Deep-learning999

TypeError: create_dataset() missing 1 required positional argument: 'test_path'

1

!python main.py --config config/dlhlp/asr_dlhlp.yaml 

Video inference is not satisfactory

2

Thanks, a very good project. I used a single gpuDemo.py to infer the video and the effect video address [output.mp4](https://youtu.be/ivzC8f-0iY4) . However, the personnel detection frame is very jittery and...

谢谢分享，但源码好像并不完整

2

像注意力模型week2源码和数据集就有1.7gb

Why is the cpu only 1.2fps in kapao_s_coco.pt

2

This is a screenshot of the generated video, why is the cpu so slow and can't reach 10fp  s

How to modify pit when pit is prohibited

For video inference, what is the fastest fps

1

For video inference, what is the fastest fps

About inferring speed

1

It is a novel method that pays more attention to real-time speed. Excuse me, compared with other methods, detection, instance segmentation, and human pose inference speed can achieve real-time, such...

KeyError: 'nkpt'

1

!python pose-estimate.py --source "football1.mp4" --device 0 Optimizer stripped from yolov7-w6-person.pt, 280.0MB Fusing layers... IDetect.fuse Frame 0 Processing --------------------------------------------------------------------------- KeyError Traceback (most recent call last) Input In [7], in () 164...

from sleap.nn.inference import TopdownPredictor Error

1

from sleap.nn.inference import TopdownPredictor,Tracker predictor = TopdownPredictor.from_trained_models( centroid_model_path="C:/Users/designlion/Documents/openvino_notebooks/notebooks/0000001sleap-mit-tutorial/sleap-mit-tutorial-master/models/baseline_model.centroids", confmap_model_path="C:/Users/designlion/Documents/openvino_notebooks/notebooks/0000001sleap-mit-tutorial/sleap-mit-tutorial-master/models/baseline_model.topdown", ) predictor.tracker = Tracker.make_tracker_by_name(tracker="simple") ImportError Traceback (most recent call last) Input In [2], in () ----> 1 from sleap.nn.inference import TopdownPredictor,Tracker...

!python train.py --data data/coco_kpts.yaml --cfg cfg/yolov7-w6-pose.yaml --weights weights/yolov7-w6-person.pt --batch-size 128 --img 960 --kpt-label --sync-bn --device 0 --name yolov7-w6-pose --hyp data/hyp.pose.yaml Namespace(adam=False, artifact_alias='latest', batch_size=128, bbox_interval=-1, bucket='', cache_images=False, cfg='cfg/yolov7-w6-pose.yaml', data='data/coco_kpts.yaml', device='0', entity=None,...