The evaluation results are all -1.000

[chycxyzd]

I used a custom dataset to finetune the model, and all losses were present and decreased normally. After 70 epochs, I conducted a test and the results showed that objects could be detected correctly. However, my evaluation metric has always been -1.000. What is the reason for this?

Here is my configuration：
`base = ('../../third_party/mmyolo/configs/yolov8/'
'yolov8_l_syncbn_fast_8xb16-500e_coco.py')
custom_imports = dict(imports=['yolo_world'], allow_failed_imports=False)

hyper-parameters

num_classes = 1
num_training_classes = 1
max_epochs = 500 # Maximum training epochs
close_mosaic_epochs = 30
save_epoch_intervals = 50
text_channels = 512
neck_embed_channels = [128, 256, base.last_stage_out_channels // 2]
neck_num_heads = [4, 8, base.last_stage_out_channels // 2 // 32]
base_lr = 1e-3
weight_decay = 0.0005
train_batch_size_per_gpu = 1
load_from = r'D:\plant_detection\YOLO-World-master\weights\yolo_world_v2_l_clip_large_o365v1_goldg_pretrain_800ft-9df82e55.pth' # 'pretrained_models/yolo_world_l_clip_t2i_bn_2e-3adamw_32xb16-100e_obj365v1_goldg_cc3mlite_train-ca93cd1f.pth'

text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'

text_model_name = r'D:\plant_detection\YOLO-World-master\configs\clip-vit-base-patch32'
persistent_workers = False

model settings

model = dict(type='YOLOWorldDetector',
mm_neck=True,
num_train_classes=num_training_classes,
num_test_classes=num_classes,
data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
backbone=dict(delete=True,
type='MultiModalYOLOBackbone',
image_model={{base.model.backbone}},
text_model=dict(type='HuggingCLIPLanguageBackbone',
model_name=text_model_name,
frozen_modules=['all'])),
neck=dict(type='YOLOWorldPAFPN',
guide_channels=text_channels,
embed_channels=neck_embed_channels,
num_heads=neck_num_heads,
block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
bbox_head=dict(type='YOLOWorldHead',
head_module=dict(
type='YOLOWorldHeadModule',
use_bn_head=True,
embed_dims=text_channels,
num_classes=num_training_classes)),
train_cfg=dict(assigner=dict(num_classes=num_training_classes)))

dataset settings

text_transform = [
dict(type='RandomLoadText',
num_neg_samples=(num_classes, num_classes),
max_num_samples=num_training_classes,
padding_to_max=True,
padding_value=''),
dict(type='mmdet.PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
'flip_direction', 'texts'))
]
mosaic_affine_transform = [
dict(type='MultiModalMosaic',
img_scale=base.img_scale,
pad_val=114.0,
pre_transform=base.pre_transform),
dict(
type='YOLOv5RandomAffine',
max_rotate_degree=0.0,
max_shear_degree=0.0,
max_aspect_ratio=100.,
scaling_ratio_range=(1 - base.affine_scale, 1 + base.affine_scale),
# img_scale is (width, height)
border=(-base.img_scale[0] // 2, -base.img_scale[1] // 2),
border_val=(114, 114, 114))
]

train_pipeline = [
*base.pre_transform, mosaic_affine_transform,
dict(type='YOLOv5MultiModalMixUp',
prob=base.mixup_prob,
pre_transform=[base.pre_transform, *mosaic_affine_transform]),
*base.last_transform[:-1], text_transform
]
train_pipeline_stage2 = [base.train_pipeline_stage2[:-1], *text_transform]

coco_train_dataset = dict(delete=True,
type='MultiModalDataset',
dataset=dict(
type='YOLOv5CocoDataset',
metainfo=dict(classes=['crop']),
data_root=r'C:\Users\lenovo\Desktop\self_coco',
ann_file=r'C:\Users\lenovo\Desktop\self_coco\train.json',
data_prefix=dict(img=r'C:\Users\lenovo\Desktop\self_coco\train'),
filter_cfg=dict(filter_empty_gt=False,
min_size=32)),
class_text_path=r'C:\Users\lenovo\Desktop\self_coco\coco_class_text.json',
pipeline=train_pipeline)

train_dataloader = dict(persistent_workers=persistent_workers,
batch_size=train_batch_size_per_gpu,
collate_fn=dict(type='yolow_collate'),
dataset=coco_train_dataset)
test_pipeline = [
*base.test_pipeline[:-1],
dict(type='LoadText'),
dict(type='mmdet.PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'pad_param', 'texts'))
]
coco_val_dataset = dict(
delete=True,
type='MultiModalDataset',
dataset=dict(type='YOLOv5CocoDataset',
metainfo=dict(classes=['crop']),
data_root=r'C:\Users\lenovo\Desktop\self_coco',
ann_file=r'C:\Users\lenovo\Desktop\self_coco\val.json',
data_prefix=dict(img=r'C:\Users\lenovo\Desktop\self_coco\val'),
filter_cfg=dict(filter_empty_gt=False, min_size=32)),
class_text_path=r'C:\Users\lenovo\Desktop\self_coco\coco_class_text.json',
pipeline=test_pipeline)
val_dataloader = dict(dataset=coco_val_dataset)
test_dataloader = val_dataloader

training settings

default_hooks = dict(param_scheduler=dict(scheduler_type='linear',
lr_factor=0.01,
max_epochs=max_epochs),
checkpoint=dict(max_keep_ckpts=-1,
save_best=True,
interval=save_epoch_intervals))
custom_hooks = [
dict(type='EMAHook',
ema_type='ExpMomentumEMA',
momentum=0.0001,
update_buffers=True,
strict_load=False,
priority=49),
dict(type='mmdet.PipelineSwitchHook',
switch_epoch=max_epochs - close_mosaic_epochs,
switch_pipeline=train_pipeline_stage2)
]
train_cfg = dict(max_epochs=max_epochs,
val_interval=1,
dynamic_intervals=[((max_epochs - close_mosaic_epochs),
base.val_interval_stage2)])
optim_wrapper = dict(optimizer=dict(
delete=True,
type='SGD',
lr=base_lr,
momentum=0.937,
nesterov=True,
weight_decay=weight_decay,
batch_size_per_gpu=train_batch_size_per_gpu),
paramwise_cfg=dict(
custom_keys={
'backbone.text_model': dict(lr_mult=0.01),
'logit_scale': dict(weight_decay=0.0)
}),
constructor='YOLOWv5OptimizerConstructor')

evaluation settings

val_evaluator = dict(delete=True,
type='mmdet.CocoMetric',
proposal_nums=(100, 1, 10),
ann_file=r'C:\Users\lenovo\Desktop\self_coco\val.json',
metric='bbox')
`

This is my console output：
12/10 16:18:08 - mmengine - INFO - Epoch(train) [1][ 50/240] base_lr: 1.0000e-03 lr: 4.9000e-05 eta: 1 day, 0:42:29 time: 0.7416 data_time: 0.4533 memory: 3570 grad_norm: nan loss: 13.6729 loss_cls: 7.2828 loss_bbox: 3.7713 loss_dfl: 2.6188 12/10 16:18:14 - mmengine - INFO - Epoch(train) [1][100/240] base_lr: 1.0000e-03 lr: 9.9000e-05 eta: 14:12:23 time: 0.1115 data_time: 0.0060 memory: 1846 grad_norm: 755.3231 loss: 13.5571 loss_cls: 7.1307 loss_bbox: 3.8186 loss_dfl: 2.6078 12/10 16:18:19 - mmengine - INFO - Epoch(train) [1][150/240] base_lr: 1.0000e-03 lr: 1.4900e-04 eta: 10:45:13 time: 0.1159 data_time: 0.0052 memory: 1846 grad_norm: inf loss: 13.8473 loss_cls: 7.8785 loss_bbox: 3.5179 loss_dfl: 2.4508 12/10 16:18:25 - mmengine - INFO - Epoch(train) [1][200/240] base_lr: 1.0000e-03 lr: 1.9900e-04 eta: 9:02:49 time: 0.1184 data_time: 0.0071 memory: 1842 grad_norm: 654.9941 loss: 15.0733 loss_cls: 7.4990 loss_bbox: 4.4653 loss_dfl: 3.1090 12/10 16:18:30 - mmengine - INFO - Exp name: yolo_world_v2_l_vlpan_bn_sgd_1e-3_40e_8gpus_finetune_coco_20241210_161716 12/10 16:18:38 - mmengine - INFO - Epoch(val) [1][50/60] eta: 0:00:01 time: 0.1562 data_time: 0.1013 memory: 3409 12/10 16:18:39 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.02s). Accumulating evaluation results... DONE (t=0.00s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 12/10 16:18:39 - mmengine - INFO - bbox_mAP_copypaste: -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 12/10 16:18:39 - mmengine - INFO - Epoch(val) [1][60/60] coco/bbox_mAP: -1.0000 coco/bbox_mAP_50: -1.0000 coco/bbox_mAP_75: -1.0000 coco/bbox_mAP_s: -1.0000 coco/bbox_mAP_m: -1.0000 coco/bbox_mAP_l: -1.0000 data_time: 0.0844 time: 0.1357