Instructions to use tanganke/convnext-base-224_eurosat_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_eurosat_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_eurosat_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_eurosat_sgd_batch-size-64_lr-0.01_steps-4000") model = AutoModelForImageClassification.from_pretrained("tanganke/convnext-base-224_eurosat_sgd_batch-size-64_lr-0.01_steps-4000", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| [2026-01-06 05:10:49,030][fusion_bench.programs.fusion_program][INFO] - Running the model fusion program. | |
| [2026-01-06 05:10:49,032][fusion_bench.programs.fusion_program][INFO] - loading model pool | |
| [2026-01-06 05:10:51,173][fusion_bench.programs.fusion_program][INFO] - loading method | |
| [2026-01-06 05:10:51,223][fusion_bench.method.classification.image_classification_finetune][INFO] - Training interval: step | |
| [2026-01-06 05:10:51,224][fusion_bench.method.classification.image_classification_finetune][INFO] - Max epochs: -1, max steps: 4000 | |
| [2026-01-06 05:10:51,225][fusion_bench.programs.fusion_program][INFO] - loading task pool | |
| [2026-01-06 05:10:52,534][fusion_bench.method.classification.image_classification_finetune][INFO] - Number of classes for dataset eurosat: 10 | |
| [2026-01-06 05:10:52,545][datasets.load][WARNING] - Using the latest cached version of the dataset since tanganke/eurosat couldn't be found on the Hugging Face Hub (offline mode is enabled). | |
| [2026-01-06 05:10:52,553][datasets.packaged_modules.cache.cache][WARNING] - Found the latest cached dataset configuration 'default' at /data/dataset/datasets/tanganke___eurosat/default/0.0.0/43750fc422c7fbd4289e2df3f7473617a5937acc (last modified on Mon Jan 5 04:16:47 2026). | |
| [2026-01-06 05:10:52,802][fusion_bench.method.classification.image_classification_finetune][INFO] - Training dataset size: 21600 | |
| [2026-01-06 05:10:52,824][datasets.load][WARNING] - Using the latest cached version of the dataset since tanganke/eurosat couldn't be found on the Hugging Face Hub (offline mode is enabled). | |
| [2026-01-06 05:10:52,831][datasets.packaged_modules.cache.cache][WARNING] - Found the latest cached dataset configuration 'default' at /data/dataset/datasets/tanganke___eurosat/default/0.0.0/43750fc422c7fbd4289e2df3f7473617a5937acc (last modified on Mon Jan 5 04:16:47 2026). | |
| [2026-01-06 05:10:52,871][fusion_bench.method.classification.image_classification_finetune][INFO] - optimizer: | |
| SGD ( | |
| Parameter Group 0 | |
| dampening: 0 | |
| differentiable: False | |
| foreach: None | |
| fused: None | |
| lr: 0.01 | |
| maximize: False | |
| momentum: 0.9 | |
| nesterov: False | |
| weight_decay: 0.0001 | |
| ) | |
| [2026-01-06 05:47:44,415][fusion_bench.method.classification.image_classification_finetune][INFO] - Saving the final model to outputs/convnext-base-224/eurosat/batch_size=64,lr=0.01/raw_checkpoints/final | |