YOLOv4-pytorch
YOLOv4-pytorch copied to clipboard
argusswift
成功复现了该厂库的代码，大家可以贴出自己遇到的问题，希望对家有帮助，最后感谢作者。
IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed我跑训练时出现这个问题
IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed我跑训练时出现这个问题 麻烦贴出你的报错代码，这样有助于找出问题所在。
你可以把问题帖出来。
发自我的iPhone
------------------ 原始邮件 ------------------ 发件人: seven060422 @.> 发送时间: 2021年4月15日 20:24 收件人: argusswift/YOLOv4-pytorch @.> 抄送: yichanshiwoa @.>, Author @.> 主题: 回复：[argusswift/YOLOv4-pytorch] 成功复现了该厂库的代码，大家可以贴出自己遇到的问题，希望对家有帮助，最后感谢作者。 (#164)
请问你能发一份源码或者写一个复现的博客嘛
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
你是不是预加载权重了，你可以不预加载权重会出现损失函数。
发自我的iPhone
------------------ 原始邮件 ------------------ 发件人: Tomas Yang @.> 发送时间: 2021年4月21日 16:49 收件人: argusswift/YOLOv4-pytorch @.> 抄送: yichanshiwoa @.>, Author @.> 主题: 回复：[argusswift/YOLOv4-pytorch] 成功复现了该厂库的代码，大家可以贴出自己遇到的问题，希望对家有帮助，最后感谢作者。 (#164)
训练的时候为什么学习率都是0啊？
显示精度的问题，建议设置为输出小数点后8位
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
数据集多大
发自我的iPhone
------------------ 原始邮件 ------------------ 发件人: sjfei @.> 发送时间: 2021年5月13日 12:37 收件人: argusswift/YOLOv4-pytorch @.> 抄送: yichanshiwoa @.>, Author @.> 主题: 回复：[argusswift/YOLOv4-pytorch] 成功复现了该厂库的代码，大家可以贴出自己遇到的问题，希望对家有帮助，最后感谢作者。 (#164)
yolov4训练自己数据集损失一直出现nan
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
这是什么情况，路径下有文件，却显示错误。
[2021-05-18 16:41:16,036]-[train.py line:279]:===== Validate ===== [2021-05-18 16:41:16,036]-[train.py line:281]:val img size is 416 Traceback (most recent call last): File "C:/GitHub/YOLOv4-pytorch/train.py", line 346, in <module> fp_16=opt.fp_16, File "C:/GitHub/YOLOv4-pytorch/train.py", line 284, in train self.yolov4, showatt=self.showatt File "C:\GitHub\YOLOv4-pytorch\eval\evaluator.py", line 44, in APs_voc with open(img_inds_file, "r") as f: FileNotFoundError: [Errno 2] No such file or directory: 'C:\\GitHub\\YOLOv4-pytorch\\data\\VOCtest-2007\\VOCdevkit\\VOC2007\\ImageSets\\Main\\test.txt'
其中config文件 `MODEL_TYPE = { "TYPE": "YOLOv4" } # YOLO type:YOLOv4, Mobilenet-YOLOv4 or Mobilenetv3-YOLOv4
CONV_TYPE = {"TYPE": "DO_CONV"} # conv type:DO_CONV or GENERAL
ATTENTION = {"TYPE": "NONE"} # attention type:SEnet、CBAM or NONE
train
TRAIN = { "DATA_TYPE": "VOC", # DATA_TYPE: VOC ,COCO or Customer "TRAIN_IMG_SIZE": 416, "AUGMENT": True, "BATCH_SIZE": 2, "MULTI_SCALE_TRAIN": True, "IOU_THRESHOLD_LOSS": 0.5, "YOLO_EPOCHS": 50, "Mobilenet_YOLO_EPOCHS": 120, "NUMBER_WORKERS": 6, "MOMENTUM": 0.9, "WEIGHT_DECAY": 0.0005, "LR_INIT": 1e-4, "LR_END": 1e-6, "WARMUP_EPOCHS": 2, # or None "showatt": False }
val
VAL = { "TEST_IMG_SIZE": 416, "BATCH_SIZE": 2, "NUMBER_WORKERS": 6, "CONF_THRESH": 0.005, "NMS_THRESH": 0.45, "MULTI_SCALE_VAL": False, "FLIP_VAL": False, "Visual": True, "showatt": False } VOC_DATA = { "NUM": 20, "CLASSES": [ "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor", ], }`
运行eval_voc.py后，生成的output文件内容为空，生成的utils\results\images\detections_one_by_one下为空，可以得到pred_result文件结果，但是一张图片对应多个box。请问怎么解决？
