| Trained with 1 GPU H800 Server from AutoDL on 2025.2.3 UTC+8 with Pytroch and converted to .h5 format at the same time. | |
| Basic Model uses CNN with accuracy of 75% on test data (80.7 MB) | |
| V1 Engine uses CNN with accuracy of 87% on test data (72.1 MB) | |
| V2 Engine uses ViT with accuracy of at most 40% Keyboard Interrupted 2025.2.3 15:57:37 BJS | |
| V3 Engine uses Hybrid Model( Combination of Convolutional layers and a Multi-Layer Perceptron (MLP)) with accuracy 68.65% on test data. (34.3 MB) | |
| Trained 2025.2.4 UTC+8 with H800 | |
| V4 Engine based of V1 but improve with more Convolutional Layers. | |
| Bottleneck Blocks: We can use bottleneck blocks (1x1 conv before and after 3x3 conv) to reduce computation, and increase depth. | |
| Residual Connections: Implement residual connections to ease training in the very deep network and to help avoid vanishing gradients. | |
| Increased Filters: Use more filters in the layers to increase the learning capacity. | |
| Accuracy 89.39% on test data. | |
| E1 Engine : 93.78% Accuracy on test data | |
| The technology used in this solution combines EfficientNet-B0 as the base model, enhanced by knowledge distillation from a ResNet-34 teacher model to improve accuracy, and quantization to reduce the model size. | |
| After training and optimization, the final quantized model achieves a compact size of 16.6 MB, making it highly efficient for deployment. | |
| On the test dataset, the model delivers a strong final accuracy of 93.78%, demonstrating its effectiveness in jersey number detection while meeting strict size constraints. | |
| Trained 2025.2.5 UTC+8 with H800 | |
| E2 Engine: 94.6% Accuracy on test data | |
| E2 technology represents an advanced iteration of E1, focusing on enhanced efficiency, security, and scalability. | |
| While E1 laid the foundational groundwork by optimizing basic system processes and improving task automation, E2 takes a step further by integrating more sophisticated encryption protocols, leveraging machine learning for predictive performance, and streamlining resource allocation. | |
| This allows E2 to better handle complex, real-time data analysis, which was a challenge for E1 due to its more rigid system structures. | |
| Additionally, E2 offers increased compatibility with distributed systems, making it ideal for applications requiring higher data throughput and reliability, thus positioning it as the go-to solution for cutting-edge enterprise environments. | |
| In essence, E2 is a more adaptive and intelligent evolution of E1's capabilities, with a stronger emphasis on securing and managing large-scale systems effectively. |