-
您好！
我在执行python data_provider/lanenet_data_feed_pipline.py --dataset_dir./data/training_data_example/training --tfrecords_dir./data/training_data_example/training/tfrecords 这段时会出现以下错误
数据库资料位置 tfrecor…
-
I change my dataset to Tusimple format, and then run train.py, but error like this:
"RuntimeError: copy_if failed to synchronize: cudaErrorAssert: device-side assert triggered"
please help me to f…
-
I trained a model on CULane, using ResNet-34 as the backbone, and the model's F1 on the test set was only 70.5. The only modification I did was changing the backbone line in the config file to `backbo…
-
Hello, i'm trying to run demo.py with my own data,i already changed the path to the images and datasets are recognizing my images and storaging them, but i getting error
```shell
$ `python` .\demo.p…
-
I have a dataset need to detect the lane, but the resolution of images in this dataset is not the same as Tusimple Dataset, so pretrained model didn't work well. therefore I want to fine-tune the pret…
-
I just want to reproduce the exact reported metrics by testing the model;
it always shows the : **AttributeError: 'NoneType' object has no attribute 'shape'**
so maybe the code can't find the tes…
-
生成的mark image
，效果不错
但是src_image中线的位置不对，请问这是什么原因
 zs@zs-B365-M-AORUS-ELITE:~/Ultra-Fast-Lane-Detection$ python train.py configs/tusimple.py
[2020/09/21 16:26:32] star…
-
The resolution is 1920x1080, slightly larget than Tusimple data, I am using tusimple configuation (raw_anchor, gird_num and cls_per_lane), the result seems totally wrong.
Doesn't it only depends on…