train YOLOv1-R18

models/yolov1/README.md

@@ -1,8 +1,16 @@
 # Redesigned YOLOv1:
 
+- VOC
+
+| Model  |  Backbone  | Batch | Scale | AP<sup>val<br>0.5 | Weight |
+|--------|------------|-------|-------|-------------------|--------|
+| YOLOv1 | ResNet-18  | 1xb16 |  640  |                   |  |
+
+- COCO
+
 | Model  |  Backbone  | Batch | Scale | AP<sup>val<br>0.5:0.95 | AP<sup>val<br>0.5 | FLOPs<br><sup>(G) | Params<br><sup>(M) | Weight |
 |--------|------------|-------|-------|------------------------|-------------------|-------------------|--------------------|--------|
-| YOLOv1 | ResNet-18  | 1xb16 |  640  |        27.9            |       47.5        |   37.8            |   21.3             | [ckpt](https://github.com/yjh0410/RT-ODLab/releases/download/yolo_tutorial_ckpt/yolov1_coco.pth) |
+| YOLOv1 | ResNet-18  | 1xb16 |  640  |                    |               |   37.8            |   21.3             | [ckpt](https://github.com/yjh0410/RT-ODLab/releases/download/yolo_tutorial_ckpt/yolov1_coco.pth) |
 
 - For training, we train redesigned YOLOv1 with 150 epochs on COCO.
 - For data augmentation, we only use the large scale jitter (LSJ), no Mosaic or Mixup augmentation.

models/yolov1/yolov1_pred.py

@@ -5,9 +5,7 @@ import torch.nn as nn
 # -------------------- Detection Pred Layer --------------------
 ## Single-level pred layer
 class Yolov1DetPredLayer(nn.Module):
-    def __init__(self,
-                 cfg,
-                 num_classes):
+    def __init__(self, cfg, num_classes):
         super().__init__()
         # --------- Basic Parameters ----------
         self.stride  = cfg.out_stride