Inception-v3: Image Classification
Inception-v3 is the third version of the Inception series proposed by Google, known for its efficiency in convolutional neural networks and widely used for image classification tasks. The key idea behind Inception-v3 is its modular design, where multiple convolution filters of different sizes run in parallel, enabling the extraction of multi-scale features to improve the network’s representational power. The model incorporates techniques like batch normalization, factorized convolutions, and auxiliary classifiers, which reduce computational complexity while enhancing stability and accuracy. Inception-v3 has demonstrated outstanding performance on the ImageNet classification task, making it a key benchmark in deep learning.
Source model
- Input shape: 299x299
- Number of paramaters: 25.9M
- Model size: 90.9M
- Output shape: 1x1000
Source model repository: Inception-v3
Performance Reference
Please search model by model name in Model Farm
Inference & Model Conversion
Please search model by model name in Model Farm
License
Source Model: BSD-3-CLAUSE
Deployable Model: APLUX-MODEL-FARM-LICENSE