Instructions to use tanganke/convnext-base-224_gtsrb_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_gtsrb_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_gtsrb_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_gtsrb_sgd_batch-size-64_lr-0.01_steps-4000") model = AutoModelForImageClassification.from_pretrained("tanganke/convnext-base-224_gtsrb_sgd_batch-size-64_lr-0.01_steps-4000") - Notebooks
- Google Colab
- Kaggle
| [2026-01-07 04:24:27,339][fusion_bench.programs.fusion_program][INFO] - Running the model fusion program. | |
| [2026-01-07 04:24:27,342][fusion_bench.programs.fusion_program][INFO] - loading model pool | |
| [2026-01-07 04:24:29,614][fusion_bench.programs.fusion_program][INFO] - loading method | |
| [2026-01-07 04:24:29,679][fusion_bench.method.classification.image_classification_finetune][INFO] - Training interval: step | |
| [2026-01-07 04:24:29,681][fusion_bench.method.classification.image_classification_finetune][INFO] - Max epochs: -1, max steps: 4000 | |
| [2026-01-07 04:24:29,682][fusion_bench.programs.fusion_program][INFO] - loading task pool | |
| [2026-01-07 04:24:31,062][fusion_bench.method.classification.image_classification_finetune][INFO] - Number of classes for dataset gtsrb: 43 | |
| [2026-01-07 04:24:31,075][datasets.load][WARNING] - Using the latest cached version of the dataset since tanganke/gtsrb couldn't be found on the Hugging Face Hub (offline mode is enabled). | |
| [2026-01-07 04:24:31,083][datasets.packaged_modules.cache.cache][WARNING] - Found the latest cached dataset configuration 'default' at /data/dataset/datasets/tanganke___gtsrb/default/0.0.0/ea889fff70dda7b09e94a4b207dded438deca549 (last modified on Mon Jan 5 04:21:02 2026). | |
| [2026-01-07 04:24:31,405][fusion_bench.method.classification.image_classification_finetune][INFO] - Training dataset size: 26640 | |
| [2026-01-07 04:24:31,430][datasets.load][WARNING] - Using the latest cached version of the dataset since tanganke/gtsrb couldn't be found on the Hugging Face Hub (offline mode is enabled). | |
| [2026-01-07 04:24:31,437][datasets.packaged_modules.cache.cache][WARNING] - Found the latest cached dataset configuration 'default' at /data/dataset/datasets/tanganke___gtsrb/default/0.0.0/ea889fff70dda7b09e94a4b207dded438deca549 (last modified on Mon Jan 5 04:21:02 2026). | |
| [2026-01-07 04:24:31,565][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 | |
| ) | |
| [2026-01-07 05:04:22,111][fusion_bench.method.classification.image_classification_finetune][INFO] - Saving the final model to outputs/convnext-base-224/gtsrb/batch_size=64,lr=0.01/raw_checkpoints/final | |