Durobert
Durobert
参考你的例子，对BiSeNetv2模型剪枝，报如下错误，这个怎么解决，能看一下吗 ```python index: [34 53 31 46 12 49 36 60 18 68 39 57 67 13 14] key: self.segment.S3.0.dwconv1.1 Traceback (most recent call last): File "model_pruning.py", line 33, in...
我的代码如下 ```python import imp import os import sys BASE_DIR = os.path.dirname(os.path.abspath(__file__)) sys.path.append(os.path.join(BASE_DIR, '..')) import torch import torchpruner import numpy as np from models.bisenetv2 import BiSeNetV2 device = torch.device('cuda' if torch.cuda.is_available()...
@cfzd For the CULane, you resize the image to 1600*320, I use the backbone resnet18, The downsampling multiple is 32，so the feature map's width is 1600/32=50，the value is 1640./50, is...
@cfzd Another problem, about the value 32./534 * 590，For the CULane，the crop_ratio is 0.6，so the resized image height is 320/0.6=534, the value 32./534 * 590 means the croped image height...
@cfzd If we have only two lanes, I wonder whether you compare the two methods or not, what's the difference of them?which method is best?
@cyymt @Roserland @Wolfwjs I also met the problem, Did you solve it?
我也是本地图片上传不了，楼上解决了吗 @F-Passion
为什么算法无法拟合特别大的值？？？
> 我已经按照CULane Dataset中下载对应的数据集并修改，下载的时候没有看到bezier_labels/train_3.json'文件？ 这个问题你是怎么解决的，我也碰到这个问题了
能再更新下二维码吗，谢谢啦