Open muhammadhammadjamil opened 11 months ago
can you provide the source dataset ucf24 ?I can not download that. Here is my email 2805211350@qq.com. Thank you.
你好,请问,请问为什么进行DDP训练损失异常的大,但是进行单卡训练没有这种情况。谢谢解答
你好,请问,请问为什么进行DDP训练损失异常的大,但是进行单卡训练没有这种情况。谢谢解答 你好,请问你的DDP训练的时候,是不是多张卡都有用到,我这里使用的服务器是四张显卡的,但是使用官方提供的ddp命令训练只使用到了一张卡,你有出现这种情况吗
@yjh0410 can you provide guildline how to train YOWOv2 on my own dataset here is alteration i make on dataset config file 'ava_v2.2': {
dataset
Model Config: YOWO_V2_LARGE Finished loading image paths from: /home/ubuntu/hammad/YOWOv2/config/frame/train.csv Traceback (most recent call last): File "train.py", line 330, in
train()
File "train.py", line 156, in train
dataset, evaluator, num_classes = build_dataset(d_cfg, args, is_train=True)
File "/home/ubuntu/hammad/YOWOv2/utils/misc.py", line 67, in build_dataset
dataset = AVA_Dataset(
File "/home/ubuntu/hammad/YOWOv2/dataset/ava.py", line 49, in init
self._load_data()
File "/home/ubuntu/hammad/YOWOv2/dataset/ava.py", line 65, in _load_data
boxes_and_labels = ava_helper.load_boxes_and_labels(
File "/home/ubuntu/hammad/YOWOv2/dataset/ava_helper.py", line 134, in load_boxes_and_labels
if box_key not in all_boxes[video_name][frame_sec]:
KeyError: 0