klintan / pytorch-lanenet

LaneNet implementation in PyTorch
MIT License
217 stars 60 forks source link

how to compose image?? #26

Closed sabadijou closed 2 years ago

sabadijou commented 3 years ago

Hi you used the following code in test.py. there are three methods that I couldn't find them (compose_img, val_img_md5, lane_cluster_and_draw). where can I find these methods ???? if step % 100 == 0: val_img_list.append( compose_img(image_data, out, binary_label, net_output["instance_seg_logits"], instance_label, 0)) val_img_md5.write(input_data["img_name"][0] + "\n") lane_cluster_and_draw(image_data, net_output["binary_seg_pred"], net_output["instance_seg_logits"], input_data["o_size"], input_data["img_name"], json_path)

shreyventure commented 2 years ago

Hi @sabadijou ! This repository has taken the reference from lanenet-danet-pytorch repository. So you might find these functions there. For an example, here's lane_cluster_and_draw. Thanks.