neuralangelo记录

前言提心吊胆地跑nerualangelo不仅是因为github上的tnt出问题的人太多了还担心motivation验证不出来吧。trainingconfig# 修改数据集目录root:datasets/tanks_and_temples/Truck num_images:251# The number of training images.mesh extractionGROUPtnt NAMEtruck CHECKPOINTlogs/${GROUP}/${NAME}/epoch_01992_iteration_000500000_checkpoint.pt OUTPUT_MESHlogs/${GROUP}/${NAME}/${NAME}.ply CONFIGlogs/${GROUP}/${NAME}/config.yaml RESOLUTION2048 BLOCK_RES128 GPUS1 # use 1 for multi-GPU mesh extraction torchrun --nproc_per_node${GPUS} projects/neuralangelo/scripts/extract_mesh.py \ --config${CONFIG} \ --checkpoint${CHECKPOINT} \ --output_file${OUTPUT_MESH} \ --resolution${RESOLUTION} \ --block_res${BLOCK_RES}GROUPnerf-syntheticNAMEnerf_legoRESOLUTION1024BLOCK_RES128CONFIGlogs/${GROUP}/${NAME}/config.yamlGPUS1CHECKPOINTlogs/${GROUP}/${NAME}/epoch_00250_iteration_000100000_checkpoint.ptOUTPUT_MESHlogs/${GROUP}/${NAME}/lego1w.ply torchrun--nproc_per_node${GPUS}projects/neuralangelo/scripts/extract_mesh.py--config${CONFIG}--checkpoint${CHECKPOINT}--output_file${OUTPUT_MESH}--resolution${RESOLUTION}--block_res${BLOCK_RES}from torch_scatterimportsegment_coo pipinstalltorch-scatter-fhttps://data.pyg.org/whl/torch-2.11.0cu128.html