retrain YOLOv7 on VOC

config/yolov7_config.py

@@ -1,56 +1,58 @@
 # YOLOv7 Config
 
 yolov7_cfg = {
-    # input
-    'trans_type': 'yolox',
-    'multi_scale': [0.5, 1.0],
-    # model
-    'backbone': 'elannet_large',
-    'pretrained': True,
-    'bk_act': 'silu',
-    'bk_norm': 'BN',
-    'bk_dpw': False,
-    'stride': [8, 16, 32],  # P3, P4, P5
-    # neck
-    'neck': 'csp_sppf',
-    'expand_ratio': 0.5,
-    'pooling_size': 5,
-    'neck_act': 'silu',
-    'neck_norm': 'BN',
-    'neck_depthwise': False,
-     # fpn
-    'fpn': 'yolov7_pafpn',
-    'fpn_act': 'silu',
-    'fpn_norm': 'BN',
-    'fpn_depthwise': False,
-    # head
-    'head': 'decoupled_head',
-    'head_act': 'silu',
-    'head_norm': 'BN',
-    'num_cls_head': 2,
-    'num_reg_head': 2,
-    'head_depthwise': False,
-    # matcher
-    'matcher': {'center_sampling_radius': 2.5,
-                'topk_candicate': 10},
-    # loss weight
-    'loss_obj_weight': 1.0,
-    'loss_cls_weight': 1.0,
-    'loss_box_weight': 5.0,
-    # training configuration
-    'no_aug_epoch': 20,
-    # optimizer
-    'optimizer': 'sgd',        # optional: sgd, adam, adamw
-    'momentum': 0.937,         # SGD: 0.937;    AdamW: invalid
-    'weight_decay': 5e-4,      # SGD: 5e-4;     AdamW: 5e-2
-    'clip_grad': 10,           # SGD: 10.0;     AdamW: -1
-    # model EMA
-    'ema_decay': 0.9999,       # SGD: 0.9999;   AdamW: 0.9998
-    'ema_tau': 2000,
-    # lr schedule
-    'scheduler': 'linear',
-    'lr0': 0.01,               # SGD: 0.01;     AdamW: 0.004
-    'lrf': 0.01,               # SGD: 0.01;     AdamW: 0.05
-    'warmup_momentum': 0.8,
-    'warmup_bias_lr': 0.1,
+    'yolov7_large':{
+        # input
+        'trans_type': 'yolov5',
+        'multi_scale': [0.5, 1.0],
+        # model
+        'backbone': 'elannet_large',
+        'pretrained': True,
+        'bk_act': 'silu',
+        'bk_norm': 'BN',
+        'bk_dpw': False,
+        'stride': [8, 16, 32],  # P3, P4, P5
+        # neck
+        'neck': 'csp_sppf',
+        'expand_ratio': 0.5,
+        'pooling_size': 5,
+        'neck_act': 'silu',
+        'neck_norm': 'BN',
+        'neck_depthwise': False,
+        # fpn
+        'fpn': 'yolov7_pafpn',
+        'fpn_act': 'silu',
+        'fpn_norm': 'BN',
+        'fpn_depthwise': False,
+        # head
+        'head': 'decoupled_head',
+        'head_act': 'silu',
+        'head_norm': 'BN',
+        'num_cls_head': 2,
+        'num_reg_head': 2,
+        'head_depthwise': False,
+        # matcher
+        'matcher': {'center_sampling_radius': 2.5,
+                    'topk_candicate': 10},
+        # loss weight
+        'loss_obj_weight': 1.0,
+        'loss_cls_weight': 1.0,
+        'loss_box_weight': 5.0,
+        # training configuration
+        'no_aug_epoch': 20,
+        # optimizer
+        'optimizer': 'sgd',        # optional: sgd, adam, adamw
+        'momentum': 0.937,         # SGD: 0.937;    AdamW: invalid
+        'weight_decay': 5e-4,      # SGD: 5e-4;     AdamW: 5e-2
+        'clip_grad': 10,           # SGD: 10.0;     AdamW: -1
+        # model EMA
+        'ema_decay': 0.9999,       # SGD: 0.9999;   AdamW: 0.9998
+        'ema_tau': 2000,
+        # lr schedule
+        'scheduler': 'linear',
+        'lr0': 0.01,               # SGD: 0.01;     AdamW: 0.004
+        'lrf': 0.01,               # SGD: 0.01;     AdamW: 0.05
+        'warmup_momentum': 0.8,
+        'warmup_bias_lr': 0.1,
+    },
 }

eval.py

@@ -28,7 +28,7 @@ def parse_args():
 
     # model
     parser.add_argument('-m', '--model', default='yolov1', type=str,
-                        choices=['yolov1', 'yolov2', 'yolov3', 'yolov4', 'yolov5', 'yolov7', 'yolov8', 'yolox'], help='build yolo')
+                        help='build yolo')
     parser.add_argument('--weight', default=None,
                         type=str, help='Trained state_dict file path to open')
     parser.add_argument('--conf_thresh', default=0.001, type=float,

test.py

@@ -40,7 +40,7 @@ def parse_args():
 
     # model
     parser.add_argument('-m', '--model', default='yolov1', type=str,
-                        choices=['yolov1', 'yolov2', 'yolov3', 'yolov4', 'yolov5', 'yolov7', 'yolov8', 'yolox'], help='build yolo')
+                        help='build yolo')
     parser.add_argument('--weight', default=None,
                         type=str, help='Trained state_dict file path to open')
     parser.add_argument('-ct', '--conf_thresh', default=0.1, type=float,

train.py

@@ -56,7 +56,7 @@ def parse_args():
 
     # model
     parser.add_argument('-m', '--model', default='yolov1', type=str,
-                        choices=['yolov1', 'yolov2', 'yolov3', 'yolov4', 'yolov5', 'yolov7', 'yolov8', 'yolox'], help='build yolo')
+                        help='build yolo')
     parser.add_argument('-ct', '--conf_thresh', default=0.005, type=float,
                         help='confidence threshold')
     parser.add_argument('-nt', '--nms_thresh', default=0.6, type=float,

train.sh

@@ -3,11 +3,11 @@ python train.py \
         --cuda \
         -d coco \
         --root /mnt/share/ssd2/dataset/ \
-        -m yolox \
+        -m yolov7_large \
         -bs 16 \
         -size 640 \
         --wp_epoch 1 \
-        --max_epoch 250 \
+        --max_epoch 150 \
         --eval_epoch 10 \
         --ema \
         --fp16 \