leandro-svg / yolov7_segmentation_tensorrt Goto Github PK

Hello, i would like to know if a tiny version for segmentation exists? I have used TensorRT to optimize my model but i would like to have a little more of speed.
Thanks

C:\Users\16550.conda\envs\yolo1\python.exe E:\yolo\Yolov7_Segmentation_Tensorrt-main\segment_image.py
Loading E:\yolo\Yolov7_Segmentation_Tensorrt-main\yolov7_fp16.engine for TensorRT inference...
[04/11/2023-20:33:54] [TRT] [I] [MemUsageChange] Init CUDA: CPU +350, GPU +0, now: CPU 10896, GPU 912 (MiB)
Deserializing engine...
[04/11/2023-20:33:54] [TRT] [I] Loaded engine size: 89 MiB
[04/11/2023-20:33:54] [TRT] [W] Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
[04/11/2023-20:33:54] [TRT] [I] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +88, now: CPU 0, GPU 88 (MiB)
[04/11/2023-20:33:54] [TRT] [I] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +133, now: CPU 0, GPU 221 (MiB)
Engine Loaded.
TensorRT inference begins !
0%| | 0/17 [00:00<?, ?it/s][ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('.'): can't open/read file: check file path/integrity
0%| | 0/17 [00:00<?, ?it/s]
Traceback (most recent call last):
File "E:\yolo\Yolov7_Segmentation_Tensorrt-main\segment_image.py", line 261, in
origin_img = pred.inference(arg_input)
File "E:\yolo\Yolov7_Segmentation_Tensorrt-main\segment_image.py", line 184, in inference
real_image = img_.copy()
AttributeError: 'NoneType' object has no attribute 'copy'

Process finished with exit code 1