Error on running KITTI tracking on validation test.

[phongphuhanam]

Hello.
I encouter the error when try to run KITTI tracking on validation dataset.
Here is the error log:

python test.py tracking --exp_id ram_kittihalf --dataset kitti_tracking --dataset_version val_half --track_thresh 0.4 --load_model ../models/ram_kittihalf.pth --is_recurrent --input_len 16 --debug 4 --random_walk --rw_head_depth 2 --pool_kernel 3 --max_age 16 --local_rw_r 0.2  --stream_test --new_thresh 0.5 --sup_reg --max_out_age 4
/opt/conda/lib/python3.6/site-packages/sklearn/utils/linear_assignment_.py:22: FutureWarning: The linear_assignment_ module is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead.
  FutureWarning)
Running tracking
Using tracking threshold for out threshold! 0.4
Fix size testing.
training chunk_sizes: [32]
input h w: 384 1280
heads {'hm': 5, 'reg': 2, 'wh': 2, 'tracking': 2}
weights {'hm': 1, 'reg': 1, 'wh': 0.1, 'tracking': 1}
head conv {'hm': [256], 'reg': [256], 'wh': [256], 'tracking': [256]}
Namespace(K=100, add_05=False, add_unmatched=False, amodel_offset_weight=1, arch='dla_34', aug_rot=0, backbone='dla34', batch_size=1, batch_split_factor=-1, border_thresh=0.05, center_dist_thresh=1, chunk_sizes=[32], const_v_over_occl=False, custom_dataset_ann_path='', custom_dataset_img_path='', data_dir='/workspace/RAM/src/lib/../../data', dataset='kitti_tracking', dataset1='coco', dataset2='coco', dataset_version='val_half', debug=4, debug_dir='/workspace/RAM/src/lib/../../exp/cam_02/tracking/ram_kittihalf/debug', debugger_theme='white', demo='', dense_reg=1, dep_weight=1, depth_scale=1, dim_weight=1, disocl_match_thresh=25, dla_node='dcn', down_ratio=4, efficient_level=0, eval_val=False, exp_dir='/workspace/RAM/src/lib/../../exp/cam_02/tracking', exp_id='ram_kittihalf', fix_res=True, fix_short=-1, flip=0.5, flip_test=False, fp_disturb=0, freeze_backbone=False, freeze_gru=False, gpus=[0], gpus_str='0', gru_filter_size=7, head_conv={'hm': [256], 'reg': [256], 'wh': [256], 'tracking': [256]}, head_kernel=3, heads={'hm': 5, 'reg': 2, 'wh': 2, 'tracking': 2}, hm_disturb=0, hm_hp_weight=1, hm_weight=1, hp_weight=1, hungarian=False, ignore_loaded_cats=[], ignore_wh_insym=False, ignorevisininvis_batch=False, input_h=384, input_len=16, input_res=1280, input_w=1280, invis_hm_weight=1, is_recurrent=True, keep_res=False, kitti_split='3dop', load_model='../models/ram_kittihalf.pth', load_results='', local_rw_r=0.2, local_rw_topk=0, lost_disturb=0, lr=0.000125, lr_step=[60], ltrb=False, ltrb_amodal=False, ltrb_amodal_weight=0.1, ltrb_weight=0.1, map_argoverse_id=False, master_batch_size=-1, max_age=16, max_frame_dist=3, max_out_age=4, max_vids=0, min_frame_dist=1, model_output_list=False, msra_outchannel=256, neck='dlaup', new_thresh=0.5, nl=False, nms=False, no_color_aug=False, no_pause=False, no_pre_img=False, no_temp_flip=False, non_block_test=False, not_cuda_benchmark=False, not_idaup=False, not_max_crop=False, not_prefetch_test=False, not_rand_crop=False, not_set_cuda_env=False, not_show_bbox=False, not_show_number=False, not_sup_invis_boxes=False, nu=False, num_classes=5, num_epochs=70, num_gru_layers=1, num_head_conv=1, num_iters=-1, num_layers=101, num_stacks=1, num_val_iters=-1, num_vis_vids=5, num_workers=0, nuscenes_att=False, nuscenes_att_weight=1, occl_len_mult=1, occlusion_thresh=0.1, off_weight=1, optim='adam', out_thresh=0.4, output_h=96, output_w=320, overlapmult=50, pad=31, person_weight=1, pool_kernel=3, pre_hm=False, pre_img=True, pre_thresh=0.4, predicted_hm=False, print_iter=0, prior_bias=-4.6, qualitative=False, radius_growth_step=0.0, random_walk=True, reg_loss='l1', reset_hm=False, resize_video=False, resume=False, reuse_hm=False, root_dir='/workspace/RAM/src/lib/../..', rot_weight=1, rotate=0, rw_head_depth=2, rw_score_thresh=0.05, rw_temp=0.05, rw_weight=0.5, same_aug_pre=False, save_all=False, save_dir='/workspace/RAM/src/lib/../../exp/cam_02/tracking/ram_kittihalf', save_framerate=30, save_img_suffix='', save_imgs=[], save_point=[90], save_results=False, save_video=False, scale=0, seed=317, shift=0, show_track_color=False, skip_first=-1, split_batch=False, stream_test=True, sup_centeroverlap=False, sup_invis=False, sup_reg=True, tango_color=False, task='tracking', test=False, test_dataset='kitti_tracking', test_focal_length=-1, test_scales=[1.0], test_with_loss=False, track_thresh=0.4, tracking=True, tracking_weight=1, trainval=False, transpose_video=False, use_kpt_center=False, use_loaded_results=False, use_occl_len=False, val_intervals=10000, variable_stride=False, velocity=False, velocity_weight=1, video_h=512, video_w=512, vis_gt_bev='', vis_hms=False, vis_thresh=0.3, vis_vids=False, visibility=False, visibility_thresh=0.01, visibility_thresh_eval=0.4, visibility_weight=1, weights={'hm': 1, 'reg': 1, 'wh': 0.1, 'tracking': 1}, wh_weight=0.1, write_to_file=False, zero_pre_hm=False, zero_tracking=False)
==> initializing val data from /workspace/RAM/src/lib/../../data/kitti_tracking/annotations/tracking_val_half.json,
 images from /workspace/RAM/src/lib/../../data/kitti_tracking/data_tracking_image_2/training/image_02 ...
loading annotations into memory...
Traceback (most recent call last):
  File "test.py", line 335, in <module>
    prefetch_test(opt)
  File "test.py", line 106, in prefetch_test
    dataset = Dataset(opt, split)
  File "/workspace/RAM/src/lib/dataset/datasets/kitti_tracking.py", line 41, in __init__
    super(KITTITracking, self).__init__(opt, split, ann_path, img_dir)
  File "/workspace/RAM/src/lib/dataset/video_dataset.py", line 29, in __init__
    super(VideoDataset, self).__init__(opt, split, ann_path, img_dir)
  File "/workspace/RAM/src/lib/dataset/generic_dataset.py", line 79, in __init__
    self.coco = coco.COCO(ann_path)
  File "/opt/conda/lib/python3.6/site-packages/pycocotools/coco.py", line 85, in __init__
    dataset = json.load(open(annotation_file, 'r'))
FileNotFoundError: [Errno 2] No such file or directory: '/workspace/RAM/src/lib/../../data/kitti_tracking/annotations/tracking_val_half.json'

I have set up the dataset according to DATA. Here is my data directory.

../data/kitti_tracking
├── annotations
│   ├── tracking_val_half_ignorecrowd.json
│   └── tracking_val_half_ignorecrowd_tao.json
├── data_tracking_calib
│   ├── testing
│   └── training
├── data_tracking_image_2
│   ├── testing
│   └── training
├── label_02
│   ├── 0000.txt
│   ├── ...
└── label_02_val_half
    ├── 0000.txt
    ├── ...

Compared to the data tree in DATA, there is none of tracking_train.json, tracking_test.json, tracking_train_half.json, tracking_val_half.json but tracking_val_half_ignorecrowd.json, tracking_val_half_ignorecrowd_tao.json is generated.