Instructions to use tanganke/convnext-base-224_kmnist_sgd_batch-size-64_lr-0.01_steps-4000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tanganke/convnext-base-224_kmnist_sgd_batch-size-64_lr-0.01_steps-4000 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="tanganke/convnext-base-224_kmnist_sgd_batch-size-64_lr-0.01_steps-4000") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("tanganke/convnext-base-224_kmnist_sgd_batch-size-64_lr-0.01_steps-4000") model = AutoModelForImageClassification.from_pretrained("tanganke/convnext-base-224_kmnist_sgd_batch-size-64_lr-0.01_steps-4000", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from tanganke/convnext-base-224_kmnist_sgd_batch-size-64_lr-0.01_steps-4000: direct link, hf CLI and curl.
- Browser
- Download file 1.04 kB
-
https://huggingface.co/tanganke/convnext-base-224_kmnist_sgd_batch-size-64_lr-0.01_steps-4000/resolve/main/config.json
- Command line
-
hf download hf://tanganke/convnext-base-224_kmnist_sgd_batch-size-64_lr-0.01_steps-4000/config.json
-
curl -L -o config.json https://huggingface.co/tanganke/convnext-base-224_kmnist_sgd_batch-size-64_lr-0.01_steps-4000/resolve/main/config.json
1.04 kB
| { | |
| "architectures": [ | |
| "ConvNextForImageClassification" | |
| ], | |
| "depths": [ | |
| 3, | |
| 3, | |
| 27, | |
| 3 | |
| ], | |
| "drop_path_rate": 0.0, | |
| "dtype": "float32", | |
| "hidden_act": "gelu", | |
| "hidden_sizes": [ | |
| 128, | |
| 256, | |
| 512, | |
| 1024 | |
| ], | |
| "id2label": { | |
| "0": "\u304a", | |
| "1": "\u304d", | |
| "2": "\u3059", | |
| "3": "\u3064", | |
| "4": "\u306a", | |
| "5": "\u306f", | |
| "6": "\u307e", | |
| "7": "\u3084", | |
| "8": "\u308c", | |
| "9": "\u3092" | |
| }, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "label2id": { | |
| "\u304a": 0, | |
| "\u304d": 1, | |
| "\u3059": 2, | |
| "\u3064": 3, | |
| "\u306a": 4, | |
| "\u306f": 5, | |
| "\u307e": 6, | |
| "\u3084": 7, | |
| "\u308c": 8, | |
| "\u3092": 9 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "layer_scale_init_value": 1e-06, | |
| "model_type": "convnext", | |
| "num_channels": 3, | |
| "num_stages": 4, | |
| "out_features": [ | |
| "stage4" | |
| ], | |
| "out_indices": [ | |
| 4 | |
| ], | |
| "patch_size": 4, | |
| "stage_names": [ | |
| "stem", | |
| "stage1", | |
| "stage2", | |
| "stage3", | |
| "stage4" | |
| ], | |
| "transformers_version": "4.57.3" | |
| } | |