Unable to reproduce results

[yxchng]

The following is my output from running eval_all.py:

(ClearCLIP) cyx@master:/cluster/data7a/cyx/jx/ClearCLIP$ python3 eval_all.py 2>&1 | tee reproduce.log
/cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/torch/distributed/launch.py:180: FutureWarning: The module torch.distributed.launch is deprecated
and will be removed in future. Use torchrun.
Note that --use_env is set by default in torchrun.
If your script expects `--local_rank` argument to be set, please
change it to read from `os.environ['LOCAL_RANK']` instead. See 
https://pytorch.org/docs/stable/distributed.html#launch-utility for 
further instructions

  warnings.warn(
WARNING:torch.distributed.run:
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
*****************************************
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
09/26 15:32:44 - mmengine - INFO - 
------------------------------------------------------------
System environment:
    sys.platform: linux
    Python: 3.10.14 (main, May  6 2024, 19:42:50) [GCC 11.2.0]
    CUDA available: True
    numpy_random_seed: 295349279
    GPU 0,1,2,3,4,5,6,7: NVIDIA GeForce RTX 3090
    CUDA_HOME: /usr/local/cuda-11.7
    NVCC: Cuda compilation tools, release 11.7, V11.7.64
    GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
    PyTorch: 1.13.1+cu117
    PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.7
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86
  - CuDNN 8.5
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

    TorchVision: 0.14.1+cu117
    OpenCV: 4.6.0
    MMEngine: 0.8.4

Runtime environment:
    cudnn_benchmark: True
    mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0}
    dist_cfg: {'backend': 'nccl'}
    seed: 295349279
    Distributed launcher: pytorch
    Distributed training: True
    GPU number: 4
------------------------------------------------------------

09/26 15:32:44 - mmengine - INFO - Config:
data_root = './data/VOCdevkit/VOC2012/'
dataset_type = 'PascalVOC20Dataset'
default_hooks = dict(
    checkpoint=dict(by_epoch=False, interval=2000, type='CheckpointHook'),
    logger=dict(interval=50, log_metric_by_epoch=False, type='LoggerHook'),
    param_scheduler=dict(type='ParamSchedulerHook'),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    timer=dict(type='IterTimerHook'),
    visualization=dict(interval=2, type='SegVisualizationHook'))
default_scope = 'mmseg'
env_cfg = dict(
    cudnn_benchmark=True,
    dist_cfg=dict(backend='nccl'),
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
launcher = 'pytorch'
load_from = None
log_level = 'INFO'
log_processor = dict(by_epoch=False)
model = dict(
    clip_type='CLIP',
    ignore_residual=True,
    model_type='vanilla',
    name_path='./configs/cls_voc20.txt',
    type='ClearCLIPSegmentation',
    vit_type='ViT-B/16')
resume = False
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
    batch_size=1,
    dataset=dict(
        ann_file='ImageSets/Segmentation/val.txt',
        data_prefix=dict(
            img_path='JPEGImages', seg_map_path='SegmentationClass'),
        data_root='./data/VOCdevkit/VOC2012/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                2048,
                448,
            ), type='Resize'),
            dict(type='LoadAnnotations'),
            dict(type='PackSegInputs'),
        ],
        type='PascalVOC20Dataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
    iou_metrics=[
        'mIoU',
    ], type='IoUMetric')
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(keep_ratio=True, scale=(
        2048,
        448,
    ), type='Resize'),
    dict(type='LoadAnnotations'),
    dict(type='PackSegInputs'),
]
vis_backends = [
    dict(type='LocalVisBackend'),
]
visualizer = dict(
    alpha=1.0,
    name='visualizer',
    type='SegLocalVisualizer',
    vis_backends=[
        dict(type='LocalVisBackend'),
    ])
work_dir = './work_logs'

09/26 15:32:48 - mmengine - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH   ) RuntimeInfoHook                    
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
before_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_train_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) DistSamplerSeedHook                
 -------------------- 
before_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_train_epoch:
(NORMAL      ) IterTimerHook                      
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_val_epoch:
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_val_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_val_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_val_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_test_epoch:
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_test_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_test_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_run:
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
09/26 15:32:49 - mmengine - WARNING - The prefix is not set in metric class IoUMetric.
09/26 15:32:51 - mmengine - INFO - Iter(test) [ 50/363]    eta: 0:00:13  time: 0.0255  data_time: 0.0016  memory: 758  
09/26 15:32:52 - mmengine - INFO - Iter(test) [100/363]    eta: 0:00:08  time: 0.0252  data_time: 0.0016  memory: 745  
09/26 15:32:53 - mmengine - INFO - Iter(test) [150/363]    eta: 0:00:06  time: 0.0233  data_time: 0.0016  memory: 744  
09/26 15:32:54 - mmengine - INFO - Iter(test) [200/363]    eta: 0:00:04  time: 0.0274  data_time: 0.0016  memory: 745  
09/26 15:32:56 - mmengine - INFO - Iter(test) [250/363]    eta: 0:00:03  time: 0.0254  data_time: 0.0016  memory: 745  
09/26 15:32:57 - mmengine - INFO - Iter(test) [300/363]    eta: 0:00:01  time: 0.0246  data_time: 0.0018  memory: 747  
09/26 15:32:58 - mmengine - INFO - Iter(test) [350/363]    eta: 0:00:00  time: 0.0225  data_time: 0.0016  memory: 746  
09/26 15:33:01 - mmengine - INFO - per class results:
09/26 15:33:01 - mmengine - INFO - 
+-------------+-------+-------+
|    Class    |  IoU  |  Acc  |
+-------------+-------+-------+
|  aeroplane  | 96.38 | 99.78 |
|   bicycle   | 54.39 | 97.62 |
|     bird    | 93.64 | 94.41 |
|     boat    | 85.71 | 93.59 |
|    bottle   | 85.95 | 91.15 |
|     bus     | 94.22 |  99.5 |
|     car     | 83.22 | 97.37 |
|     cat     | 90.47 | 98.77 |
|    chair    | 28.76 | 33.64 |
|     cow     | 88.73 | 95.18 |
| diningtable | 40.57 | 91.74 |
|     dog     | 85.67 | 95.77 |
|    horse    | 85.32 | 96.69 |
|  motorbike  | 75.15 | 92.38 |
|    person   | 48.88 | 49.78 |
| pottedplant | 72.72 | 86.97 |
|    sheep    | 81.77 | 97.98 |
|     sofa    | 62.24 | 89.46 |
|    train    | 97.16 | 99.75 |
|  tvmonitor  | 63.97 | 64.89 |
+-------------+-------+-------+
09/26 15:33:01 - mmengine - INFO - Iter(test) [363/363]    aAcc: 83.7900  mIoU: 75.7500  mAcc: 88.3200  data_time: 0.0024  time: 0.0267
/cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/torch/distributed/launch.py:180: FutureWarning: The module torch.distributed.launch is deprecated
and will be removed in future. Use torchrun.
Note that --use_env is set by default in torchrun.
If your script expects `--local_rank` argument to be set, please
change it to read from `os.environ['LOCAL_RANK']` instead. See 
https://pytorch.org/docs/stable/distributed.html#launch-utility for 
further instructions

  warnings.warn(
WARNING:torch.distributed.run:
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
*****************************************
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
09/26 15:33:16 - mmengine - INFO - 
------------------------------------------------------------
System environment:
    sys.platform: linux
    Python: 3.10.14 (main, May  6 2024, 19:42:50) [GCC 11.2.0]
    CUDA available: True
    numpy_random_seed: 1878372319
    GPU 0,1,2,3,4,5,6,7: NVIDIA GeForce RTX 3090
    CUDA_HOME: /usr/local/cuda-11.7
    NVCC: Cuda compilation tools, release 11.7, V11.7.64
    GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
    PyTorch: 1.13.1+cu117
    PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.7
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86
  - CuDNN 8.5
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

    TorchVision: 0.14.1+cu117
    OpenCV: 4.6.0
    MMEngine: 0.8.4

Runtime environment:
    cudnn_benchmark: True
    mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0}
    dist_cfg: {'backend': 'nccl'}
    seed: 1878372319
    Distributed launcher: pytorch
    Distributed training: True
    GPU number: 4
------------------------------------------------------------

09/26 15:33:16 - mmengine - INFO - Config:
data_root = './data/cityscapes'
dataset_type = 'CityscapesDataset'
default_hooks = dict(
    checkpoint=dict(by_epoch=False, interval=2000, type='CheckpointHook'),
    logger=dict(interval=50, log_metric_by_epoch=False, type='LoggerHook'),
    param_scheduler=dict(type='ParamSchedulerHook'),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    timer=dict(type='IterTimerHook'),
    visualization=dict(interval=2, type='SegVisualizationHook'))
default_scope = 'mmseg'
env_cfg = dict(
    cudnn_benchmark=True,
    dist_cfg=dict(backend='nccl'),
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
launcher = 'pytorch'
load_from = None
log_level = 'INFO'
log_processor = dict(by_epoch=False)
model = dict(
    clip_type='CLIP',
    ignore_residual=True,
    model_type='vanilla',
    name_path='./configs/cls_city_scapes.txt',
    slide_crop=224,
    type='ClearCLIPSegmentation',
    vit_type='ViT-B/16')
resume = False
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
    batch_size=1,
    dataset=dict(
        data_prefix=dict(
            img_path='leftImg8bit/val', seg_map_path='gtFine/val'),
        data_root='./data/cityscapes',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                2048,
                448,
            ), type='Resize'),
            dict(type='LoadAnnotations'),
            dict(type='PackSegInputs'),
        ],
        type='CityscapesDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
    iou_metrics=[
        'mIoU',
    ], type='IoUMetric')
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(keep_ratio=True, scale=(
        2048,
        448,
    ), type='Resize'),
    dict(type='LoadAnnotations'),
    dict(type='PackSegInputs'),
]
vis_backends = [
    dict(type='LocalVisBackend'),
]
visualizer = dict(
    alpha=1.0,
    name='visualizer',
    type='SegLocalVisualizer',
    vis_backends=[
        dict(type='LocalVisBackend'),
    ])
work_dir = './work_logs'

09/26 15:33:21 - mmengine - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH   ) RuntimeInfoHook                    
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
before_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_train_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) DistSamplerSeedHook                
 -------------------- 
before_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_train_epoch:
(NORMAL      ) IterTimerHook                      
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_val_epoch:
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_val_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_val_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_val_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_test_epoch:
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_test_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_test_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_run:
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
09/26 15:33:21 - mmengine - WARNING - The prefix is not set in metric class IoUMetric.
09/26 15:33:27 - mmengine - INFO - Iter(test) [ 50/125]    eta: 0:00:08  time: 0.0973  data_time: 0.0043  memory: 927  
09/26 15:33:31 - mmengine - INFO - Iter(test) [100/125]    eta: 0:00:02  time: 0.0935  data_time: 0.0043  memory: 927  
09/26 15:33:34 - mmengine - INFO - per class results:
09/26 15:33:34 - mmengine - INFO - 
+---------------+-------+-------+
|     Class     |  IoU  |  Acc  |
+---------------+-------+-------+
|      road     | 55.15 | 81.56 |
|    sidewalk   | 12.71 | 37.69 |
|    building   | 35.99 | 38.27 |
|      wall     |  6.19 | 40.47 |
|     fence     |  9.44 | 10.26 |
|      pole     |  1.57 |  1.72 |
| traffic light |  4.04 | 61.24 |
|  traffic sign | 16.69 | 24.49 |
|   vegetation  | 26.09 |  27.2 |
|    terrain    |  0.0  |  0.0  |
|      sky      |  4.75 |  4.77 |
|     person    |  2.98 |  3.05 |
|     rider     |  0.15 |  0.15 |
|      car      | 36.87 | 77.12 |
|     truck     | 23.02 | 72.27 |
|      bus      | 28.06 | 82.78 |
|     train     |  8.88 | 20.39 |
|   motorcycle  | 16.55 | 18.89 |
|    bicycle    | 28.75 | 45.84 |
+---------------+-------+-------+
09/26 15:33:34 - mmengine - INFO - Iter(test) [125/125]    aAcc: 52.6700  mIoU: 16.7300  mAcc: 34.1100  data_time: 0.0085  time: 0.1036
/cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/torch/distributed/launch.py:180: FutureWarning: The module torch.distributed.launch is deprecated
and will be removed in future. Use torchrun.
Note that --use_env is set by default in torchrun.
If your script expects `--local_rank` argument to be set, please
change it to read from `os.environ['LOCAL_RANK']` instead. See 
https://pytorch.org/docs/stable/distributed.html#launch-utility for 
further instructions

  warnings.warn(
WARNING:torch.distributed.run:
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
*****************************************
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
Extension horovod.torch has not been built: /cluster/home2/cyx/miniconda3/envs/ClearCLIP/lib/python3.10/site-packages/horovod/torch/mpi_lib_v2.cpython-310-x86_64-linux-gnu.so not found
If this is not expected, reinstall Horovod with HOROVOD_WITH_PYTORCH=1 to debug the build error.
Warning! MPI libs are missing, but python applications are still available.
09/26 15:33:53 - mmengine - INFO - 
------------------------------------------------------------
System environment:
    sys.platform: linux
    Python: 3.10.14 (main, May  6 2024, 19:42:50) [GCC 11.2.0]
    CUDA available: True
    numpy_random_seed: 1388269388
    GPU 0,1,2,3,4,5,6,7: NVIDIA GeForce RTX 3090
    CUDA_HOME: /usr/local/cuda-11.7
    NVCC: Cuda compilation tools, release 11.7, V11.7.64
    GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
    PyTorch: 1.13.1+cu117
    PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.7
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86
  - CuDNN 8.5
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

    TorchVision: 0.14.1+cu117
    OpenCV: 4.6.0
    MMEngine: 0.8.4

Runtime environment:
    cudnn_benchmark: True
    mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0}
    dist_cfg: {'backend': 'nccl'}
    seed: 1388269388
    Distributed launcher: pytorch
    Distributed training: True
    GPU number: 4
------------------------------------------------------------

09/26 15:33:53 - mmengine - INFO - Config:
data_root = './data/ade/ADEChallengeData2016'
dataset_type = 'ADE20KDataset'
default_hooks = dict(
    checkpoint=dict(by_epoch=False, interval=2000, type='CheckpointHook'),
    logger=dict(interval=50, log_metric_by_epoch=False, type='LoggerHook'),
    param_scheduler=dict(type='ParamSchedulerHook'),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    timer=dict(type='IterTimerHook'),
    visualization=dict(interval=2, type='SegVisualizationHook'))
default_scope = 'mmseg'
env_cfg = dict(
    cudnn_benchmark=True,
    dist_cfg=dict(backend='nccl'),
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
launcher = 'pytorch'
load_from = None
log_level = 'INFO'
log_processor = dict(by_epoch=False)
model = dict(
    clip_type='CLIP',
    ignore_residual=True,
    model_type='vanilla',
    name_path='./configs/cls_ade20k.txt',
    prob_thd=0.0,
    type='ClearCLIPSegmentation',
    vit_type='ViT-B/16')
resume = False
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
    batch_size=1,
    dataset=dict(
        data_prefix=dict(
            img_path='images/validation',
            seg_map_path='annotations/validation'),
        data_root='./data/ade/ADEChallengeData2016',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                2048,
                448,
            ), type='Resize'),
            dict(reduce_zero_label=True, type='LoadAnnotations'),
            dict(type='PackSegInputs'),
        ],
        type='ADE20KDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
    iou_metrics=[
        'mIoU',
    ], type='IoUMetric')
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(keep_ratio=True, scale=(
        2048,
        448,
    ), type='Resize'),
    dict(reduce_zero_label=True, type='LoadAnnotations'),
    dict(type='PackSegInputs'),
]
vis_backends = [
    dict(type='LocalVisBackend'),
]
visualizer = dict(
    alpha=1.0,
    name='visualizer',
    type='SegLocalVisualizer',
    vis_backends=[
        dict(type='LocalVisBackend'),
    ])
work_dir = './work_logs'

09/26 15:34:00 - mmengine - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH   ) RuntimeInfoHook                    
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
before_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_train_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) DistSamplerSeedHook                
 -------------------- 
before_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_train_epoch:
(NORMAL      ) IterTimerHook                      
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_val_epoch:
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_val_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_val_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_val_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_test_epoch:
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_test_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_test_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_run:
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
09/26 15:34:00 - mmengine - WARNING - The prefix is not set in metric class IoUMetric.
09/26 15:34:03 - mmengine - INFO - Iter(test) [ 50/500]    eta: 0:00:21  time: 0.0269  data_time: 0.0019  memory: 1187  
09/26 15:34:04 - mmengine - INFO - Iter(test) [100/500]    eta: 0:00:15  time: 0.0250  data_time: 0.0017  memory: 1236  
09/26 15:34:05 - mmengine - INFO - Iter(test) [150/500]    eta: 0:00:12  time: 0.0285  data_time: 0.0018  memory: 1023  
09/26 15:34:07 - mmengine - INFO - Iter(test) [200/500]    eta: 0:00:09  time: 0.0253  data_time: 0.0019  memory: 1047  
09/26 15:34:08 - mmengine - INFO - Iter(test) [250/500]    eta: 0:00:07  time: 0.0294  data_time: 0.0019  memory: 1077  
09/26 15:34:10 - mmengine - INFO - Iter(test) [300/500]    eta: 0:00:06  time: 0.0280  data_time: 0.0016  memory: 2896  
09/26 15:34:11 - mmengine - INFO - Iter(test) [350/500]    eta: 0:00:04  time: 0.0245  data_time: 0.0017  memory: 1022  
09/26 15:34:12 - mmengine - INFO - Iter(test) [400/500]    eta: 0:00:02  time: 0.0273  data_time: 0.0018  memory: 1076  
09/26 15:34:13 - mmengine - INFO - Iter(test) [450/500]    eta: 0:00:01  time: 0.0258  data_time: 0.0019  memory: 1027  
09/26 15:34:15 - mmengine - INFO - Iter(test) [500/500]    eta: 0:00:00  time: 0.0298  data_time: 0.0019  memory: 1051  
09/26 15:34:17 - mmengine - INFO - per class results:
09/26 15:34:17 - mmengine - INFO - 
+---------------------+-------+-------+
|        Class        |  IoU  |  Acc  |
+---------------------+-------+-------+
|         wall        |  4.32 |  4.78 |
|       building      | 11.36 |  11.9 |
|         sky         | 12.42 |  12.6 |
|        floor        | 17.81 | 23.76 |
|         tree        | 28.47 |  39.3 |
|       ceiling       |  7.4  |  8.13 |
|         road        | 26.97 | 58.99 |
|         bed         |  28.3 | 94.03 |
|      windowpane     |  0.76 |  0.77 |
|        grass        | 30.88 | 57.99 |
|       cabinet       |  3.77 |  4.31 |
|       sidewalk      | 13.65 | 52.31 |
|        person       |  5.09 |  5.24 |
|        earth        |  0.0  |  0.0  |
|         door        | 12.47 | 25.36 |
|        table        | 11.68 | 38.28 |
|       mountain      | 27.41 | 35.31 |
|        plant        |  19.5 |  22.7 |
|       curtain       |  8.22 |  9.21 |
|        chair        |  2.49 |  2.69 |
|         car         | 31.43 | 68.27 |
|        water        |  5.4  |  5.8  |
|       painting      |  4.87 |  5.89 |
|         sofa        | 19.35 | 74.45 |
|        shelf        |  4.88 |  5.65 |
|        house        |  4.94 | 73.81 |
|         sea         | 18.65 | 44.23 |
|        mirror       |  0.98 |  0.99 |
|         rug         |  9.16 |  22.3 |
|        field        |  8.21 | 20.91 |
|       armchair      |  7.71 |  20.6 |
|         seat        |  13.1 | 36.45 |
|        fence        | 13.84 | 19.72 |
|         desk        |  8.6  | 44.21 |
|         rock        | 15.69 | 47.98 |
|       wardrobe      | 14.14 | 41.11 |
|         lamp        |  6.27 |  7.5  |
|       bathtub       | 17.91 | 61.02 |
|       railing       |  1.64 |  2.12 |
|       cushion       |  0.58 |  0.59 |
|         base        |  0.0  |  0.0  |
|         box         |  3.53 |  6.92 |
|        column       | 11.46 | 18.28 |
|      signboard      |  3.37 |  4.29 |
|   chest of drawers  |  1.23 |  1.42 |
|       counter       |  2.08 | 14.82 |
|         sand        | 29.25 | 74.41 |
|         sink        |  4.17 |  5.34 |
|      skyscraper     | 36.25 | 89.76 |
|      fireplace      |  21.0 |  49.3 |
|     refrigerator    |  7.27 | 30.13 |
|      grandstand     |  5.54 |  8.59 |
|         path        |  6.29 | 13.21 |
|        stairs       |  2.25 |  4.61 |
|        runway       | 30.16 |  50.1 |
|         case        |  0.0  |  0.0  |
|      pool table     | 35.52 | 48.82 |
|        pillow       |  1.42 |  1.55 |
|     screen door     |  0.0  |  0.0  |
|       stairway      | 11.87 | 32.44 |
|        river        |  6.14 | 31.86 |
|        bridge       |  9.37 | 24.42 |
|       bookcase      | 17.82 | 44.99 |
|        blind        |  2.48 |  2.72 |
|     coffee table    |  1.26 |  2.07 |
|        toilet       |  5.63 | 77.66 |
|        flower       | 11.65 | 22.76 |
|         book        |  5.62 |  5.94 |
|         hill        |  1.68 | 19.52 |
|        bench        | 10.97 | 13.23 |
|      countertop     |  1.16 |  10.3 |
|        stove        |  2.45 |  3.8  |
|         palm        | 19.29 | 46.75 |
|    kitchen island   |  2.3  | 80.29 |
|       computer      | 21.69 | 25.49 |
|     swivel chair    |  2.15 |  4.11 |
|         boat        | 18.87 | 72.92 |
|         bar         | 20.14 | 58.71 |
|    arcade machine   |  2.33 |  2.88 |
|        hovel        |  1.52 | 74.22 |
|         bus         | 21.07 |  80.8 |
|        towel        |  4.83 |  9.57 |
|        light        |  0.0  |  0.0  |
|        truck        |  9.09 | 32.76 |
|        tower        |  8.83 | 89.38 |
|      chandelier     | 12.73 | 21.76 |
|        awning       |  1.81 | 18.88 |
|     streetlight     |  3.26 |  5.54 |
|        booth        |  0.85 | 10.18 |
| television receiver |  6.29 |  7.47 |
|       airplane      |  5.05 | 30.15 |
|      dirt track     |  0.0  |  0.0  |
|       apparel       |  0.0  |  0.0  |
|         pole        |  0.02 |  0.03 |
|         land        |  0.26 |  6.82 |
|      bannister      |  2.81 |  6.3  |
|      escalator      | 30.33 |  45.6 |
|       ottoman       |  0.0  |  0.0  |
|        bottle       | 20.33 |  32.7 |
|        buffet       |  0.57 |  6.04 |
|        poster       |  6.53 |  9.2  |
|        stage        | 10.13 | 50.49 |
|         van         |  4.57 | 23.93 |
|         ship        |  2.86 |  3.77 |
|       fountain      |  7.74 | 33.45 |
|    conveyer belt    |  0.0  |  0.0  |
|        canopy       |  0.0  |  0.01 |
|        washer       | 39.83 | 56.11 |
|      plaything      |  2.0  |  2.49 |
|    swimming pool    | 13.25 | 96.53 |
|        stool        |  0.4  |  1.07 |
|        barrel       |  1.26 | 37.36 |
|        basket       |  0.12 |  0.17 |
|      waterfall      |  12.9 | 98.11 |
|         tent        | 19.66 |  96.9 |
|         bag         |  0.78 |  1.03 |
|       minibike      | 13.59 | 13.82 |
|        cradle       |  9.98 | 53.26 |
|         oven        |  0.0  |  0.0  |
|         ball        | 10.96 | 64.46 |
|         food        |  9.69 | 32.69 |
|         step        |  0.07 |  1.18 |
|         tank        |  8.52 |  9.44 |
|      trade name     |  0.77 |  1.63 |
|      microwave      | 37.02 | 41.99 |
|         pot         |  0.12 |  0.13 |
|        animal       |  21.7 | 35.98 |
|       bicycle       | 20.84 | 43.63 |
|         lake        |  5.14 | 85.93 |
|      dishwasher     |  0.0  |  0.0  |
|        screen       | 21.68 | 40.13 |
|       blanket       |  0.05 |  0.05 |
|      sculpture      | 20.81 | 39.61 |
|         hood        |  0.0  |  0.0  |
|        sconce       |  0.38 |  0.49 |
|         vase        |  2.51 |  2.52 |
|    traffic light    |  7.65 |  18.2 |
|         tray        |  1.38 |  2.93 |
|        ashcan       |  0.0  |  0.0  |
|         fan         |  0.0  |  0.0  |
|         pier        |  6.83 | 45.81 |
|      crt screen     |  0.13 |  0.44 |
|        plate        | 28.35 | 39.55 |
|       monitor       |  1.87 |  2.96 |
|    bulletin board   |  0.41 |  1.54 |
|        shower       |  0.24 |  33.5 |
|       radiator      |  0.0  |  0.0  |
|        glass        |  0.0  |  0.0  |
|        clock        |  4.86 | 15.74 |
|         flag        | 25.98 | 36.44 |
+---------------------+-------+-------+
09/26 15:34:17 - mmengine - INFO - Iter(test) [500/500]    aAcc: 21.9200  mIoU: 9.1300  mAcc: 25.1200  data_time: 0.0024  time: 0.0292
Running ./configs/cfg_voc20.py
Running ./configs/cfg_city_scapes.py
Running ./configs/cfg_ade20k.py

I am getting for 75.75 for Context59, 16.73 for Cityscapes and 9.13 for ADE.

which does not seem to match

[mc-lan]

Please set the parameter _modeltype correctly. In this case, if you would to reproduce ClearCLIP's results, please set it to "ClearCLIP", instead of "vanilla".