pjjjjjj

Cannot read properties of null (reading 'default')

4

**Describe the issue**: It started out working properly, and then suddenly the problem arose，But the first trail is still functioning   **Environment**: - NNI version:2.6.1 - Training service (local|remote|pai|aml|etc):remote...

total loss 很大 ，并且下降的特别慢，跪求各位大佬指点

10

我使用的是yoloV4，训练的自己的数据集 

runing train_voc.py TypeError forward() takes 2 positional arguments but 11 were given File "G:\GitHub_work\Yolo-v2-pytorch\train_voc.py", line 95, in train writer.add_graph(model.cpu(), torch.rand(opt.batch_size, 3, opt.image_size, opt.image_size)) File "G:\GitHub_work\Yolo-v2-pytorch\train_voc.py", line 186, in train(opt) help...

Expected 4-dimensional input for 4-dimensional weight 64 3 7 7, but got 3-dimensional input of size [3, 448, 448] instead 增加了下面一行代码 ，出现了更多的问题。感谢感谢!!! def predict_gpu(model,image_name,root_path=''): result = [] image = cv2.imread(root_path+image_name)...

ple可以只用于单任务吗

1

作者您好，看到源码中限制了任务的数量，必须要大于1，可以修改这里的源码，用于单任务吗 [ple源码](https://github.com/shenweichen/DeepCTR/blob/master/deepctr/models/multitask/ple.py) ` num_tasks = len(task_names) if num_tasks

训练250epoch，loss特别大，不知道是什么原因

1

 下面是我的配置  谢谢作者的答复

Thanks to the author for sharing, when I execute retrain

2

Thanks to the author for sharing, when I execute retrain, I will report an error. After checkinging the code I found that want to use the .cuda() method to move...

reg loss can not fall

5

Hello author, I trained VisDrone dataset and loss can't fall. Can you take a look at it for me, thank you  train：python train.py -c 0 -p visdrone2019 --batch_size 8...