Instructions to use tanganke/convnext-base-224_dtd_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_dtd_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_dtd_sgd_batch-size-64_lr-0.01_steps-4000") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("tanganke/convnext-base-224_dtd_sgd_batch-size-64_lr-0.01_steps-4000") model = AutoModelForImageClassification.from_pretrained("tanganke/convnext-base-224_dtd_sgd_batch-size-64_lr-0.01_steps-4000", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download cli.log from tanganke/convnext-base-224_dtd_sgd_batch-size-64_lr-0.01_steps-4000: direct link, hf CLI and curl.
- Browser
- Download file 2.33 kB
-
https://huggingface.co/tanganke/convnext-base-224_dtd_sgd_batch-size-64_lr-0.01_steps-4000/resolve/5b7ffc01c1c013d601b5f9c228547c5b99b4e091/cli.log
- Command line
-
hf download hf://tanganke/convnext-base-224_dtd_sgd_batch-size-64_lr-0.01_steps-4000@5b7ffc01c1c013d601b5f9c228547c5b99b4e091/cli.log
-
curl -L -o cli.log https://huggingface.co/tanganke/convnext-base-224_dtd_sgd_batch-size-64_lr-0.01_steps-4000/resolve/5b7ffc01c1c013d601b5f9c228547c5b99b4e091/cli.log
2.33 kB
| [2026-01-08 04:49:05,782][fusion_bench.programs.fusion_program][INFO] - Running the model fusion program. | |
| [2026-01-08 04:49:05,785][fusion_bench.programs.fusion_program][INFO] - loading model pool | |
| [2026-01-08 04:49:08,035][fusion_bench.programs.fusion_program][INFO] - loading method | |
| [2026-01-08 04:49:08,098][fusion_bench.method.classification.image_classification_finetune][INFO] - Training interval: step | |
| [2026-01-08 04:49:08,098][fusion_bench.method.classification.image_classification_finetune][INFO] - Max epochs: -1, max steps: 4000 | |
| [2026-01-08 04:49:08,099][fusion_bench.programs.fusion_program][INFO] - loading task pool | |
| [2026-01-08 04:49:09,773][fusion_bench.method.classification.image_classification_finetune][INFO] - Number of classes for dataset dtd: 47 | |
| [2026-01-08 04:49:09,786][datasets.load][WARNING] - Using the latest cached version of the dataset since tanganke/dtd couldn't be found on the Hugging Face Hub (offline mode is enabled). | |
| [2026-01-08 04:49:09,795][datasets.packaged_modules.cache.cache][WARNING] - Found the latest cached dataset configuration 'default' at /data/dataset/datasets/tanganke___dtd/default/0.0.0/d2afa97d9f335b1a6b3b09c637aef667f98f966e (last modified on Mon Jan 5 04:22:16 2026). | |
| [2026-01-08 04:49:09,972][fusion_bench.method.classification.image_classification_finetune][INFO] - Training dataset size: 3760 | |
| [2026-01-08 04:49:10,003][datasets.load][WARNING] - Using the latest cached version of the dataset since tanganke/dtd couldn't be found on the Hugging Face Hub (offline mode is enabled). | |
| [2026-01-08 04:49:10,010][datasets.packaged_modules.cache.cache][WARNING] - Found the latest cached dataset configuration 'default' at /data/dataset/datasets/tanganke___dtd/default/0.0.0/d2afa97d9f335b1a6b3b09c637aef667f98f966e (last modified on Mon Jan 5 04:22:16 2026). | |
| [2026-01-08 04:49:10,060][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 | |
| ) | |
| [2026-01-08 05:15:05,827][fusion_bench.method.classification.image_classification_finetune][INFO] - Saving the final model to outputs/convnext-base-224/dtd/batch_size=64,lr=0.01/raw_checkpoints/final | |