Instructions to use TheSleepyJo/mobilevitv2_fold_5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheSleepyJo/mobilevitv2_fold_5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="TheSleepyJo/mobilevitv2_fold_5") 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("TheSleepyJo/mobilevitv2_fold_5") model = AutoModelForImageClassification.from_pretrained("TheSleepyJo/mobilevitv2_fold_5") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "apple/mobilevitv2-1.0-imagenet1k-256", | |
| "architectures": [ | |
| "MobileViTV2ForImageClassification" | |
| ], | |
| "aspp_dropout_prob": 0.1, | |
| "aspp_out_channels": 512, | |
| "atrous_rates": [ | |
| 6, | |
| 12, | |
| 18 | |
| ], | |
| "attn_dropout": 0.0, | |
| "base_attn_unit_dims": [ | |
| 128, | |
| 192, | |
| 256 | |
| ], | |
| "classifier_dropout_prob": 0.1, | |
| "conv_kernel_size": 3, | |
| "expand_ratio": 2.0, | |
| "ffn_dropout": 0.0, | |
| "ffn_multiplier": 2, | |
| "hidden_act": "swish", | |
| "id2label": { | |
| "0": "fresh", | |
| "1": "most_fresh", | |
| "2": "not_fresh", | |
| "3": "spoiled" | |
| }, | |
| "image_size": 256, | |
| "initializer_range": 0.02, | |
| "label2id": { | |
| "fresh": "0", | |
| "most_fresh": "1", | |
| "not_fresh": "2", | |
| "spoiled": "3" | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "mlp_ratio": 2.0, | |
| "model_type": "mobilevitv2", | |
| "n_attn_blocks": [ | |
| 2, | |
| 4, | |
| 3 | |
| ], | |
| "num_channels": 3, | |
| "output_stride": 32, | |
| "patch_size": 2, | |
| "problem_type": "single_label_classification", | |
| "semantic_loss_ignore_index": 255, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.34.1", | |
| "width_multiplier": 1.0 | |
| } | |