GoogLeNet: Image Classification
GoogLeNet is a convolutional neural network model introduced by Google in 2014, famous for its Inception architecture. It won the ImageNet Large Scale Visual Recognition Challenge (ILSVRC 2014). The core of GoogLeNet is the Inception module, which performs multiple convolutions and pooling operations in parallel at the same layer, capturing multi-scale features of images while reducing the number of parameters and computational complexity. Compared to traditional convolutional neural networks, GoogLeNet has greater depth but achieves higher computational efficiency due to its modular design. Consisting of 22 layers with several Inception modules, GoogLeNet is widely used in tasks like image classification and object detection.
Source model
- Input shape: 224x224
- Number of parameters: 6.31M
- Model size: 25.29M
- Output shape: 1x1000
Source model repository: GoogLeNet
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