G-reen / effnet_b0_iNat2019_deepmoe_lambda7e-05

huggingface.co
Total runs: 5
24-hour runs: 0
7-day runs: -3
30-day runs: -4
Model's Last Updated: April 21 2026
image-classification

Introduction of effnet_b0_iNat2019_deepmoe_lambda7e-05

Model Details of effnet_b0_iNat2019_deepmoe_lambda7e-05

DeepMoE EfficientNet-B0 fine-tuned on iNaturalist 2019

This model is a Mixture-of-Experts (DeepMoE) variant of EfficientNet-B0, fine-tuned on the iNaturalist 2019 dataset to optimize both accuracy and computational efficiency (FLOP reduction).

Training Results
  • Final Score (Acc/FLOPs composite) : 83.4129
  • Final Validation Accuracy : 69.1%
  • Expert Activation Ratio : 32.0%
  • FLOPs Usage : 57.2% (compared to baseline B0)
  • Baseline B0 Reference FLOPs : 388,184,000
  • Total Runtime : 5204.99 seconds
Hyperparameters
  • Batch Size : 256
  • Gradient Accumulation Steps : 4
  • Weight Decay : 0.005
Epochs
  • Total Epochs : 10
    • Joint Training Epochs: 10
    • Routing-Frozen Finetuning Epochs: 0
DeepMoE Architecture & Routing
  • MoE Start Stage : 1
  • Latent Dimension : 32
  • Sparsity Penalty ($\lambda_g$) : 7e-05
  • Target Sparsity ($\mu$) : 0.5
  • ReLU Init (Val / Std) : 1 / 1
Learning Rates
  • MoE Routing Parameters : 1.20e-01
  • Classification Head : 2.00e-02
  • Base Model (Body) : 2.00e-03
  • Finetune Phase (Frozen Routing) : 0.00e+00

Training was tracked using Weights & Biases .

Runs of G-reen effnet_b0_iNat2019_deepmoe_lambda7e-05 on huggingface.co

5
Total runs
0
24-hour runs
-1
3-day runs
-3
7-day runs
-4
30-day runs

More Information About effnet_b0_iNat2019_deepmoe_lambda7e-05 huggingface.co Model

effnet_b0_iNat2019_deepmoe_lambda7e-05 huggingface.co

effnet_b0_iNat2019_deepmoe_lambda7e-05 huggingface.co is an AI model on huggingface.co that provides effnet_b0_iNat2019_deepmoe_lambda7e-05's model effect (), which can be used instantly with this G-reen effnet_b0_iNat2019_deepmoe_lambda7e-05 model. huggingface.co supports a free trial of the effnet_b0_iNat2019_deepmoe_lambda7e-05 model, and also provides paid use of the effnet_b0_iNat2019_deepmoe_lambda7e-05. Support call effnet_b0_iNat2019_deepmoe_lambda7e-05 model through api, including Node.js, Python, http.

effnet_b0_iNat2019_deepmoe_lambda7e-05 huggingface.co Url

https://huggingface.co/G-reen/effnet_b0_iNat2019_deepmoe_lambda7e-05

G-reen effnet_b0_iNat2019_deepmoe_lambda7e-05 online free

effnet_b0_iNat2019_deepmoe_lambda7e-05 huggingface.co is an online trial and call api platform, which integrates effnet_b0_iNat2019_deepmoe_lambda7e-05's modeling effects, including api services, and provides a free online trial of effnet_b0_iNat2019_deepmoe_lambda7e-05, you can try effnet_b0_iNat2019_deepmoe_lambda7e-05 online for free by clicking the link below.

G-reen effnet_b0_iNat2019_deepmoe_lambda7e-05 online free url in huggingface.co:

https://huggingface.co/G-reen/effnet_b0_iNat2019_deepmoe_lambda7e-05

effnet_b0_iNat2019_deepmoe_lambda7e-05 install

effnet_b0_iNat2019_deepmoe_lambda7e-05 is an open source model from GitHub that offers a free installation service, and any user can find effnet_b0_iNat2019_deepmoe_lambda7e-05 on GitHub to install. At the same time, huggingface.co provides the effect of effnet_b0_iNat2019_deepmoe_lambda7e-05 install, users can directly use effnet_b0_iNat2019_deepmoe_lambda7e-05 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

effnet_b0_iNat2019_deepmoe_lambda7e-05 install url in huggingface.co:

https://huggingface.co/G-reen/effnet_b0_iNat2019_deepmoe_lambda7e-05

Url of effnet_b0_iNat2019_deepmoe_lambda7e-05

effnet_b0_iNat2019_deepmoe_lambda7e-05 huggingface.co Url

Provider of effnet_b0_iNat2019_deepmoe_lambda7e-05 huggingface.co

G-reen
ORGANIZATIONS

Other API from G-reen

huggingface.co

Total runs: 15
Run Growth: 0
Growth Rate: 0.00%
Updated:September 04 2024
huggingface.co

Total runs: 8
Run Growth: 0
Growth Rate: 0.00%
Updated:June 02 2024
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:August 26 2024