披荆斩棘的哥哥

在CULane数据上训练，报如下错误。

2

Error when executing Mixed operator decoders__Image, instance name: "__Image_4", encountered: Error in thread 0: nvml error (999): A nvml internal driver error occurred Current pipeline object is no longer valid.

为什么基于tusimple_res34.pth模型的可视化结果，车道线飘上天了

12


麻烦问下，网络有输出车道线的置信度吗

9

麻烦问下，该网络有输出车道线的置信度吗

if valid_col[0, :, i].sum() >= num_cls_col / 4，这里为什么是除以4，而不是除以2啊

1

大佬麻烦问下，def pred2coords(pred, row_anchor, col_anchor, local_width=1, original_image_width=1640, original_image_height=590): batch_size, num_grid_row, num_cls_row, num_lane_row = pred['loc_row'].shape batch_size, num_grid_col, num_cls_col, num_lane_col = pred['loc_col'].shape max_indices_row = pred['loc_row'].argmax(1).cpu() # n , num_cls, num_lanes valid_row = pred['exist_row'].argmax(1).cpu()...

在预训练模型基础上继续训练时，loss一直为nan

2

您好，麻烦问下，loss一直为nan是什么原因啊。

ALLOWLISTING : SUB layer : Elementwise subtraction with none of the inputs constant/initializer (both inputs as variable inputs) is not supported -- file info - tidl_import_common_model_check.cpp , TIDL_checkAddMulSubDivTensorProperties , 293

2

ALLOWLISTING : SUB layer : Elementwise subtraction with none of the inputs constant/initializer (both inputs as variable inputs) is not supported -- file info - tidl_import_common_model_check.cpp , TIDL_checkAddMulSubDivTensorProperties , 293...