charlesq34 / pointnet

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Other
4.76k stars 1.45k forks source link

IOError: [Errno 2] No such file or directory: 'all_pred_data_label_filelist.txt' #219

Open longmalongma opened 4 years ago

longmalongma commented 4 years ago

when i try to run python eval_iou_accuracy.py,i meet this problem: IOError: [Errno 2] No such file or directory: 'all_pred_data_label_filelist.txt',where can i find this txt?looking forward to your reply.

heliangha commented 4 years ago

您好,您解决了嘛。

piyushsingh2k7 commented 2 years ago

@charlesq34 . I am also having this problem. IOError: [Errno 2] No such file or directory: 'all_pred_data_label_filelist.txt', where can I find this txt? l looking forward to your reply.

Brodong commented 2 years ago

In my view, we should create it ourself.

Please refer to all_pred_data_label_filelist.txt

Before create this file, make sure we have gotten all models. We need run all commands below:

# model 1
python train.py --log_dir log1 --test_area 1
python batch_inference.py --model_path log1/model.ckpt --dump_dir log1/dump --output_filelist log1/output_filelist.txt --room_data_filelist meta/area1_data_label.txt --visu
# model 2
python train.py --log_dir log2 --test_area 2
python batch_inference.py --model_path log2/model.ckpt --dump_dir log2/dump --output_filelist log2/output_filelist.txt --room_data_filelist meta/area2_data_label.txt --visu
# model 3
python train.py --log_dir log3 --test_area 3
python batch_inference.py --model_path log3/model.ckpt --dump_dir log3/dump --output_filelist log3/output_filelist.txt --room_data_filelist meta/area3_data_label.txt --visu
# model 4
python train.py --log_dir log4 --test_area 4
python batch_inference.py --model_path log4/model.ckpt --dump_dir log4/dump --output_filelist log4/output_filelist.txt --room_data_filelist meta/area4_data_label.txt --visu
# model 5
python train.py --log_dir log5 --test_area 5
python batch_inference.py --model_path log5/model.ckpt --dump_dir log5/dump --output_filelist log5/output_filelist.txt --room_data_filelist meta/area5_data_label.txt --visu
# model 6
python train.py - -log_dir log6 --test_area 6
python batch_inference.py --model_path log6/model.ckpt --dump_dir log6/dump --output_filelist log6/output_filelist.txt --room_data_filelist meta/area6_data_label.txt --visu

We may miss area1_data_label.txt, area2_data_label.txt under sem_seg/meta path. I create a shell script to generate them.

file name: test.sh    
file path: sem_seg/test.sh

#!/bin/bash
rm ../sem_seg/meta/area*.txt
for ((i=1; i<=6; i++))
do
  filelist=$(ls ../data/stanford_indoor3d | grep "Area_${i}")
  for f in $filelist;
  do
    echo "data/stanford_indoor3d/${f}" >> "../sem_seg/meta/area${i}_data_label.txt"
  done
done

Then we can create all_pred_data_label_filelist.txt and run the python file(sem_seg/eval_iou_accuracy.py). I create a shell script to generate it.

file name: test.sh    
file path: sem_seg/test.sh

#!/bin/bash
rm all_pred_data_label_filelist.txt
touch all_pred_data_label_filelist.txt
for ((i=1; i<=6; i++))
do
  filelist=$(ls "log${i}/dump/" | grep '_pred.txt')
  for f in $filelist;
  do
    echo "log${i}/dump/${f}" >> all_pred_data_label_filelist.txt
  done
done