Instructions to use qubvel-hf/microsoft-conditional-detr-resnet-50-finetuned-10k-cppe5-manual-pad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qubvel-hf/microsoft-conditional-detr-resnet-50-finetuned-10k-cppe5-manual-pad with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="qubvel-hf/microsoft-conditional-detr-resnet-50-finetuned-10k-cppe5-manual-pad")# Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("qubvel-hf/microsoft-conditional-detr-resnet-50-finetuned-10k-cppe5-manual-pad") model = AutoModelForObjectDetection.from_pretrained("qubvel-hf/microsoft-conditional-detr-resnet-50-finetuned-10k-cppe5-manual-pad", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 100.0, | |
| "eval_loss": 1.2867472171783447, | |
| "eval_map": 0.3142, | |
| "eval_map_50": 0.6067, | |
| "eval_map_75": 0.2769, | |
| "eval_map_Coverall": 0.5532, | |
| "eval_map_Face_Shield": 0.3268, | |
| "eval_map_Gloves": 0.1937, | |
| "eval_map_Goggles": 0.1922, | |
| "eval_map_Mask": 0.3053, | |
| "eval_map_large": 0.5119, | |
| "eval_map_medium": 0.2662, | |
| "eval_map_small": 0.1689, | |
| "eval_mar_1": 0.3035, | |
| "eval_mar_10": 0.4412, | |
| "eval_mar_100": 0.4638, | |
| "eval_mar_100_Coverall": 0.6559, | |
| "eval_mar_100_Face_Shield": 0.4886, | |
| "eval_mar_100_Gloves": 0.3603, | |
| "eval_mar_100_Goggles": 0.3892, | |
| "eval_mar_100_Mask": 0.4249, | |
| "eval_mar_large": 0.6548, | |
| "eval_mar_medium": 0.4191, | |
| "eval_mar_small": 0.2652, | |
| "eval_runtime": 6.5804, | |
| "eval_samples_per_second": 22.795, | |
| "eval_steps_per_second": 2.887, | |
| "test_loss": 1.007723093032837, | |
| "test_map": 0.4282, | |
| "test_map_50": 0.8092, | |
| "test_map_75": 0.3479, | |
| "test_map_Coverall": 0.6154, | |
| "test_map_Face_Shield": 0.5313, | |
| "test_map_Gloves": 0.3247, | |
| "test_map_Goggles": 0.247, | |
| "test_map_Mask": 0.4228, | |
| "test_map_large": 0.6798, | |
| "test_map_medium": 0.2881, | |
| "test_map_small": 0.4374, | |
| "test_mar_1": 0.3426, | |
| "test_mar_10": 0.5385, | |
| "test_mar_100": 0.5519, | |
| "test_mar_100_Coverall": 0.7067, | |
| "test_mar_100_Face_Shield": 0.6647, | |
| "test_mar_100_Gloves": 0.4426, | |
| "test_mar_100_Goggles": 0.4281, | |
| "test_mar_100_Mask": 0.5173, | |
| "test_mar_large": 0.7432, | |
| "test_mar_medium": 0.4023, | |
| "test_mar_small": 0.4868, | |
| "test_runtime": 3.5844, | |
| "test_samples_per_second": 8.091, | |
| "test_steps_per_second": 8.091, | |
| "total_flos": 2.386038004919996e+19, | |
| "train_loss": 0.0, | |
| "train_runtime": 3.3486, | |
| "train_samples_per_second": 25383.788, | |
| "train_steps_per_second": 3195.371 | |
| } |