YOLOV5白皮书-第Y2周：训练自己的数据集
我的环境：
•语言环境：Python3.9
•编译器：PyCharm
•深度学习环境：
。torch= = 1.10.0+cu113
。torchvision ==0.11.1 +cu113
•显卡：GeForce RTX 3060
,可供学习使用数据集：水果检测
一、准备自己的数据
二、运行 split_train_val.py 文件
ImageSets文件夹下面有个Main子文件夹，其下面存放了 train.txt、val.txt、test.txt和 trainval.txt四个文件，它们是通过split_train_val.py文件来生成的。
split_train_val.py文件的位置：
split_train_val.py 的内容如下:
# 划分train、test、val文件
import os
import random
import argparse
parser = argparse.ArgumentParser()
# xml文件的地址，根据自己的数据进行修改 xml一般存放在Annotations下
parser.add_argument('--xml_path', default='annotations', type=str, help='input txt label path')
# 数据集的划分，地址选择自己数据下的ImageSets/Main
parser.add_argument('--txt_path', default='Imagesets/Main', type=str, help='output txt label path')
opt = parser.parse_args()
trainval_percent = 1
train_percent = 0.9
xmlfilepath = opt.xml_path
txtsavepath = opt.txt_path
total_xml = os.listdir(xmlfilepath)
if not os.path.exists(txtsavepath):
os.makedirs(txtsavepath)
num = len(total_xml)
list_index = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list_index, tv)
train = random.sample(trainval, tr)
file_trainval = open(txtsavepath + '/trainval.txt', 'w')
file_test = open(txtsavepath + '/test.txt', 'w')
file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')
for i in list_index:
name = total_xml[i][:-4] + '\n'
if i in trainval:
file_trainval.write(name)
if i in train:
file_train.write(name)
else:
file_val.write(name)
else:
file_test.write(name)
file_trainval.close()
file_train.close()
file_val.close()
file_test.close()
运行 split_train_val.py 文件后你将得至train.txt、val.txt、test.txt 和 trainval.txt 四 个文件，结果如下：
注：如修改数据集中训练集.验证集.测试集的比例，请参考:
三、生成 train.txt test.txt val.txt 文件
我们要生成的文件位置
现在我们需要的是voc_label.py文件。
注意：这里的classes = [“banana”, “snake fruit”, “dragon fruit”, “pineapple”] # 改成自己的类别
import xml.etree.ElementTree as ET
import os
from os import getcwd
sets = ['train', 'val', 'test']
classes = ["banana", "snake fruit", "dragon fruit", "pineapple"] # 改成自己的类别
abs_path = os.getcwd()
print(abs_path)
def convert(size, box):
dw = 1. / (size[0])
dh = 1. / (size[1])
x = (box[0] + box[1]) / 2.0 - 1
y = (box[2] + box[3]) / 2.0 - 1
w = box[1] - box[0]
h = box[3] - box[2]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
return x, y, w, h
def convert_annotation(image_id):
in_file = open('./annotations/%s.xml' % (image_id), encoding='UTF-8')
out_file = open('./labels/%s.txt' % (image_id), 'w')
tree = ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult) == 1:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
float(xmlbox.find('ymax').text))
b1, b2, b3, b4 = b
# 标注越界修正
if b2 > w:
b2 = w
if b4 > h:
b4 = h
b = (b1, b2, b3, b4)
bb = convert((w, h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
wd = getcwd()
for image_set in sets:
if not os.path.exists('labels/'):
os.makedirs('labels/')
image_ids = open('./ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
list_file = open('./%s.txt' % (image_set),'w')
for image_id in image_ids:
list_file.write(abs_path + '/images/%s.png\n' % (image_id))
convert_annotation(image_id)
list_file.close()
运行voc_label.py文件，你将会得到train.txt、test.txt、val.txt三个文件, 文件内容如下
val.txt
注意： 我这里是乱码，因为我用了中文目录，但不影响运行
四、创建ab.yaml文件
这个文件名是我随意取的，这个可以做出改变的，ab.yaml文件的位置如下:
我的ab.yaml文件内容如下:
train: ./paper_data/train.txt
val: ./paper_data/val.txt
nc: 4
names: ["banana", "snake fruit", "dragon fruit", "pineapple"]
注意，这里的names要改为自己的类别。同时，nc要修改为类别个数。
五、开始用自己的数据集训练模型
输入命令：
python train.py --img 900 --batch 2 --epoch 100 --data paper_data/ab.yaml --cfg models/yolov5s.yaml --weights yolov5s.pt
输出结果：
train: weights=yolov5s.pt, cfg=models/yolov5s.yaml, data=paper_data/ab.yaml, hyp=data\hyps\hyp.scratch-low.yaml, epochs=100, batch_size=2, imgsz=900, rect=False, resume=False, nosave=F
alse, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=None, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False,
workers=8, project=runs\train, name=exp, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, seed=0, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest
github: skipping check (not a git repository), for updates see https://github.com/ultralytics/yolov5
YOLOv5 2022-12-7 Python-3.9.15 torch-1.13.0+cpu CPU
hyperparameters: lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0
, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0
ClearML: run 'pip install clearml' to automatically track, visualize and remotely train YOLOv5 in ClearML
Comet: run 'pip install comet_ml' to automatically track and visualize YOLOv5 runs in Comet
TensorBoard: Start with 'tensorboard --logdir runs\train', view at http://localhost:6006/
Overriding model.yaml nc=80 with nc=4
from n params module arguments
0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2]
1 -1 1 18560 models.common.Conv [32, 64, 3, 2]
2 -1 1 18816 models.common.C3 [64, 64, 1]
3 -1 1 73984 models.common.Conv [64, 128, 3, 2]
4 -1 2 115712 models.common.C3 [128, 128, 2]
5 -1 1 295424 models.common.Conv [128, 256, 3, 2]
6 -1 3 625152 models.common.C3 [256, 256, 3]
7 -1 1 1180672 models.common.Conv [256, 512, 3, 2]
8 -1 1 1182720 models.common.C3 [512, 512, 1]
9 -1 1 656896 models.common.SPPF [512, 512, 5]
10 -1 1 131584 models.common.Conv [512, 256, 1, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 models.common.Concat [1]
13 -1 1 361984 models.common.C3 [512, 256, 1, False]
14 -1 1 33024 models.common.Conv [256, 128, 1, 1]
15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
16 [-1, 4] 1 0 models.common.Concat [1]
17 -1 1 90880 models.common.C3 [256, 128, 1, False]
18 -1 1 147712 models.common.Conv [128, 128, 3, 2]
19 [-1, 14] 1 0 models.common.Concat [1]
20 -1 1 296448 models.common.C3 [256, 256, 1, False]
21 -1 1 590336 models.common.Conv [256, 256, 3, 2]
22 [-1, 10] 1 0 models.common.Concat [1]
23 -1 1 1182720 models.common.C3 [512, 512, 1, False]
24 [17, 20, 23] 1 24273 models.yolo.Detect [4, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
YOLOv5s summary: 214 layers, 7030417 parameters, 7030417 gradients, 16.0 GFLOPs
Transferred 308/349 items from yolov5s.pt
WARNING --img-size 900 must be multiple of max stride 32, updating to 928
optimizer: SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 60 weight(decay=0.0005), 60 bias
train: Scanning E:\doc\1.学院\3.学习培训\21.365深度学习训练营\y2\yolov5-master\paper_data\train... 180 images, 0 backgrounds, 0 corrupt: 100%|██████████| 180/180 [00:06<00:00, 28.48it
train: WARNING Cache directory E:\doc\1.\3.\21.365\y2\yolov5-master\paper_data is not writeable: [WinError 183] : 'E:\\doc\\1.\\3.\\21.365\\y2\\yolov5-master\\paper_data\\train.cache.npy' -> 'E:\\doc\\1.\\3.\\21.365\\y2\\yolov5-master\\paper_data\\train.cache'
val: Scanning E:\doc\1.学院\3.学习培训\21.365深度学习训练营\y2\yolov5-master\paper_data\val... 20 images, 0 backgrounds, 0 corrupt: 100%|██████████| 20/20 [00:06<00:00, 3.07it/s]
val: New cache created: E:\doc\1.\3.\21.365\y2\yolov5-master\paper_data\val.cache
AutoAnchor: 4.82 anchors/target, 1.000 Best Possible Recall (BPR). Current anchors are a good fit to dataset
Plotting labels to runs\train\exp15\labels.jpg...
Image sizes 928 train, 928 val
Using 2 dataloader workers
Logging results to runs\train\exp15
Starting training for 100 epochs...
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
0/99 0G 0.1211 0.0558 0.05001 9 928: 0%| | 0/90 [00:02<?, ?it/s]WARNING TensorBoard graph visualization failure Sizes of tensors must match except in dimension 1. Expected size 58 but got size 57 for tensor number 1 in the list.
0/99 0G 0.1056 0.0601 0.04505 11 928: 100%|██████████| 90/90 [03:18<00:00, 2.20s/it]
Class Images Instances P R mAP50 mAP50-95: 20%|██ | 1/5 [00:01<00:05, 1.32s/it]WARNING NMS time limit 0.700s exceeded
Class Images Instances P R mAP50 mAP50-95: 40%|████ | 2/5 [00:03<00:05, 1.72s/it]WARNING NMS time limit 0.700s exceeded
Class Images Instances P R mAP50 mAP50-95: 60%|██████ | 3/5 [00:05<00:03, 1.86s/it]WARNING NMS time limit 0.700s exceeded
Class Images Instances P R mAP50 mAP50-95: 80%|████████ | 4/5 [00:07<00:01, 1.85s/it]WARNING NMS time limit 0.700s exceeded
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:09<00:00, 1.81s/it]
all 20 60 0 0 0 0
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
1/99 0G 0.08738 0.06344 0.03942 5 928: 100%|██████████| 90/90 [02:56<00:00, 1.97s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.19s/it]
all 20 60 0.00934 0.912 0.0419 0.00868
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
2/99 0G 0.07767 0.06266 0.03367 13 928: 100%|██████████| 90/90 [02:57<00:00, 1.97s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:06<00:00, 1.30s/it]
all 20 60 0.00679 0.62 0.00761 0.00173
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
3/99 0G 0.07745 0.05135 0.02945 17 928: 100%|██████████| 90/90 [02:57<00:00, 1.97s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.06s/it]
all 20 60 0.0218 0.921 0.0483 0.0114
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
4/99 0G 0.07231 0.04728 0.02629 7 928: 100%|██████████| 90/90 [02:57<00:00, 1.97s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.05s/it]
all 20 60 0.152 0.62 0.196 0.0655
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
5/99 0G 0.0698 0.04278 0.02369 18 928: 100%|██████████| 90/90 [02:57<00:00, 1.97s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.04s/it]
all 20 60 0.259 0.588 0.367 0.155
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
6/99 0G 0.06335 0.03941 0.02255 13 928: 100%|██████████| 90/90 [02:57<00:00, 1.97s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.03s/it]
all 20 60 0.237 0.604 0.443 0.215
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
7/99 0G 0.05831 0.03681 0.02154 7 928: 100%|██████████| 90/90 [02:57<00:00, 1.97s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.03s/it]
all 20 60 0.46 0.6 0.409 0.146
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
8/99 0G 0.06084 0.03499 0.02064 16 928: 100%|██████████| 90/90 [02:55<00:00, 1.95s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.02s/it]
all 20 60 0.743 0.6 0.676 0.29
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
9/99 0G 0.05665 0.03497 0.01896 10 928: 100%|██████████| 90/90 [02:58<00:00, 1.98s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.03s/it]
all 20 60 0.591 0.779 0.808 0.313
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
10/99 0G 0.05506 0.03503 0.01872 18 928: 100%|██████████| 90/90 [02:56<00:00, 1.96s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.03s/it]
all 20 60 0.688 0.818 0.854 0.376
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
11/99 0G 0.051 0.03416 0.01733 15 928: 100%|██████████| 90/90 [02:56<00:00, 1.96s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.02s/it]
all 20 60 0.64 0.683 0.836 0.359
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
12/99 0G 0.05272 0.0319 0.01605 14 928: 100%|██████████| 90/90 [02:56<00:00, 1.96s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.03s/it]
all 20 60 0.728 0.841 0.873 0.5
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
13/99 0G 0.04572 0.03122 0.01514 13 928: 100%|██████████| 90/90 [03:00<00:00, 2.01s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:05<00:00, 1.05s/it]
all 20 60 0.525 0.792 0.773 0.417
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
14/99 0G 0.04438 0.03155 0.01424 23 928: 100%|██████████| 90/90 [02:55<00:00, 1.95s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.07it/s]
all 20 60 0.561 0.904 0.894 0.433
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
15/99 0G 0.04381 0.02858 0.01276 23 928: 100%|██████████| 90/90 [02:41<00:00, 1.80s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.00it/s]
all 20 60 0.627 0.834 0.851 0.475
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
16/99 0G 0.04439 0.02928 0.01195 5 928: 100%|██████████| 90/90 [02:43<00:00, 1.82s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.05it/s]
all 20 60 0.774 0.841 0.885 0.507
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
17/99 0G 0.04548 0.02568 0.009813 14 928: 100%|██████████| 90/90 [02:41<00:00, 1.80s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.07it/s]
all 20 60 0.684 0.93 0.881 0.557
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
18/99 0G 0.04013 0.02926 0.01151 11 928: 100%|██████████| 90/90 [02:41<00:00, 1.80s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.08it/s]
all 20 60 0.851 0.944 0.959 0.658
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
19/99 0G 0.03894 0.02951 0.008872 7 928: 100%|██████████| 90/90 [02:41<00:00, 1.79s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.08it/s]
all 20 60 0.928 0.954 0.986 0.636
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
20/99 0G 0.03955 0.02666 0.00873 8 928: 100%|██████████| 90/90 [02:41<00:00, 1.79s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.06it/s]
all 20 60 0.87 0.957 0.981 0.536
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
21/99 0G 0.04063 0.02842 0.007628 10 928: 100%|██████████| 90/90 [02:41<00:00, 1.79s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.08it/s]
all 20 60 0.928 0.944 0.982 0.546
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
22/99 0G 0.0395 0.02729 0.007109 11 928: 100%|██████████| 90/90 [02:40<00:00, 1.79s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.08it/s]
all 20 60 0.906 0.949 0.977 0.587
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
23/99 0G 0.03845 0.02439 0.0067 9 928: 100%|██████████| 90/90 [02:40<00:00, 1.79s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.08it/s]
all 20 60 0.792 0.928 0.948 0.618
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
24/99 0G 0.03753 0.02705 0.006873 13 928: 100%|██████████| 90/90 [02:45<00:00, 1.84s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.875 0.962 0.976 0.671
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
25/99 0G 0.03344 0.02463 0.006468 10 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.849 0.968 0.96 0.644
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
26/99 0G 0.03553 0.02689 0.00649 9 928: 100%|██████████| 90/90 [02:47<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.75 0.945 0.899 0.623
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
27/99 0G 0.03316 0.02471 0.005116 12 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.797 0.971 0.965 0.695
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
28/99 0G 0.0344 0.02363 0.00567 15 928: 100%|██████████| 90/90 [02:47<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.795 0.952 0.961 0.641
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
29/99 0G 0.03334 0.02373 0.00489 11 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.921 0.971 0.984 0.713
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
30/99 0G 0.03192 0.02439 0.006354 5 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.945 0.988 0.988 0.706
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
31/99 0G 0.03468 0.02568 0.006189 7 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.956 0.984 0.986 0.717
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
32/99 0G 0.03359 0.02325 0.004633 13 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.9 0.98 0.972 0.729
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
33/99 0G 0.03396 0.02579 0.005256 14 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.969 0.974 0.985 0.685
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
34/99 0G 0.03294 0.0237 0.004858 17 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.859 0.977 0.983 0.746
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
35/99 0G 0.03106 0.02374 0.004119 24 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.974 0.974 0.987 0.72
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
36/99 0G 0.03063 0.02372 0.003885 9 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.988 0.994 0.995 0.719
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
37/99 0G 0.03069 0.02239 0.003554 7 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.987 0.999 0.995 0.722
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
38/99 0G 0.0306 0.02406 0.004276 17 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.986 0.987 0.995 0.671
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
39/99 0G 0.03037 0.02309 0.004153 7 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.988 0.988 0.995 0.788
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
40/99 0G 0.0274 0.02272 0.003755 12 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.989 0.989 0.995 0.77
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
41/99 0G 0.02877 0.0221 0.0041 6 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.02it/s]
all 20 60 0.987 0.985 0.995 0.761
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
42/99 0G 0.02875 0.02292 0.003007 14 928: 100%|██████████| 90/90 [02:48<00:00, 1.88s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.987 0.966 0.992 0.715
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
43/99 0G 0.02863 0.02398 0.003227 9 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.961 0.996 0.994 0.731
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
44/99 0G 0.02858 0.02116 0.003865 21 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.97 0.993 0.995 0.797
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
45/99 0G 0.02632 0.02006 0.003483 7 928: 100%|██████████| 90/90 [02:48<00:00, 1.88s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.847 0.957 0.99 0.776
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
46/99 0G 0.0271 0.02305 0.003096 9 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.973 0.994 0.995 0.751
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
47/99 0G 0.0274 0.02358 0.003008 9 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.982 0.993 0.995 0.773
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
48/99 0G 0.02708 0.02264 0.0036 9 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.976 0.994 0.995 0.778
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
49/99 0G 0.02597 0.02265 0.002325 17 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.981 0.992 0.995 0.798
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
50/99 0G 0.02592 0.02098 0.003093 10 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.946 0.974 0.991 0.8
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
51/99 0G 0.02549 0.01992 0.003059 7 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.98 0.975 0.993 0.765
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
52/99 0G 0.02612 0.02144 0.003005 8 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.984 0.992 0.995 0.763
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
53/99 0G 0.02559 0.02263 0.002611 13 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.97 0.988 0.995 0.821
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
54/99 0G 0.02491 0.02004 0.002507 16 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.976 0.992 0.995 0.789
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
55/99 0G 0.02476 0.02248 0.003541 11 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.983 0.994 0.995 0.835
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
56/99 0G 0.02416 0.02057 0.002543 7 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.969 0.981 0.993 0.782
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
57/99 0G 0.0247 0.02049 0.003057 9 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.966 0.982 0.994 0.806
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
58/99 0G 0.02251 0.02066 0.002434 14 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.983 0.994 0.995 0.758
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
59/99 0G 0.02361 0.0211 0.002272 8 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.984 0.997 0.995 0.775
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
60/99 0G 0.02351 0.01995 0.002283 14 928: 100%|██████████| 90/90 [02:48<00:00, 1.88s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.02it/s]
all 20 60 0.985 0.995 0.995 0.818
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
61/99 0G 0.02341 0.02245 0.003217 14 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.976 0.996 0.995 0.821
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
62/99 0G 0.02281 0.02112 0.001963 10 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.979 0.992 0.995 0.811
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
63/99 0G 0.02321 0.02098 0.002418 13 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.98 0.993 0.995 0.819
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
64/99 0G 0.02302 0.02106 0.002212 9 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.982 0.976 0.993 0.83
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
65/99 0G 0.0231 0.021 0.002807 8 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.977 0.993 0.995 0.81
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
66/99 0G 0.02257 0.02045 0.001738 12 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.985 0.989 0.995 0.829
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
67/99 0G 0.02163 0.01999 0.001787 7 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.985 0.99 0.995 0.811
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
68/99 0G 0.02155 0.02035 0.002539 6 928: 100%|██████████| 90/90 [02:48<00:00, 1.88s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.987 0.993 0.995 0.832
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
69/99 0G 0.02169 0.01939 0.002132 11 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.987 0.992 0.995 0.849
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
70/99 0G 0.02087 0.01953 0.002244 6 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.987 0.995 0.995 0.838
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
71/99 0G 0.02074 0.01855 0.002009 7 928: 100%|██████████| 90/90 [02:47<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.987 0.994 0.995 0.848
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
72/99 0G 0.01967 0.01967 0.001669 12 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.984 0.983 0.984 0.83
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
73/99 0G 0.0208 0.0202 0.001607 7 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.983 0.979 0.987 0.831
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
74/99 0G 0.01984 0.0187 0.00194 10 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.983 0.979 0.986 0.829
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
75/99 0G 0.02075 0.01917 0.001813 9 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.985 0.991 0.995 0.835
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
76/99 0G 0.02018 0.01926 0.001293 14 928: 100%|██████████| 90/90 [02:47<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.989 0.992 0.995 0.857
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
77/99 0G 0.02065 0.01968 0.001775 11 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.989 0.989 0.995 0.846
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
78/99 0G 0.01955 0.01961 0.001545 10 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.987 0.992 0.995 0.846
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
79/99 0G 0.01911 0.01881 0.00171 10 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.988 0.992 0.995 0.846
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
80/99 0G 0.01912 0.01777 0.001713 13 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.985 0.994 0.995 0.831
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
81/99 0G 0.02033 0.02024 0.002025 18 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.986 0.991 0.995 0.84
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
82/99 0G 0.01905 0.01925 0.001558 10 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.989 0.992 0.995 0.836
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
83/99 0G 0.01889 0.01882 0.001722 15 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.988 0.99 0.995 0.845
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
84/99 0G 0.01813 0.01962 0.003011 6 928: 100%|██████████| 90/90 [02:47<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.02it/s]
all 20 60 0.987 0.995 0.995 0.858
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
85/99 0G 0.01877 0.01951 0.001948 6 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.987 0.998 0.995 0.853
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
86/99 0G 0.01812 0.01907 0.001587 18 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.987 0.997 0.995 0.846
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
87/99 0G 0.0181 0.01792 0.002081 15 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.987 0.998 0.995 0.867
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
88/99 0G 0.01702 0.01824 0.001836 8 928: 100%|██████████| 90/90 [02:47<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.02it/s]
all 20 60 0.988 0.999 0.995 0.868
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
89/99 0G 0.01761 0.01849 0.001372 14 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.99 0.998 0.995 0.863
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
90/99 0G 0.01774 0.01732 0.001869 15 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.987 0.997 0.995 0.871
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
91/99 0G 0.01756 0.01916 0.001809 15 928: 100%|██████████| 90/90 [02:47<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.99 0.996 0.995 0.869
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
92/99 0G 0.0179 0.01904 0.001088 11 928: 100%|██████████| 90/90 [02:47<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.99 0.999 0.995 0.865
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
93/99 0G 0.01724 0.01819 0.001318 7 928: 100%|██████████| 90/90 [02:47<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.04it/s]
all 20 60 0.989 0.995 0.995 0.866
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
94/99 0G 0.0175 0.01806 0.001875 7 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.988 0.998 0.995 0.866
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
95/99 0G 0.01682 0.01935 0.001596 15 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.988 0.999 0.995 0.876
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
96/99 0G 0.01717 0.01848 0.001317 14 928: 100%|██████████| 90/90 [02:47<00:00, 1.86s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.984 0.997 0.995 0.877
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
97/99 0G 0.01627 0.01685 0.002426 12 928: 100%|██████████| 90/90 [02:48<00:00, 1.87s/it]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.03it/s]
all 20 60 0.988 0.997 0.995 0.87
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 5/5 [00:04<00:00, 1.13it/s]
all 20 60 0.986 0.997 0.995 0.878
banana 20 16 0.992 1 0.995 0.933
snake fruit 20 20 0.99 1 0.995 0.79
dragon fruit 20 11 0.962 1 0.995 0.912
pineapple 20 13 1 0.988 0.995 0.876
Results saved to runs\train\exp15