Instructions to use mobilint/DeiT_Base_Patch16_384 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Mobilint
How to use mobilint/DeiT_Base_Patch16_384 with Mobilint:
# pip install mblt-model-zoo from mblt_model_zoo.vision import MBLT_Engine model = MBLT_Engine( model_cls="DeiT_Base_Patch16_384", model_type="DEFAULT", model_path="", core_mode="global8", ) try: image = model.preprocess("path/to/image.jpg") output = model(image) result = model.postprocess(output) finally: model.dispose() - Notebooks
- Google Colab
- Kaggle
DeiT_Base_Patch16_384
aries-rb/ holds the MXQ reproduced from the published arxiv folder (https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/DeiT_Base_Patch16_384). It was compiled by qbcompiler 1.3.0 in the image mobilint/qbcompiler:1.3-cuda12.8.1-ubuntu22.04 (sha256:6ad69aaa9581487ac6a1864b88d4c2179c7a4a486a3ab1ac376dbdfe763415e7) with --inference-scheme single, so it supports the core mode(s) single only.
It was evaluated with qbruntime 1.5.0 in async inference mode on imagenet (50000 samples): top1_accuracy 0.83106, top5_accuracy 0.9636. Only the evaluated core mode was measured.
SHA-256: 97bb353da7590dddb34f6cd6cb0bc3d13912efd1ccb5a1c5473f954f2867b7f2 (92362810 bytes). Verify a download with sha256sum <file>.mxq and compare the digest with this value and with aries-rb/metadata.json.
aries-rb/best_result.json contains legacy build values and is retained for mblt-vision-python compile defaults. The legacy aries/ directory was removed; mblt-model-zoo <= 2.12 must pin an older revision.
{
"schema_version": 2,
"model": "DeiT_Base_Patch16_384",
"variant": "baseline",
"qbcompiler": "1.3.0",
"qbruntime": "1.5.0",
"compile": {
"image_tag": "1.3-cuda12.8.1-ubuntu22.04",
"image_digest": "sha256:6ad69aaa9581487ac6a1864b88d4c2179c7a4a486a3ab1ac376dbdfe763415e7",
"inference_scheme": "single",
"device": "gpu"
},
"evaluation": {
"dataset": "imagenet",
"sample_count": 50000,
"primary": {
"top1_accuracy": 0.83106
},
"secondary": {
"top5_accuracy": 0.9636
},
"protocol": null,
"eval_data_identity": null,
"identity_audit": "absent",
"inference_mode": "async",
"image_tag": "1.3-cpu-ubuntu22.04",
"image_digest": "sha256:7c25b894fc0807acdf27f15c61b910b96dc66d3f5d97e04b595b2d7a8008e77c"
},
"retention_percent": {
"top1_accuracy": 100.0
},
"content_sha256": "8ca79726dffda9eee539e70b0595cc56109fa50750cca2de8b336c6518847fe6",
"attempt_id": "DeiT_Base_Patch16_384-jinman-20261017t150509-d372a",
"superseded_attempt_ids": [],
"sha256": "97bb353da7590dddb34f6cd6cb0bc3d13912efd1ccb5a1c5473f954f2867b7f2",
"format": "MXQv7",
"supported_modes": [
"single"
],
"size": 92362810,
"ops_commits": {
"selection": "9c9a469c2a5f34dd9650f972b289e1bfdf438c27"
},
"arxiv_folder": "https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/DeiT_Base_Patch16_384",
"publication": {
"status": "public",
"reason": "approved"
}
}
- Downloads last month
- 44
Model tree for mobilint/DeiT_Base_Patch16_384
Base model
timm/deit_base_patch16_384.fb_in1k