -79,16 +79,17 @@ def process_batch(detections, labels, iouv):
     """
     correct = torch.zeros(detections.shape[0], iouv.shape[0], dtype=torch.bool, device=iouv.device)
     iou = box_iou(labels[:, 1:], detections[:, :4])
-    x = torch.where((iou >= iouv[0]) & (labels[:, 0:1] == detections[:, 5]))  # IoU above threshold and classes match
-    if x[0].shape[0]:
-        matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()  # [label, detection, iou]
-        if x[0].shape[0] > 1:
-            matches = matches[matches[:, 2].argsort()[::-1]]
-            matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
-            # matches = matches[matches[:, 2].argsort()[::-1]]
-            matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
-        matches = torch.Tensor(matches).to(iouv.device)
-        correct[matches[:, 1].long()] = matches[:, 2:3] >= iouv
+    for i in range(len(iouv)):
+        x = torch.where((iou >= iouv[i]) & (labels[:, 0:1] == detections[:, 5]))  # IoU above threshold and classes match
+        if x[0].shape[0]:
+            matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()  # [label, detection, iou]
+            if x[0].shape[0] > 1:
+                matches = matches[matches[:, 2].argsort()[::-1]]
+                matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
+                # matches = matches[matches[:, 2].argsort()[::-1]]
+                matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
+            matches = torch.Tensor(matches).to(iouv.device)
+            correct[matches[:, 1].long(), i] = True
     return correct
 
 
@@ -206,6 +207,7 @@ def run(data,
 
         # Metrics
         for si, pred in enumerate(out):
+            pred = pred[:100]
             labels = targets[targets[:, 0] == si, 1:]
             nl = len(labels)
             tcls = labels[:, 0].tolist() if nl else []  # target class