yangheqing commited on
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- trogeo_pi3_eccv_checkpoint.pth.tar +3 -0
- trogeo_pi3_eccv_model_best.pth.tar +3 -0
- wandb/wandb/debug-internal.log +0 -0
- wandb/wandb/debug.log +24 -0
- wandb/wandb/run-20260507_130026-3lo4j577/files/config.yaml +178 -0
- wandb/wandb/run-20260507_130026-3lo4j577/files/output.log +104 -0
- wandb/wandb/run-20260507_130026-3lo4j577/files/requirements.txt +94 -0
- wandb/wandb/run-20260507_130026-3lo4j577/files/wandb-metadata.json +93 -0
- wandb/wandb/run-20260507_130026-3lo4j577/files/wandb-summary.json +1 -0
- wandb/wandb/run-20260507_130026-3lo4j577/logs/debug-internal.log +0 -0
- wandb/wandb/run-20260507_130026-3lo4j577/logs/debug.log +24 -0
- wandb/wandb/run-20260507_130026-3lo4j577/run-3lo4j577.wandb +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
wandb/wandb/run-20260507_130026-3lo4j577/run-3lo4j577.wandb filter=lfs diff=lfs merge=lfs -text
|
trogeo_pi3_eccv_checkpoint.pth.tar
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03c4ddaff0e1734b1abc4ab7e7ee85ed707d6423a29476adbb528ac410fb44f4
|
| 3 |
+
size 6949481519
|
trogeo_pi3_eccv_model_best.pth.tar
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7b8962f00957ea42651a60d0f43bf30beabb34769c65b655c86f279b9651e83
|
| 3 |
+
size 6949481519
|
wandb/wandb/debug-internal.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
wandb/wandb/debug.log
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2026-05-07 13:00:27,076 INFO MainThread:4596 [wandb_setup.py:_flush():81] Current SDK version is 0.26.1
|
| 2 |
+
2026-05-07 13:00:27,079 INFO MainThread:4596 [wandb_setup.py:_flush():81] Configure stats pid to 4596
|
| 3 |
+
2026-05-07 13:00:27,082 INFO MainThread:4596 [wandb_setup.py:_flush():81] Loading settings from environment variables
|
| 4 |
+
2026-05-07 13:00:27,087 INFO MainThread:4596 [wandb_init.py:setup_run_log_directory():723] Logging user logs to /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs/wandb/wandb/run-20260507_130026-3lo4j577/logs/debug.log
|
| 5 |
+
2026-05-07 13:00:27,094 INFO MainThread:4596 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs/wandb/wandb/run-20260507_130026-3lo4j577/logs/debug-internal.log
|
| 6 |
+
2026-05-07 13:00:27,099 INFO MainThread:4596 [wandb_init.py:init():850] calling init triggers
|
| 7 |
+
2026-05-07 13:00:27,101 INFO MainThread:4596 [wandb_init.py:init():855] wandb.init called with sweep_config: {}
|
| 8 |
+
config: {'config': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/configs/trogeo_pi3_offline.yaml', 'gpu': '0,1,2,3,4,5,6,7', 'num_workers': 3, 'max_epoch': 25, 'lr': 0.0001, 'batch_size': 12, 'emb_size': 768, 'img_size': 518, 'data_root': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/data', 'data_name': 'CVOGL_DroneAerial', 'dataset_type': 'eccv', 'train_json': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/train_all.json', 'val_json': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/val_all.json', 'test_json': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/test_all.json', 'backbone_type': 'pi3', 'pi3_pretrain': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/location_v4/checkpoints_offline/pi3_model.safetensors', 'pi3_decoder_size': 'large', 'freeze_encoder': True, 'freeze_decoder': False, 'pretrain': '', 'resume': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs', 'print_freq': 10, 'savename': 'trogeo_pi3_eccv', 'output_dir': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs', 'seed': 2024, 'beta': 1.0, 'pos_weight': 15.0, 'test': False, 'val': False, 'wandb': True, 'wandb_project': 'CVOS-Code', 'wandb_dir': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs/wandb', 'use_amp': True, 'use_tf32': True, 'persistent_workers': True, 'prefetch_factor': 4, 'rank': 0, 'world_size': 8, 'local_rank': 0, 'anchors': '18,20, 36,40, 48,108, 64,64, 96,40, 96,88, 124,140, 198,171, 275,286', 'train_loader_len': 1994, '_wandb': {}}
|
| 9 |
+
2026-05-07 13:00:27,104 INFO MainThread:4596 [wandb_init.py:init():898] starting backend
|
| 10 |
+
2026-05-07 13:00:30,625 INFO MainThread:4596 [wandb_init.py:init():913] sending inform_init request
|
| 11 |
+
2026-05-07 13:00:34,851 INFO MainThread:4596 [wandb_init.py:init():918] backend started and connected
|
| 12 |
+
2026-05-07 13:00:34,858 INFO MainThread:4596 [wandb_init.py:init():988] updated telemetry
|
| 13 |
+
2026-05-07 13:00:35,346 INFO MainThread:4596 [wandb_init.py:init():1011] communicating run to backend with 90.0 second timeout
|
| 14 |
+
2026-05-07 13:00:36,116 INFO MainThread:4596 [wandb_init.py:init():1056] starting run threads in backend
|
| 15 |
+
2026-05-07 13:00:37,271 INFO MainThread:4596 [wandb_run.py:_console_start():2554] atexit reg
|
| 16 |
+
2026-05-07 13:00:37,275 INFO MainThread:4596 [wandb_run.py:_redirect():2403] redirect: wrap_raw
|
| 17 |
+
2026-05-07 13:00:37,277 INFO MainThread:4596 [wandb_run.py:_redirect():2472] Wrapping output streams.
|
| 18 |
+
2026-05-07 13:00:37,279 INFO MainThread:4596 [wandb_run.py:_redirect():2495] Redirects installed.
|
| 19 |
+
2026-05-07 13:00:37,329 INFO MainThread:4596 [wandb_init.py:init():1094] run started, returning control to user process
|
| 20 |
+
2026-05-08 12:24:12,317 INFO MainThread:4596 [wandb_run.py:_finish():2321] finishing run hycd540-beihang-university/CVOS-Code/3lo4j577
|
| 21 |
+
2026-05-08 12:24:12,337 INFO MainThread:4596 [wandb_run.py:_atexit_cleanup():2520] got exitcode: 0
|
| 22 |
+
2026-05-08 12:24:12,343 INFO MainThread:4596 [wandb_run.py:_restore():2502] restore
|
| 23 |
+
2026-05-08 12:24:12,345 INFO MainThread:4596 [wandb_run.py:_restore():2508] restore done
|
| 24 |
+
2026-05-08 12:24:15,240 INFO MainThread:4596 [wandb_run.py:_footer_sync_info():3889] logging synced files
|
wandb/wandb/run-20260507_130026-3lo4j577/files/config.yaml
ADDED
|
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_wandb:
|
| 2 |
+
value:
|
| 3 |
+
cli_version: 0.26.1
|
| 4 |
+
e:
|
| 5 |
+
n66y3yolechf07hvu2i2dxfxcxu3un0q:
|
| 6 |
+
args:
|
| 7 |
+
- --config
|
| 8 |
+
- /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/configs/trogeo_pi3_offline.yaml
|
| 9 |
+
codePath: train.py
|
| 10 |
+
codePathLocal: train.py
|
| 11 |
+
cpu_count: 96
|
| 12 |
+
cpu_count_logical: 184
|
| 13 |
+
cudaVersion: "12.4"
|
| 14 |
+
disk:
|
| 15 |
+
/:
|
| 16 |
+
total: "53687091200"
|
| 17 |
+
used: "121737216"
|
| 18 |
+
email: hycd540@gmail.com
|
| 19 |
+
executable: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/location_v4/.venv/bin/python
|
| 20 |
+
git:
|
| 21 |
+
commit: 69ac6ce26abfd5b5619ce59bf76b093bbf75f1cc
|
| 22 |
+
remote: git@github.com:cipual/CVOS-Code.git
|
| 23 |
+
gpu: NVIDIA H200
|
| 24 |
+
gpu_count: 8
|
| 25 |
+
gpu_nvidia:
|
| 26 |
+
- architecture: Hopper
|
| 27 |
+
cudaCores: 16896
|
| 28 |
+
memoryTotal: "150754820096"
|
| 29 |
+
name: NVIDIA H200
|
| 30 |
+
uuid: GPU-e691af30-9e76-2280-b5cc-1276df37a4fb
|
| 31 |
+
- architecture: Hopper
|
| 32 |
+
cudaCores: 16896
|
| 33 |
+
memoryTotal: "150754820096"
|
| 34 |
+
name: NVIDIA H200
|
| 35 |
+
uuid: GPU-1c3e7100-2e19-234c-3046-f07e76b3d684
|
| 36 |
+
- architecture: Hopper
|
| 37 |
+
cudaCores: 16896
|
| 38 |
+
memoryTotal: "150754820096"
|
| 39 |
+
name: NVIDIA H200
|
| 40 |
+
uuid: GPU-45f60f31-9a59-e99b-da1c-eb7df5e0df4d
|
| 41 |
+
- architecture: Hopper
|
| 42 |
+
cudaCores: 16896
|
| 43 |
+
memoryTotal: "150754820096"
|
| 44 |
+
name: NVIDIA H200
|
| 45 |
+
uuid: GPU-96df27eb-a35a-2c2f-1024-455553308768
|
| 46 |
+
- architecture: Hopper
|
| 47 |
+
cudaCores: 16896
|
| 48 |
+
memoryTotal: "150754820096"
|
| 49 |
+
name: NVIDIA H200
|
| 50 |
+
uuid: GPU-d3d78141-29c8-e2ce-ce62-8cb199bbd05e
|
| 51 |
+
- architecture: Hopper
|
| 52 |
+
cudaCores: 16896
|
| 53 |
+
memoryTotal: "150754820096"
|
| 54 |
+
name: NVIDIA H200
|
| 55 |
+
uuid: GPU-ea15c218-130a-565f-058d-6cadc9ac3aa5
|
| 56 |
+
- architecture: Hopper
|
| 57 |
+
cudaCores: 16896
|
| 58 |
+
memoryTotal: "150754820096"
|
| 59 |
+
name: NVIDIA H200
|
| 60 |
+
uuid: GPU-76ee9c8e-bad5-8e3c-1766-c891bc14e07a
|
| 61 |
+
- architecture: Hopper
|
| 62 |
+
cudaCores: 16896
|
| 63 |
+
memoryTotal: "150754820096"
|
| 64 |
+
name: NVIDIA H200
|
| 65 |
+
uuid: GPU-25afd362-e436-a0d2-ad7f-c31a4a73a20f
|
| 66 |
+
host: psx4524xrlkpndoc-worker-0
|
| 67 |
+
memory:
|
| 68 |
+
total: "1887436800000"
|
| 69 |
+
os: Linux-5.10.0-218.0.0.mt20250120.565.mt2203sp4.x86_64-x86_64-with-glibc2.32
|
| 70 |
+
program: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/train.py
|
| 71 |
+
python: CPython 3.11.14
|
| 72 |
+
root: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs/wandb
|
| 73 |
+
startedAt: "2026-05-07T05:00:26.945273Z"
|
| 74 |
+
writerId: n66y3yolechf07hvu2i2dxfxcxu3un0q
|
| 75 |
+
m: []
|
| 76 |
+
python_version: 3.11.14
|
| 77 |
+
t:
|
| 78 |
+
"1":
|
| 79 |
+
- 1
|
| 80 |
+
- 41
|
| 81 |
+
- 49
|
| 82 |
+
- 80
|
| 83 |
+
"2":
|
| 84 |
+
- 1
|
| 85 |
+
- 41
|
| 86 |
+
- 49
|
| 87 |
+
- 80
|
| 88 |
+
"3":
|
| 89 |
+
- 2
|
| 90 |
+
- 13
|
| 91 |
+
- 16
|
| 92 |
+
- 61
|
| 93 |
+
"4": 3.11.14
|
| 94 |
+
"5": 0.26.1
|
| 95 |
+
"12": 0.26.1
|
| 96 |
+
"13": linux-x86_64
|
| 97 |
+
anchors:
|
| 98 |
+
value: 18,20, 36,40, 48,108, 64,64, 96,40, 96,88, 124,140, 198,171, 275,286
|
| 99 |
+
backbone_type:
|
| 100 |
+
value: pi3
|
| 101 |
+
batch_size:
|
| 102 |
+
value: 12
|
| 103 |
+
beta:
|
| 104 |
+
value: 1
|
| 105 |
+
config:
|
| 106 |
+
value: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/configs/trogeo_pi3_offline.yaml
|
| 107 |
+
data_name:
|
| 108 |
+
value: CVOGL_DroneAerial
|
| 109 |
+
data_root:
|
| 110 |
+
value: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/data
|
| 111 |
+
dataset_type:
|
| 112 |
+
value: eccv
|
| 113 |
+
emb_size:
|
| 114 |
+
value: 768
|
| 115 |
+
freeze_decoder:
|
| 116 |
+
value: false
|
| 117 |
+
freeze_encoder:
|
| 118 |
+
value: true
|
| 119 |
+
gpu:
|
| 120 |
+
value: 0,1,2,3,4,5,6,7
|
| 121 |
+
img_size:
|
| 122 |
+
value: 518
|
| 123 |
+
local_rank:
|
| 124 |
+
value: 0
|
| 125 |
+
lr:
|
| 126 |
+
value: 0.0001
|
| 127 |
+
max_epoch:
|
| 128 |
+
value: 25
|
| 129 |
+
num_workers:
|
| 130 |
+
value: 3
|
| 131 |
+
output_dir:
|
| 132 |
+
value: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs
|
| 133 |
+
persistent_workers:
|
| 134 |
+
value: true
|
| 135 |
+
pi3_decoder_size:
|
| 136 |
+
value: large
|
| 137 |
+
pi3_pretrain:
|
| 138 |
+
value: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/location_v4/checkpoints_offline/pi3_model.safetensors
|
| 139 |
+
pos_weight:
|
| 140 |
+
value: 15
|
| 141 |
+
prefetch_factor:
|
| 142 |
+
value: 4
|
| 143 |
+
pretrain:
|
| 144 |
+
value: ""
|
| 145 |
+
print_freq:
|
| 146 |
+
value: 10
|
| 147 |
+
rank:
|
| 148 |
+
value: 0
|
| 149 |
+
resume:
|
| 150 |
+
value: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs
|
| 151 |
+
savename:
|
| 152 |
+
value: trogeo_pi3_eccv
|
| 153 |
+
seed:
|
| 154 |
+
value: 2024
|
| 155 |
+
test:
|
| 156 |
+
value: false
|
| 157 |
+
test_json:
|
| 158 |
+
value: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/test_all.json
|
| 159 |
+
train_json:
|
| 160 |
+
value: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/train_all.json
|
| 161 |
+
train_loader_len:
|
| 162 |
+
value: 1994
|
| 163 |
+
use_amp:
|
| 164 |
+
value: true
|
| 165 |
+
use_tf32:
|
| 166 |
+
value: true
|
| 167 |
+
val:
|
| 168 |
+
value: false
|
| 169 |
+
val_json:
|
| 170 |
+
value: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/val_all.json
|
| 171 |
+
wandb:
|
| 172 |
+
value: true
|
| 173 |
+
wandb_dir:
|
| 174 |
+
value: /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs/wandb
|
| 175 |
+
wandb_project:
|
| 176 |
+
value: CVOS-Code
|
| 177 |
+
world_size:
|
| 178 |
+
value: 8
|
wandb/wandb/run-20260507_130026-3lo4j577/files/output.log
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
('lr', 0.0001)
|
| 2 |
+
Train Epoch 0: 100%|██████████| 1994/1994 [50:15<00:00, 1.51s/it, loss=3.4721, geo=0.1546, cls=2.8872, accu=0.7500, miou=0.6599, accu_c=0.4167, dt=1.496s]
|
| 3 |
+
Val Epoch 0: 100%|██████████| 125/125 [01:41<00:00, 1.23it/s, accu50=0.4583, accu25=0.5833, miou=0.4058, accu_c=0.2917, dt=0.786s]
|
| 4 |
+
Accu50: 0.48011, Accu25: 0.67026, mIoU: 0.42649, Accu Center: 0.24682
|
| 5 |
+
/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/location_v4/.venv/lib/python3.11/site-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via `init_process_group` or `barrier `. Using the current device set by the user.
|
| 6 |
+
warnings.warn( # warn only once
|
| 7 |
+
('lr', 0.0001)
|
| 8 |
+
Train Epoch 1: 100%|██████████| 1994/1994 [49:51<00:00, 1.50s/it, loss=2.9348, geo=0.1290, cls=2.4171, accu=0.8333, miou=0.6097, accu_c=0.5000, dt=1.497s]
|
| 9 |
+
Val Epoch 1: 100%|██████████| 125/125 [01:39<00:00, 1.26it/s, accu50=0.5833, accu25=0.7083, miou=0.4671, accu_c=0.2917, dt=0.787s]
|
| 10 |
+
Accu50: 0.56979, Accu25: 0.74695, mIoU: 0.49041, Accu Center: 0.29969
|
| 11 |
+
('lr', 0.0001)
|
| 12 |
+
Train Epoch 2: 100%|██████████| 1994/1994 [49:51<00:00, 1.50s/it, loss=3.1956, geo=0.1702, cls=2.6621, accu=0.6667, miou=0.5718, accu_c=0.4167, dt=1.497s]
|
| 13 |
+
Val Epoch 2: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.6667, accu25=0.7917, miou=0.5274, accu_c=0.3333, dt=0.786s]
|
| 14 |
+
Accu50: 0.60022, Accu25: 0.77144, mIoU: 0.51186, Accu Center: 0.33191
|
| 15 |
+
('lr', 0.0001)
|
| 16 |
+
Train Epoch 3: 100%|██████████| 1994/1994 [49:52<00:00, 1.50s/it, loss=2.4825, geo=0.1389, cls=2.0033, accu=0.5833, miou=0.5864, accu_c=0.3333, dt=1.496s]
|
| 17 |
+
Val Epoch 3: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.8333, miou=0.5194, accu_c=0.4583, dt=0.786s]
|
| 18 |
+
Accu50: 0.61597, Accu25: 0.78557, mIoU: 0.52427, Accu Center: 0.34767
|
| 19 |
+
('lr', 0.0001)
|
| 20 |
+
Train Epoch 4: 100%|██████████| 1994/1994 [49:51<00:00, 1.50s/it, loss=2.7691, geo=0.0920, cls=2.2314, accu=0.5833, miou=0.4442, accu_c=0.3333, dt=1.497s]
|
| 21 |
+
Val Epoch 4: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.6667, accu25=0.7917, miou=0.5264, accu_c=0.3750, dt=0.787s]
|
| 22 |
+
Accu50: 0.62734, Accu25: 0.79468, mIoU: 0.53739, Accu Center: 0.36622
|
| 23 |
+
('lr', 0.0001)
|
| 24 |
+
Train Epoch 5: 100%|██████████| 1994/1994 [49:52<00:00, 1.50s/it, loss=2.5781, geo=0.0811, cls=1.8582, accu=0.6667, miou=0.6095, accu_c=0.5833, dt=1.497s]
|
| 25 |
+
Val Epoch 5: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5417, accu25=0.7917, miou=0.5327, accu_c=0.4583, dt=0.787s]
|
| 26 |
+
Accu50: 0.64314, Accu25: 0.80759, mIoU: 0.54760, Accu Center: 0.37124
|
| 27 |
+
('lr', 0.0001)
|
| 28 |
+
Train Epoch 6: 100%|██████████| 1994/1994 [49:52<00:00, 1.50s/it, loss=1.3582, geo=0.1030, cls=0.9880, accu=0.7500, miou=0.5849, accu_c=0.8333, dt=1.494s]
|
| 29 |
+
Val Epoch 6: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5383, accu_c=0.3750, dt=0.787s]
|
| 30 |
+
Accu50: 0.65242, Accu25: 0.81566, mIoU: 0.55271, Accu Center: 0.38378
|
| 31 |
+
('lr', 0.0001)
|
| 32 |
+
Train Epoch 7: 100%|██████████| 1994/1994 [49:49<00:00, 1.50s/it, loss=1.6938, geo=0.1253, cls=1.3444, accu=0.7500, miou=0.7229, accu_c=0.5833, dt=1.496s]
|
| 33 |
+
Val Epoch 7: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.6250, accu25=0.8333, miou=0.5236, accu_c=0.2917, dt=0.787s]
|
| 34 |
+
Accu50: 0.66282, Accu25: 0.82038, mIoU: 0.56240, Accu Center: 0.38190
|
| 35 |
+
('lr', 0.0001)
|
| 36 |
+
Train Epoch 8: 100%|██████████| 1994/1994 [49:50<00:00, 1.50s/it, loss=2.0382, geo=0.0671, cls=1.6468, accu=0.9167, miou=0.6967, accu_c=0.5833, dt=1.495s]
|
| 37 |
+
Val Epoch 8: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5160, accu_c=0.2917, dt=0.787s]
|
| 38 |
+
Accu50: 0.67828, Accu25: 0.82644, mIoU: 0.57158, Accu Center: 0.38624
|
| 39 |
+
('lr', 0.0001)
|
| 40 |
+
Train Epoch 9: 100%|██████████| 1994/1994 [49:52<00:00, 1.50s/it, loss=0.9196, geo=0.0802, cls=0.7432, accu=0.7500, miou=0.6685, accu_c=0.7500, dt=1.498s]
|
| 41 |
+
Val Epoch 9: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.4583, accu25=0.7917, miou=0.4656, accu_c=0.3750, dt=0.787s]
|
| 42 |
+
Accu50: 0.66199, Accu25: 0.82084, mIoU: 0.56267, Accu Center: 0.39673
|
| 43 |
+
('lr', 1e-05)
|
| 44 |
+
Train Epoch 10: 100%|██████████| 1994/1994 [49:51<00:00, 1.50s/it, loss=1.1155, geo=0.0903, cls=0.8719, accu=1.0000, miou=0.8320, accu_c=0.6667, dt=1.495s]
|
| 45 |
+
Val Epoch 10: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5000, accu25=0.7500, miou=0.4939, accu_c=0.3333, dt=0.785s]
|
| 46 |
+
Accu50: 0.69968, Accu25: 0.84771, mIoU: 0.59382, Accu Center: 0.43033
|
| 47 |
+
('lr', 1e-05)
|
| 48 |
+
Train Epoch 11: 100%|██████████| 1994/1994 [49:50<00:00, 1.50s/it, loss=1.2032, geo=0.0522, cls=1.0270, accu=0.9167, miou=0.7849, accu_c=0.5833, dt=1.494s]
|
| 49 |
+
Val Epoch 11: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5417, accu25=0.7917, miou=0.4995, accu_c=0.2917, dt=0.787s]
|
| 50 |
+
Accu50: 0.70323, Accu25: 0.84938, mIoU: 0.59601, Accu Center: 0.43714
|
| 51 |
+
('lr', 1e-05)
|
| 52 |
+
Train Epoch 12: 100%|██████████| 1994/1994 [49:50<00:00, 1.50s/it, loss=1.0123, geo=0.0635, cls=0.7869, accu=0.9167, miou=0.7628, accu_c=0.5833, dt=1.497s]
|
| 53 |
+
Val Epoch 12: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5105, accu_c=0.3333, dt=0.787s]
|
| 54 |
+
Accu50: 0.70340, Accu25: 0.84959, mIoU: 0.59492, Accu Center: 0.43882
|
| 55 |
+
('lr', 1e-05)
|
| 56 |
+
Train Epoch 13: 100%|██████████| 1994/1994 [49:51<00:00, 1.50s/it, loss=1.5644, geo=0.0697, cls=1.3500, accu=0.8333, miou=0.6840, accu_c=0.4167, dt=1.494s]
|
| 57 |
+
Val Epoch 13: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.4988, accu_c=0.2917, dt=0.786s]
|
| 58 |
+
Accu50: 0.70821, Accu25: 0.85298, mIoU: 0.59926, Accu Center: 0.44007
|
| 59 |
+
('lr', 1e-05)
|
| 60 |
+
Train Epoch 14: 100%|██████████| 1994/1994 [49:48<00:00, 1.50s/it, loss=0.9199, geo=0.1082, cls=0.6514, accu=0.8333, miou=0.6749, accu_c=0.9167, dt=1.495s]
|
| 61 |
+
Val Epoch 14: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5080, accu_c=0.2917, dt=0.786s]
|
| 62 |
+
Accu50: 0.71067, Accu25: 0.85214, mIoU: 0.60067, Accu Center: 0.44270
|
| 63 |
+
('lr', 1e-05)
|
| 64 |
+
Train Epoch 15: 100%|██████████| 1994/1994 [49:51<00:00, 1.50s/it, loss=0.9338, geo=0.0484, cls=0.7569, accu=0.8333, miou=0.7187, accu_c=0.5000, dt=1.495s]
|
| 65 |
+
Val Epoch 15: 100%|██████████| 125/125 [01:40<00:00, 1.25it/s, accu50=0.5417, accu25=0.7917, miou=0.5080, accu_c=0.2917, dt=0.787s]
|
| 66 |
+
Accu50: 0.70583, Accu25: 0.85080, mIoU: 0.59717, Accu Center: 0.44032
|
| 67 |
+
('lr', 1e-05)
|
| 68 |
+
Train Epoch 16: 100%|██████████| 1994/1994 [49:49<00:00, 1.50s/it, loss=0.7115, geo=0.0585, cls=0.4862, accu=0.9167, miou=0.7482, accu_c=0.7500, dt=1.495s]
|
| 69 |
+
Val Epoch 16: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5089, accu_c=0.2917, dt=0.786s]
|
| 70 |
+
Accu50: 0.70449, Accu25: 0.85172, mIoU: 0.59748, Accu Center: 0.44153
|
| 71 |
+
('lr', 1e-05)
|
| 72 |
+
Train Epoch 17: 100%|██████████| 1994/1994 [49:52<00:00, 1.50s/it, loss=0.8768, geo=0.0600, cls=0.6826, accu=1.0000, miou=0.7404, accu_c=0.7500, dt=1.494s]
|
| 73 |
+
Val Epoch 17: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.6667, accu25=0.8333, miou=0.5421, accu_c=0.3333, dt=0.787s]
|
| 74 |
+
Accu50: 0.71063, Accu25: 0.85135, mIoU: 0.60151, Accu Center: 0.43982
|
| 75 |
+
('lr', 1e-05)
|
| 76 |
+
Train Epoch 18: 100%|██████████| 1994/1994 [49:48<00:00, 1.50s/it, loss=1.0363, geo=0.0552, cls=0.8747, accu=1.0000, miou=0.7751, accu_c=0.6667, dt=1.494s]
|
| 77 |
+
Val Epoch 18: 100%|██████████| 125/125 [01:40<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5135, accu_c=0.3750, dt=0.786s]
|
| 78 |
+
Accu50: 0.70992, Accu25: 0.85164, mIoU: 0.60126, Accu Center: 0.44107
|
| 79 |
+
('lr', 1e-05)
|
| 80 |
+
Train Epoch 19: 100%|██████████| 1994/1994 [49:47<00:00, 1.50s/it, loss=0.8069, geo=0.0419, cls=0.6339, accu=1.0000, miou=0.7871, accu_c=0.6667, dt=1.497s]
|
| 81 |
+
Val Epoch 19: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5045, accu_c=0.2917, dt=0.786s]
|
| 82 |
+
Accu50: 0.70478, Accu25: 0.85097, mIoU: 0.59983, Accu Center: 0.43852
|
| 83 |
+
('lr', 1.0000000000000002e-06)
|
| 84 |
+
Train Epoch 20: 100%|██████████| 1994/1994 [49:48<00:00, 1.50s/it, loss=0.4784, geo=0.0402, cls=0.3337, accu=1.0000, miou=0.8210, accu_c=0.8333, dt=1.498s]
|
| 85 |
+
Val Epoch 20: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5015, accu_c=0.2917, dt=0.786s]
|
| 86 |
+
Accu50: 0.70909, Accu25: 0.85277, mIoU: 0.60155, Accu Center: 0.44283
|
| 87 |
+
('lr', 1.0000000000000002e-06)
|
| 88 |
+
Train Epoch 21: 100%|██████████| 1994/1994 [49:55<00:00, 1.50s/it, loss=0.9288, geo=0.0195, cls=0.8041, accu=1.0000, miou=0.8106, accu_c=0.7500, dt=1.500s]
|
| 89 |
+
Val Epoch 21: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5047, accu_c=0.2917, dt=0.787s]
|
| 90 |
+
Accu50: 0.71155, Accu25: 0.85256, mIoU: 0.60218, Accu Center: 0.44233
|
| 91 |
+
('lr', 1.0000000000000002e-06)
|
| 92 |
+
Train Epoch 22: 100%|██████████| 1994/1994 [49:49<00:00, 1.50s/it, loss=0.8759, geo=0.0302, cls=0.7199, accu=1.0000, miou=0.8106, accu_c=0.6667, dt=1.496s]
|
| 93 |
+
Val Epoch 22: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5057, accu_c=0.2917, dt=0.788s]
|
| 94 |
+
Accu50: 0.71084, Accu25: 0.85318, mIoU: 0.60185, Accu Center: 0.44366
|
| 95 |
+
('lr', 1.0000000000000002e-06)
|
| 96 |
+
Train Epoch 23: 100%|██████████| 1994/1994 [49:50<00:00, 1.50s/it, loss=0.3663, geo=0.0669, cls=0.1929, accu=0.8333, miou=0.7454, accu_c=0.9167, dt=1.496s]
|
| 97 |
+
Val Epoch 23: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5029, accu_c=0.2917, dt=0.787s]
|
| 98 |
+
Accu50: 0.71063, Accu25: 0.85289, mIoU: 0.60239, Accu Center: 0.44437
|
| 99 |
+
('lr', 1.0000000000000002e-06)
|
| 100 |
+
Train Epoch 24: 100%|██████████| 1994/1994 [49:50<00:00, 1.50s/it, loss=0.5847, geo=0.0369, cls=0.3998, accu=0.8333, miou=0.7486, accu_c=0.7500, dt=1.496s]
|
| 101 |
+
Val Epoch 24: 100%|██████████| 125/125 [01:39<00:00, 1.25it/s, accu50=0.5833, accu25=0.7917, miou=0.5022, accu_c=0.2917, dt=0.785s]
|
| 102 |
+
Accu50: 0.71097, Accu25: 0.85285, mIoU: 0.60220, Accu Center: 0.44392
|
| 103 |
+
|
| 104 |
+
Best Accu: 0.711551
|
wandb/wandb/run-20260507_130026-3lo4j577/files/requirements.txt
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
absl-py==2.4.0
|
| 2 |
+
accelerate==1.12.0
|
| 3 |
+
albucore==0.0.24
|
| 4 |
+
albumentations==2.0.8
|
| 5 |
+
annotated-doc==0.0.4
|
| 6 |
+
annotated-types==0.7.0
|
| 7 |
+
anyio==4.12.1
|
| 8 |
+
certifi==2026.1.4
|
| 9 |
+
charset-normalizer==3.4.7
|
| 10 |
+
click==8.3.1
|
| 11 |
+
contourpy==1.3.3
|
| 12 |
+
cycler==0.12.1
|
| 13 |
+
deepspeed==0.18.6
|
| 14 |
+
einops==0.8.2
|
| 15 |
+
filelock==3.23.0
|
| 16 |
+
fonttools==4.61.1
|
| 17 |
+
fsspec==2026.2.0
|
| 18 |
+
gitdb==4.0.12
|
| 19 |
+
GitPython==3.1.49
|
| 20 |
+
grpcio==1.78.0
|
| 21 |
+
h11==0.16.0
|
| 22 |
+
hf-xet==1.2.0
|
| 23 |
+
hjson==3.1.0
|
| 24 |
+
httpcore==1.0.9
|
| 25 |
+
httpx==0.28.1
|
| 26 |
+
huggingface_hub==1.4.1
|
| 27 |
+
idna==3.11
|
| 28 |
+
Jinja2==3.1.6
|
| 29 |
+
kiwisolver==1.4.9
|
| 30 |
+
Markdown==3.10.2
|
| 31 |
+
markdown-it-py==4.0.0
|
| 32 |
+
MarkupSafe==3.0.3
|
| 33 |
+
matplotlib==3.10.8
|
| 34 |
+
mdurl==0.1.2
|
| 35 |
+
mpmath==1.3.0
|
| 36 |
+
msgpack==1.1.2
|
| 37 |
+
networkx==3.6.1
|
| 38 |
+
ninja==1.13.0
|
| 39 |
+
numpy==2.4.2
|
| 40 |
+
nvidia-cublas-cu11==11.11.3.6
|
| 41 |
+
nvidia-cuda-cupti-cu11==11.8.87
|
| 42 |
+
nvidia-cuda-nvrtc-cu11==11.8.89
|
| 43 |
+
nvidia-cuda-runtime-cu11==11.8.89
|
| 44 |
+
nvidia-cudnn-cu11==9.1.0.70
|
| 45 |
+
nvidia-cufft-cu11==10.9.0.58
|
| 46 |
+
nvidia-curand-cu11==10.3.0.86
|
| 47 |
+
nvidia-cusolver-cu11==11.4.1.48
|
| 48 |
+
nvidia-cusparse-cu11==11.7.5.86
|
| 49 |
+
nvidia-nccl-cu11==2.21.5
|
| 50 |
+
nvidia-nvtx-cu11==11.8.86
|
| 51 |
+
opencv-python==4.13.0.92
|
| 52 |
+
opencv-python-headless==4.13.0.92
|
| 53 |
+
packaging==26.0
|
| 54 |
+
pillow==12.1.1
|
| 55 |
+
platformdirs==4.9.6
|
| 56 |
+
protobuf==6.33.5
|
| 57 |
+
psutil==7.2.2
|
| 58 |
+
py-cpuinfo==9.0.0
|
| 59 |
+
pycocotools==2.0.11
|
| 60 |
+
pydantic==2.12.5
|
| 61 |
+
pydantic_core==2.41.5
|
| 62 |
+
Pygments==2.19.2
|
| 63 |
+
pyparsing==3.3.2
|
| 64 |
+
python-dateutil==2.9.0.post0
|
| 65 |
+
PyYAML==6.0.3
|
| 66 |
+
regex==2026.1.15
|
| 67 |
+
requests==2.33.1
|
| 68 |
+
rich==14.3.2
|
| 69 |
+
safetensors==0.7.0
|
| 70 |
+
scipy==1.17.0
|
| 71 |
+
sentry-sdk==2.59.0
|
| 72 |
+
setuptools==82.0.0
|
| 73 |
+
shapely==2.1.2
|
| 74 |
+
shellingham==1.5.4
|
| 75 |
+
simsimd==6.5.16
|
| 76 |
+
six==1.17.0
|
| 77 |
+
smmap==5.0.3
|
| 78 |
+
stringzilla==4.6.0
|
| 79 |
+
sympy==1.14.0
|
| 80 |
+
tensorboard==2.20.0
|
| 81 |
+
tensorboard-data-server==0.7.2
|
| 82 |
+
tokenizers==0.22.2
|
| 83 |
+
torch==2.7.1+cu118
|
| 84 |
+
torchvision==0.22.1+cu118
|
| 85 |
+
tqdm==4.67.3
|
| 86 |
+
transformers==5.1.0
|
| 87 |
+
triton==3.3.1
|
| 88 |
+
typer==0.23.1
|
| 89 |
+
typer-slim==0.23.1
|
| 90 |
+
typing_extensions==4.15.0
|
| 91 |
+
typing-inspection==0.4.2
|
| 92 |
+
urllib3==2.6.3
|
| 93 |
+
wandb==0.26.1
|
| 94 |
+
Werkzeug==3.1.5
|
wandb/wandb/run-20260507_130026-3lo4j577/files/wandb-metadata.json
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"os": "Linux-5.10.0-218.0.0.mt20250120.565.mt2203sp4.x86_64-x86_64-with-glibc2.32",
|
| 3 |
+
"python": "CPython 3.11.14",
|
| 4 |
+
"startedAt": "2026-05-07T05:00:26.945273Z",
|
| 5 |
+
"args": [
|
| 6 |
+
"--config",
|
| 7 |
+
"/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/configs/trogeo_pi3_offline.yaml"
|
| 8 |
+
],
|
| 9 |
+
"program": "/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/train.py",
|
| 10 |
+
"codePath": "train.py",
|
| 11 |
+
"codePathLocal": "train.py",
|
| 12 |
+
"git": {
|
| 13 |
+
"remote": "git@github.com:cipual/CVOS-Code.git",
|
| 14 |
+
"commit": "69ac6ce26abfd5b5619ce59bf76b093bbf75f1cc"
|
| 15 |
+
},
|
| 16 |
+
"email": "hycd540@gmail.com",
|
| 17 |
+
"root": "/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs/wandb",
|
| 18 |
+
"host": "psx4524xrlkpndoc-worker-0",
|
| 19 |
+
"executable": "/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/location_v4/.venv/bin/python",
|
| 20 |
+
"cpu_count": 96,
|
| 21 |
+
"cpu_count_logical": 184,
|
| 22 |
+
"gpu": "NVIDIA H200",
|
| 23 |
+
"gpu_count": 8,
|
| 24 |
+
"disk": {
|
| 25 |
+
"/": {
|
| 26 |
+
"total": "53687091200",
|
| 27 |
+
"used": "121737216"
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"memory": {
|
| 31 |
+
"total": "1887436800000"
|
| 32 |
+
},
|
| 33 |
+
"gpu_nvidia": [
|
| 34 |
+
{
|
| 35 |
+
"name": "NVIDIA H200",
|
| 36 |
+
"memoryTotal": "150754820096",
|
| 37 |
+
"cudaCores": 16896,
|
| 38 |
+
"architecture": "Hopper",
|
| 39 |
+
"uuid": "GPU-e691af30-9e76-2280-b5cc-1276df37a4fb"
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"name": "NVIDIA H200",
|
| 43 |
+
"memoryTotal": "150754820096",
|
| 44 |
+
"cudaCores": 16896,
|
| 45 |
+
"architecture": "Hopper",
|
| 46 |
+
"uuid": "GPU-1c3e7100-2e19-234c-3046-f07e76b3d684"
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"name": "NVIDIA H200",
|
| 50 |
+
"memoryTotal": "150754820096",
|
| 51 |
+
"cudaCores": 16896,
|
| 52 |
+
"architecture": "Hopper",
|
| 53 |
+
"uuid": "GPU-45f60f31-9a59-e99b-da1c-eb7df5e0df4d"
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"name": "NVIDIA H200",
|
| 57 |
+
"memoryTotal": "150754820096",
|
| 58 |
+
"cudaCores": 16896,
|
| 59 |
+
"architecture": "Hopper",
|
| 60 |
+
"uuid": "GPU-96df27eb-a35a-2c2f-1024-455553308768"
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"name": "NVIDIA H200",
|
| 64 |
+
"memoryTotal": "150754820096",
|
| 65 |
+
"cudaCores": 16896,
|
| 66 |
+
"architecture": "Hopper",
|
| 67 |
+
"uuid": "GPU-d3d78141-29c8-e2ce-ce62-8cb199bbd05e"
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"name": "NVIDIA H200",
|
| 71 |
+
"memoryTotal": "150754820096",
|
| 72 |
+
"cudaCores": 16896,
|
| 73 |
+
"architecture": "Hopper",
|
| 74 |
+
"uuid": "GPU-ea15c218-130a-565f-058d-6cadc9ac3aa5"
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"name": "NVIDIA H200",
|
| 78 |
+
"memoryTotal": "150754820096",
|
| 79 |
+
"cudaCores": 16896,
|
| 80 |
+
"architecture": "Hopper",
|
| 81 |
+
"uuid": "GPU-76ee9c8e-bad5-8e3c-1766-c891bc14e07a"
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"name": "NVIDIA H200",
|
| 85 |
+
"memoryTotal": "150754820096",
|
| 86 |
+
"cudaCores": 16896,
|
| 87 |
+
"architecture": "Hopper",
|
| 88 |
+
"uuid": "GPU-25afd362-e436-a0d2-ad7f-c31a4a73a20f"
|
| 89 |
+
}
|
| 90 |
+
],
|
| 91 |
+
"cudaVersion": "12.4",
|
| 92 |
+
"writerId": "n66y3yolechf07hvu2i2dxfxcxu3un0q"
|
| 93 |
+
}
|
wandb/wandb/run-20260507_130026-3lo4j577/files/wandb-summary.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"train/iter_geo_loss":0.03693510591983795,"train/epoch_accu50":0.9428702774991642,"train/iter_cls_loss":0.399825781583786,"val/accu25":0.8528502173186225,"val/mean_iou":0.6021959871721284,"train/epoch_loss":0.619293495731516,"_runtime":84216.218279293,"val/accu_center":0.44391507856904044,"lr":1.0000000000000002e-06,"train/epoch_cls_loss":0.43923675313002525,"_wandb":{"runtime":84216},"val/accu50":0.7109662320294216,"train/epoch_accu_center":0.8237995235707122,"val/mean_iou_epoch_end":0.6021959871721284,"val/accu50_epoch_end":0.7109662320294216,"train/iter_accu_center":0.75,"train/epoch_geo_loss":0.04564429601127097,"val/accu_center_epoch_end":0.44391507856904044,"train/iter_accu50":0.8333333730697632,"train/iter_iou":0.7486404180526733,"val/accu25_epoch_end":0.8528502173186225,"train/epoch_iou":0.7757921489892856,"_step":49850,"_timestamp":1.7782141200428004e+09,"train/iter_loss":0.584656834602356}
|
wandb/wandb/run-20260507_130026-3lo4j577/logs/debug-internal.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
wandb/wandb/run-20260507_130026-3lo4j577/logs/debug.log
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2026-05-07 13:00:27,076 INFO MainThread:4596 [wandb_setup.py:_flush():81] Current SDK version is 0.26.1
|
| 2 |
+
2026-05-07 13:00:27,079 INFO MainThread:4596 [wandb_setup.py:_flush():81] Configure stats pid to 4596
|
| 3 |
+
2026-05-07 13:00:27,082 INFO MainThread:4596 [wandb_setup.py:_flush():81] Loading settings from environment variables
|
| 4 |
+
2026-05-07 13:00:27,087 INFO MainThread:4596 [wandb_init.py:setup_run_log_directory():723] Logging user logs to /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs/wandb/wandb/run-20260507_130026-3lo4j577/logs/debug.log
|
| 5 |
+
2026-05-07 13:00:27,094 INFO MainThread:4596 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to /mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs/wandb/wandb/run-20260507_130026-3lo4j577/logs/debug-internal.log
|
| 6 |
+
2026-05-07 13:00:27,099 INFO MainThread:4596 [wandb_init.py:init():850] calling init triggers
|
| 7 |
+
2026-05-07 13:00:27,101 INFO MainThread:4596 [wandb_init.py:init():855] wandb.init called with sweep_config: {}
|
| 8 |
+
config: {'config': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/configs/trogeo_pi3_offline.yaml', 'gpu': '0,1,2,3,4,5,6,7', 'num_workers': 3, 'max_epoch': 25, 'lr': 0.0001, 'batch_size': 12, 'emb_size': 768, 'img_size': 518, 'data_root': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/data', 'data_name': 'CVOGL_DroneAerial', 'dataset_type': 'eccv', 'train_json': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/train_all.json', 'val_json': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/val_all.json', 'test_json': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CMA-Loc/test_all.json', 'backbone_type': 'pi3', 'pi3_pretrain': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/location_v4/checkpoints_offline/pi3_model.safetensors', 'pi3_decoder_size': 'large', 'freeze_encoder': True, 'freeze_decoder': False, 'pretrain': '', 'resume': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs', 'print_freq': 10, 'savename': 'trogeo_pi3_eccv', 'output_dir': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs', 'seed': 2024, 'beta': 1.0, 'pos_weight': 15.0, 'test': False, 'val': False, 'wandb': True, 'wandb_project': 'CVOS-Code', 'wandb_dir': '/mnt/dolphinfs/ssd_pool/docker/user/hadoop-nlp-sh02/hadoop-aipnlp/EVA/yangheqing/workspace/CVOS-Code/outputs/wandb', 'use_amp': True, 'use_tf32': True, 'persistent_workers': True, 'prefetch_factor': 4, 'rank': 0, 'world_size': 8, 'local_rank': 0, 'anchors': '18,20, 36,40, 48,108, 64,64, 96,40, 96,88, 124,140, 198,171, 275,286', 'train_loader_len': 1994, '_wandb': {}}
|
| 9 |
+
2026-05-07 13:00:27,104 INFO MainThread:4596 [wandb_init.py:init():898] starting backend
|
| 10 |
+
2026-05-07 13:00:30,625 INFO MainThread:4596 [wandb_init.py:init():913] sending inform_init request
|
| 11 |
+
2026-05-07 13:00:34,851 INFO MainThread:4596 [wandb_init.py:init():918] backend started and connected
|
| 12 |
+
2026-05-07 13:00:34,858 INFO MainThread:4596 [wandb_init.py:init():988] updated telemetry
|
| 13 |
+
2026-05-07 13:00:35,346 INFO MainThread:4596 [wandb_init.py:init():1011] communicating run to backend with 90.0 second timeout
|
| 14 |
+
2026-05-07 13:00:36,116 INFO MainThread:4596 [wandb_init.py:init():1056] starting run threads in backend
|
| 15 |
+
2026-05-07 13:00:37,271 INFO MainThread:4596 [wandb_run.py:_console_start():2554] atexit reg
|
| 16 |
+
2026-05-07 13:00:37,275 INFO MainThread:4596 [wandb_run.py:_redirect():2403] redirect: wrap_raw
|
| 17 |
+
2026-05-07 13:00:37,277 INFO MainThread:4596 [wandb_run.py:_redirect():2472] Wrapping output streams.
|
| 18 |
+
2026-05-07 13:00:37,279 INFO MainThread:4596 [wandb_run.py:_redirect():2495] Redirects installed.
|
| 19 |
+
2026-05-07 13:00:37,329 INFO MainThread:4596 [wandb_init.py:init():1094] run started, returning control to user process
|
| 20 |
+
2026-05-08 12:24:12,317 INFO MainThread:4596 [wandb_run.py:_finish():2321] finishing run hycd540-beihang-university/CVOS-Code/3lo4j577
|
| 21 |
+
2026-05-08 12:24:12,337 INFO MainThread:4596 [wandb_run.py:_atexit_cleanup():2520] got exitcode: 0
|
| 22 |
+
2026-05-08 12:24:12,343 INFO MainThread:4596 [wandb_run.py:_restore():2502] restore
|
| 23 |
+
2026-05-08 12:24:12,345 INFO MainThread:4596 [wandb_run.py:_restore():2508] restore done
|
| 24 |
+
2026-05-08 12:24:15,240 INFO MainThread:4596 [wandb_run.py:_footer_sync_info():3889] logging synced files
|
wandb/wandb/run-20260507_130026-3lo4j577/run-3lo4j577.wandb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66c87c9e0521decdb5455f09b6a7c9600049e3f1371db89f4a79b89b9f6452c0
|
| 3 |
+
size 63687309
|