# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("ZafarLocAI/mar_20_class_split_without_class_weights")
model = AutoModelForImageClassification.from_pretrained("ZafarLocAI/mar_20_class_split_without_class_weights", device_map="auto")Quick Links
mar_20_class_split_without_class_weights
This model is a fine-tuned version of facebook/convnextv2-large-22k-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0577
- Accuracy: 0.9804
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3077 | 1.0 | 278 | 0.0853 | 0.9729 |
| 0.1899 | 2.0 | 556 | 0.0618 | 0.9804 |
| 0.1152 | 3.0 | 834 | 0.0577 | 0.9804 |
Framework versions
- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Datasets 4.6.1
- Tokenizers 0.22.2
- Downloads last month
- 2
Model tree for ZafarLocAI/mar_20_class_split_without_class_weights
Base model
facebook/convnextv2-large-22k-224
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ZafarLocAI/mar_20_class_split_without_class_weights") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")