"device": "npu:0",
"input_shape": [
"pooler_output_shape": [
"throughput_images_per_sec": 107.09043558188225,
Device: npu:0
Output last_hidden_state shape: torch.Size([1, 201, 768])
Output pooler_output (CLS embedding) shape: torch.Size([1, 768])
Throughput: 107.09 images/s

.
├── .gitignore
├── README.md
├── assets/README.md
├── assets/accuracy_eval_result.png
├── assets/env_check.png
├── assets/git_submit_result.png
├── assets/inference_result.png
├── assets/performance_eval_result.png
├── eval/eval_accuracy.py
├── eval/eval_performance.py
├── inference.py
├── logs/accuracy_eval.log
├── logs/env_check.log
├── logs/inference.log
├── logs/model_check.log
├── logs/performance_eval.log
├── requirements.txt
├── results/accuracy_eval.json
├── results/env_info.json
├── results/inference_result.json
└── results/performance_eval.json

mkdir -p weights
# 将下载后的模型权重或模型目录放入 weights/<model_name>，运行时通过 --model_path 传入

pip install -r requirements.txt
python inference.py --model_path <model_path> --image_path <image.jpg> --device npu

python eval/eval_accuracy.py --model_path <model_path> --device npu
python eval/eval_performance.py --model_path <model_path> --device npu

python eval/eval_accuracy.py --model_path <model_path> --device npu
python eval/eval_performance.py --model_path <model_path> --device npu

python inference.py --help
python inference.py --model_path <model_path> --image_path <image.jpg> --device npu

[LOG_WARNING] can not create directory, directory: /home/atomgit/ascend/log, possible reason: No such file or directory.path string is NULLpath string is NULL{
  "os": "Linux-5.10.0-182.0.0.95.r2220_156.hce2.aarch64-aarch64-with-glibc2.35",
  "python_version": "3.11.14",
  "arch": "aarch64",
  "torch_version": "2.9.0+cpu",
  "torch_npu_version": "2.9.0.post1+gitee7ba04",
  "transformers_version": "4.57.6",
  "accelerate_version": "1.13.0",
  "numpy_version": "1.26.4",
  "pillow_version": "12.2.0",
  "npu_available": true,
  "npu_count": 2,
  "npu_device_name": "Ascend910_9362",
  "npu_error": "'torch_npu._C._NPUDeviceProperties' object has no attribute 'total_mem'",
  "cann_path": "/usr/local/Ascend/cann-8.5.1",
  "ascend_toolkit_home": "/usr/local/Ascend/cann-8.5.1",
  "soc_version": "ascend910_9391",
  "npu_smi": "+------------------------------------------------------------------------------------------------+\n| npu-smi 25.5.2                   Version: 25.5.2                                               |\n+---------------------------+---------------+----------------------------------------------------+\n| NPU   Name                | Health        | Power(W)    Temp(C)           Hugepages-Usage(page)|\n| Chip  Phy-ID              | Bus-Id        | AICore(%)   Memory-Usage(MB)  HBM-Usage(MB)        |\n+===========================+===============+====================================================+\n| 5     Ascend910           | OK            | 186.9       46                0    / 0             |\n| 0     10                  | 0000:0B:00.0  | 0           0    / 0          3158 / 65536         |\n+------------------------------------------------------------------------------------------------+\n| 5     Ascend910           | OK            | -           47                0    / 0             |\n| 1     11                  | 0000:0A:00.0  | 0           0    / 0          2870 / 65536         |\n+===========================+===============+====================================================+\n+---------------------------+---------------+----------------------------------------------------+\n| NPU     Chip              | Process id    | Process name             | Process memory(MB)      |\n+===========================+===============+====================================================+\n| 5       0                 | 14910         | python3                  | 110                     |\n+===========================+===============+====================================================+\n"
}

{
  "os": "Linux-5.10.0-182.0.0.95.r2220_156.hce2.aarch64-aarch64-with-glibc2.35",
  "python_version": "3.11.14",
  "arch": "aarch64",
  "torch_version": "2.9.0+cpu",
  "torch_npu_version": "2.9.0.post1+gitee7ba04",
  "transformers_version": "4.57.6",
  "accelerate_version": "1.13.0",
  "numpy_version": "1.26.4",
  "pillow_version": "12.2.0",
  "npu_available": true,
  "npu_count": 2,
  "npu_device_name": "Ascend910_9362",
  "npu_error": "'torch_npu._C._NPUDeviceProperties' object has no attribute 'total_mem'",
  "cann_path": "/usr/local/Ascend/cann-8.5.1",
  "ascend_toolkit_home": "/usr/local/Ascend/cann-8.5.1",
  "soc_version": "ascend910_9391",
  "npu_smi": "+------------------------------------------------------------------------------------------------+\n| npu-smi 25.5.2                   Version: 25.5.2                                               |\n+---------------------------+---------------+----------------------------------------------------+\n| NPU   Name                | Health        | Power(W)    Temp(C)           Hugepages-Usage(page)|\n| Chip  Phy-ID              | Bus-Id        | AICore(%)   Memory-Usage(MB)  HBM-Usage(MB)        |\n+===========================+===============+====================================================+\n| 5     Ascend910           | OK            | 186.9       46                0    / 0             |\n| 0     10                  | 0000:0B:00.0  | 0           0    / 0          3158 / 65536         |\n+------------------------------------------------------------------------------------------------+\n| 5     Ascend910           | OK            | -           47                0    / 0             |\n| 1     11                  | 0000:0A:00.0  | 0           0    / 0          2870 / 65536         |\n+===========================+===============+====================================================+\n+---------------------------+---------------+----------------------------------------------------+\n| NPU     Chip              | Process id    | Process name             | Process memory(MB)      |\n+===========================+===============+====================================================+\n| 5       0                 | 14910         | python3                  | 110                     |\n+===========================+===============+====================================================+\n"
}

Model Check Log
================
Model: facebook/dinov3-vitb16-pretrain-lvd1689m
Source: ModelScope (snapshot_download)
Path: /tmp/ms_cache/facebook/dinov3-vitb16-pretrain-lvd1689m

Files:
- config.json: OK (DINOv3ViTConfig, hidden_size=768, num_layers=12)
- model.safetensors: OK (342MB)
- preprocessor_config.json: OK (224x224, ImageNet normalization)
- README.md: OK
- LICENSE.md: OK

Model Architecture: DINOv3ViTModel
- hidden_size: 768
- num_attention_heads: 12
- num_hidden_layers: 12
- patch_size: 16
- image_size: 224
- num_register_tokens: 4
- model_type: dinov3_vit

CPU inference test: PASS
- Output: last_hidden_state [1, 201, 768], pooler_output [1, 768]

============================================================
DINOv3 ViT-B/16 Inference - Ascend NPU
============================================================
Device: npu:0
Dtype: float32
NPU available: True (count: 2)
Model path: /tmp/ms_cache/facebook/dinov3-vitb16-pretrain-lvd1689m

Loading model...
Model loaded in 4.03s

Loading image: random test image
Image size: (224, 224)
Input shape: torch.Size([1, 3, 224, 224])

Warmup run...

Running inference...

============================================================
Inference Results
============================================================
Output last_hidden_state shape: torch.Size([1, 201, 768])
Output pooler_output (CLS embedding) shape: torch.Size([1, 768])

CLS Embedding (first 10 values): [0.5102764368057251, 0.6638539433479309, 0.47167640924453735, -0.9210608601570129, -0.07699183374643326, -0.5380324125289917, -1.1415667533874512, 0.8834766149520874, 0.36170053482055664, -0.94185471534729]
CLS Embedding stats:
  mean: -0.006348
  std:  0.610877
  min:  -2.102153
  max:  2.061325
  norm: 16.930029

Patch Tokens shape: (196, 768)
Patch Tokens stats:
  mean: 0.001928
  std:  0.452366

============================================================
Performance
============================================================
Inference time: 9.34 ms
Throughput: 107.09 images/s
Batch size: 1

Device: Ascend910_9362
Device memory: 61.3 GB

PyTorch version: 2.9.0+cpu
torch_npu version: 2.9.0.post1+gitee7ba04

{
  "model": "facebook/dinov3-vitb16-pretrain-lvd1689m",
  "device": "npu:0",
  "dtype": "float32",
  "input_shape": [
    1,
    3,
    224,
    224
  ],
  "last_hidden_state_shape": [
    1,
    201,
    768
  ],
  "pooler_output_shape": [
    1,
    768
  ],
  "cls_embedding_first10": [
    0.5102764368057251,
    0.6638539433479309,
    0.47167640924453735,
    -0.9210608601570129,
    -0.07699183374643326,
    -0.5380324125289917,
    -1.1415667533874512,
    0.8834766149520874,
    0.36170053482055664,
    -0.94185471534729
  ],
  "cls_embedding_mean": -0.006347866263240576,
  "cls_embedding_std": 0.6108768582344055,
  "inference_time_ms": 9.337902069091797,
  "throughput_images_per_sec": 107.09043558188225,
  "npu_available": true,
  "npu_count": 2
}

============================================================
DINOv3 ViT-B/16 Accuracy Evaluation
CPU Reference vs NPU
============================================================

Loading CPU reference model...
Loading NPU model...

Generating 5 test images...

--- Sample 1/5 ---
  CLS Cosine Sim:     0.99999361
  CLS MAE:            0.00173097
  CLS Max Abs Err %:  0.3456%
  Hidden Cosine Sim:  0.99999520
  Hidden MAE:         0.00108265
  Hidden Max Abs Err%:0.0449%

--- Sample 2/5 ---
  CLS Cosine Sim:     0.99999374
  CLS MAE:            0.00167155
  CLS Max Abs Err %:  0.3371%
  Hidden Cosine Sim:  0.99999628
  Hidden MAE:         0.00106982
  Hidden Max Abs Err%:0.0554%

--- Sample 3/5 ---
  CLS Cosine Sim:     0.99999340
  CLS MAE:            0.00173932
  CLS Max Abs Err %:  0.3643%
  Hidden Cosine Sim:  0.99999582
  Hidden MAE:         0.00108726
  Hidden Max Abs Err%:0.0607%

--- Sample 4/5 ---
  CLS Cosine Sim:     0.99999327
  CLS MAE:            0.00174950
  CLS Max Abs Err %:  0.3864%
  Hidden Cosine Sim:  0.99999592
  Hidden MAE:         0.00111066
  Hidden Max Abs Err%:0.0602%

--- Sample 5/5 ---
  CLS Cosine Sim:     0.99999352
  CLS MAE:            0.00172203
  CLS Max Abs Err %:  0.3576%
  Hidden Cosine Sim:  0.99999548
  Hidden MAE:         0.00108854
  Hidden Max Abs Err%:0.0448%

============================================================
Summary
============================================================
Num samples: 5

CLS Embedding (pooler_output):
  Mean Cosine Similarity:       0.99999351
  Mean Absolute Error (MAE):    0.00172267
  Max Abs Error (% of ref max): 0.3864%

Hidden States (last_hidden_state):
  Mean Cosine Similarity:       0.99999574
  Mean Absolute Error (MAE):    0.00108779
  Max Abs Error (% of ref max): 0.0607%

Pass Criteria (feature extraction standard):
  Cosine Similarity > 0.9999:   PASS (0.999994, 0.999996)
  Max Abs Error < 1% of ref:    PASS (0.3864%, 0.0607%)

Overall Accuracy Test: PASS

Results saved to results/accuracy_eval.json

{
  "model": "facebook/dinov3-vitb16-pretrain-lvd1689m",
  "device": "npu:0",
  "dtype": "float32",
  "num_samples": 5,
  "cls_embedding_mean_cosine_similarity": 0.9999935100423747,
  "cls_embedding_mean_absolute_error": 0.0017226734664291144,
  "cls_embedding_max_abs_error_pct": 0.3863671328872442,
  "hidden_states_mean_cosine_similarity": 0.9999957420834166,
  "hidden_states_mean_absolute_error": 0.0010877869557589293,
  "hidden_states_max_abs_error_pct": 0.060721178306266665,
  "pass_criteria": {
    "cosine_similarity_gt_09999": true,
    "max_abs_error_lt_1pct": true
  },
  "passed": true,
  "per_sample_results": [
    {
      "sample": 1,
      "cls_cosine_similarity": 0.9999936124485376,
      "hidden_cosine_similarity": 0.9999952001063316,
      "cls_mae": 0.0017309744143858552,
      "cls_max_abs_error": 0.007264852523803711,
      "cls_max_abs_error_pct": 0.34559275954961777,
      "hidden_mae": 0.0010826531797647476,
      "hidden_max_abs_error": 0.007970809936523438,
      "hidden_max_abs_error_pct": 0.044928232091479
    },
    {
      "sample": 2,
      "cls_cosine_similarity": 0.9999937432478961,
      "hidden_cosine_similarity": 0.9999962841768066,
      "cls_mae": 0.0016715462552383542,
      "cls_max_abs_error": 0.007165037095546722,
      "cls_max_abs_error_pct": 0.3371236380189657,
      "hidden_mae": 0.0010698226979002357,
      "hidden_max_abs_error": 0.00982046127319336,
      "hidden_max_abs_error_pct": 0.05538108525797725
    },
    {
      "sample": 3,
      "cls_cosine_similarity": 0.9999934030519578,
      "hidden_cosine_similarity": 0.9999958235962666,
      "cls_mae": 0.0017393153393641114,
      "cls_max_abs_error": 0.007513284683227539,
      "cls_max_abs_error_pct": 0.36434633657336235,
      "hidden_mae": 0.0010872612474486232,
      "hidden_max_abs_error": 0.010775089263916016,
      "hidden_max_abs_error_pct": 0.060721178306266665
    },
    {
      "sample": 4,
      "cls_cosine_similarity": 0.9999932705273146,
      "hidden_cosine_similarity": 0.999995923863986,
      "cls_mae": 0.0017495034262537956,
      "cls_max_abs_error": 0.007689923048019409,
      "cls_max_abs_error_pct": 0.3863671328872442,
      "hidden_mae": 0.0011106599122285843,
      "hidden_max_abs_error": 0.010659217834472656,
      "hidden_max_abs_error_pct": 0.06019209395162761
    },
    {
      "sample": 5,
      "cls_cosine_similarity": 0.9999935209361668,
      "hidden_cosine_similarity": 0.9999954786736922,
      "cls_mae": 0.0017220278969034553,
      "cls_max_abs_error": 0.007261514663696289,
      "cls_max_abs_error_pct": 0.3576264716684818,
      "hidden_mae": 0.0010885377414524555,
      "hidden_max_abs_error": 0.0079498291015625,
      "hidden_max_abs_error_pct": 0.044762989273294806
    }
  ]
}

============================================================
DINOv3 ViT-B/16 Performance Evaluation
============================================================

Loading model to npu...
Batch size: 1
Input shape: torch.Size([1, 3, 224, 224])
Device: npu
Dtype: float32

Memory before warmup: allocated=327.4MB, reserved=382.0MB

Warmup: 3 iterations...
Memory after warmup: allocated=328.0MB, reserved=418.0MB

Timed runs: 10 iterations...
  Run 1: 8.56 ms
  Run 2: 8.55 ms
  Run 3: 8.54 ms
  Run 4: 8.50 ms
  Run 5: 8.80 ms
  Run 6: 8.62 ms
  Run 7: 8.62 ms
  Run 8: 8.61 ms
  Run 9: 8.22 ms
  Run 10: 8.11 ms

============================================================
Performance Results
============================================================
Batch size: 1
Input shape: [1, 3, 224, 224]
Num runs: 10
Avg latency: 8.51 ms
Std latency: 0.19 ms
Min latency: 8.11 ms
Max latency: 8.80 ms
Median latency: 8.55 ms
Throughput: 117.45 images/s
Peak NPU memory: allocated=328.6MB, reserved=418.0MB
Device: Ascend910_9362 (61.3 GB)
PyTorch: 2.9.0+cpu
torch_npu: 2.9.0.post1+gitee7ba04

Results saved to results/performance_eval.json

{
  "model": "facebook/dinov3-vitb16-pretrain-lvd1689m",
  "device": "npu",
  "dtype": "float32",
  "batch_size": 1,
  "image_size": 224,
  "input_shape": [
    1,
    3,
    224,
    224
  ],
  "warmup": 3,
  "num_runs": 10,
  "avg_latency_ms": 8.514189720153809,
  "std_latency_ms": 0.18973333298118578,
  "min_latency_ms": 8.114337921142578,
  "max_latency_ms": 8.79526138305664,
  "median_latency_ms": 8.553028106689453,
  "throughput_images_per_sec": 117.45098862818564,
  "peak_npu_memory_mb": {
    "allocated_mb": 328.62744140625,
    "reserved_mb": 418.0
  },
  "all_runs_ms": [
    8.55875015258789,
    8.547306060791016,
    8.544921875,
    8.498668670654297,
    8.79526138305664,
    8.6212158203125,
    8.624553680419922,
    8.611917495727539,
    8.224964141845703,
    8.114337921142578
  ]
}