vuongnhathien / convnext-nano-3e-4-augment

huggingface.co
Total runs: 5
24-hour runs: 1
7-day runs: -2
30-day runs: -1
Model's Last Updated: May 25 2024
image-classification

Introduction of convnext-nano-3e-4-augment

Model Details of convnext-nano-3e-4-augment

convnext-nano-3e-4-augment

This model is a fine-tuned version of facebook/convnextv2-nano-22k-384 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2872
  • Accuracy: 0.9280
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: 0.0003
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 10
Training results
Training Loss Epoch Step Validation Loss Accuracy
0.8119 1.0 275 0.5637 0.8270
0.5829 2.0 550 0.5016 0.8497
0.4623 3.0 825 0.4494 0.8755
0.359 4.0 1100 0.3809 0.8887
0.2881 5.0 1375 0.3742 0.8998
0.2302 6.0 1650 0.3402 0.9113
0.1827 7.0 1925 0.3150 0.9121
0.1466 8.0 2200 0.3012 0.9229
0.1223 9.0 2475 0.2996 0.9249
0.1332 10.0 2750 0.2948 0.9249
Framework versions
  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2

Runs of vuongnhathien convnext-nano-3e-4-augment on huggingface.co

5
Total runs
1
24-hour runs
0
3-day runs
-2
7-day runs
-1
30-day runs

More Information About convnext-nano-3e-4-augment huggingface.co Model

More convnext-nano-3e-4-augment license Visit here:

https://choosealicense.com/licenses/apache-2.0

convnext-nano-3e-4-augment huggingface.co

convnext-nano-3e-4-augment huggingface.co is an AI model on huggingface.co that provides convnext-nano-3e-4-augment's model effect (), which can be used instantly with this vuongnhathien convnext-nano-3e-4-augment model. huggingface.co supports a free trial of the convnext-nano-3e-4-augment model, and also provides paid use of the convnext-nano-3e-4-augment. Support call convnext-nano-3e-4-augment model through api, including Node.js, Python, http.

convnext-nano-3e-4-augment huggingface.co Url

https://huggingface.co/vuongnhathien/convnext-nano-3e-4-augment

vuongnhathien convnext-nano-3e-4-augment online free

convnext-nano-3e-4-augment huggingface.co is an online trial and call api platform, which integrates convnext-nano-3e-4-augment's modeling effects, including api services, and provides a free online trial of convnext-nano-3e-4-augment, you can try convnext-nano-3e-4-augment online for free by clicking the link below.

vuongnhathien convnext-nano-3e-4-augment online free url in huggingface.co:

https://huggingface.co/vuongnhathien/convnext-nano-3e-4-augment

convnext-nano-3e-4-augment install

convnext-nano-3e-4-augment is an open source model from GitHub that offers a free installation service, and any user can find convnext-nano-3e-4-augment on GitHub to install. At the same time, huggingface.co provides the effect of convnext-nano-3e-4-augment install, users can directly use convnext-nano-3e-4-augment installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

convnext-nano-3e-4-augment install url in huggingface.co:

https://huggingface.co/vuongnhathien/convnext-nano-3e-4-augment

Url of convnext-nano-3e-4-augment

convnext-nano-3e-4-augment huggingface.co Url

Provider of convnext-nano-3e-4-augment huggingface.co

vuongnhathien
ORGANIZATIONS

Other API from vuongnhathien