cfzd

Results 254 comments of cfzd

Traceback (most recent call last): File "scripts/convert_tusimple.py", line 145, in <module> names,line_txt = get_tusimple_list(args.root, ['label_data_0601.json','label_data_0531.json','label_data_0313.json']) File "scripts/convert_tusimple.py", line 45, in get_tusimple_list label_json = [json.loads(line) for line in open(l).readlines()] FileNotFoundError: [Errno 2] No such file or directory: '/UFast/TUSIMPLEROOT/label_data_0601.json'

@5wmy5 你有没有tusimple数据集呢？你确定放到`'/UFast/TUSIMPLEROOT/`这个地方了吗？

fatal error: opencv2/core.hpp: No such file or directory

@onAugust1 你有安装opencv吗？有执行 ``` ln -s /usr/local/include/opencv4/opencv2 /usr/local/include/opencv2 ``` 这个命令吗？

fatal error: opencv2/core.hpp: No such file or directory

@onAugust1 你可以尝试一下Option2的安装方式： ``` cd evaluation/culane mkdir build && cd build cmake .. make mv culane_evaluator ../evaluate ``` 你也直接进入到这个路径：`cd /usr/local/include/opencv2 && ls`看看`opencv.hpp`到底存不存在。 或者你可以删掉`rm /usr/local/include/opencv2`这个link，然后重新执行一下`ln -s /usr/local/include/opencv4/opencv2 /usr/local/include/opencv2`

大佬您好问一下resnet34的问题

@dddtyz 对的，改成34即可 https://github.com/cfzd/Ultra-Fast-Lane-Detection/blob/353df107756b8c03c22c27201e33fc63d84ecfe6/model/backbone.py#L17-L20

Output Structure

@jdanielhoyos Of course it would not produce any lanes since `speed_real.py` do not load trained models. You can try to look at `demo.py`.

Run in CPU without NVIDIA+CUDDA

@jdanielhoyos You might need to cancel all the `.cuda()` calls to make your model and data runs in cpu. Sorry I can't provide all the locations of `.cuda()`, but I...

关于模型输出点增加的问题

@qiyuefun anchor的数目和图片分辨率没有关系，如果你想输出的更密，设置更密集的anchor即可

About row anchors

@Tu-Ear 1. This question can be found in our new version UFLDv2: https://arxiv.org/pdf/2206.07389. Generally speaking, the more anchors, the higher performance. 2. The range should cover the possibale range of...

Labelling our own data

@KaiTang98 The most convenient way might be: label your data like CULane, and use the labeled data to train the model as the CULane ways.

Labelling our own data

@KaiTang98 The error `CUDA error: device-side assert triggered` usually means that the number of classess in GT exceeds the number of classes of the network. For example, you have a...