Search Results for « Model pruning »

This talks about the techniques used to compress a model as well as improve the inference latency: training a baseline model, fine-tuning it with magnitude-based weight pruning to high sparsity, and then exporting a deployment-ready TensorFlow Lite (TFLite) model using post-training quantization (PTQ). Using the tutorial pipeline, we obtain an export model sparsity of 0.799 and achieve an 8.99× reduction in model size (78,283 bytes to 8,703 bytes) with a modest test accuracy decrease (0.9785 to 0.9669).

Deep learning models, particularly large-scale language and vision architectures, are computationally intensive due to their extensive number of parameters and complex neural network designs. This paper presents an improved method for model pruning aimed at reducing the computational burden while maintaining performance levels comparable to unpruned models. By analyzing weights, biases, activations, and other key indicators, we propose a novel algorithm that effectively identifies and removes neurons or connections with minimal contribution to the model’s output quality. Our approach achieves a higher pruning efficiency across various pruning ratios, resulting in smaller, faster, and more cost-effective models. Experimental results demonstrate that our method significantly outperforms state-of-the-art (SOTA) pruning techniques in terms of both inference speed and memory usage, with negligible degradation in accuracy. This work contributes to the development of resource-efficient models suitable for deployment in environments with limited computational resources, paving the way for more scalable and sustainable deep-learning applications.

Convolutional neural networks (CNNs) are extensively utilized in computer vision; however, they pose challenges in terms of computational time and storage requirements. To address this issue, one well-known approach is filter pruning. However, fine-tuning pruned models necessitates substantial computing power and a large retraining dataset. To restore model performance after pruning each layer, we propose the Convolutional Approximation Small Model (CASM) framework. CASM involves training a compact model with the remaining kernels and optimizing their weights to restore feature maps that resemble the original kernels. This method requires less complexity and fewer training samples compared to basic fine-tuning. We evaluate the performance of CASM on the CIFAR-10 and ImageNet datasets using VGG-16 and ResNet-50 models. The experimental results demonstrate that CASM surpasses the basic fine-tuning framework in terms of time acceleration (3.3× faster), requiring a smaller dataset for performance recovery after pruning, and achieving enhanced accuracy.

Background: The detection of suture needles is of paramount importance, yet it poses considerable challenges due to their small size and the complex detection background.Methods: To address this problem, this study proposes YOLOv8-DWE, a lightweight and high-efficiency detection model specially developed for suture needle detection.Results ：In this study, the Generative Adversarial Network (GAN) is applied for data augmentation to improve the generalization performance of the model; a Dual-stage Weighted Residual Module (DWR) is designed for feature enhancement; the SEAM attention mechanism is adopted to reconstruct the HEAD; and the label-quality adaptive Wisc-IoU loss function is employed to enhance the model's capability to handle complex backgrounds.Conclusions ：YOLOv8-DWE demonstrates enormous potential for real-time detection in embedded surgical systems.

Federated Learning serves as a distributed framework for machine learning. Traditional approaches to federated learning often assume the independence and identical distribution (IID) of client data. However, real-world scenarios frequently feature personalized characteristics in client data, deviating from the IID assumption. Additionally, challenges such as substantial communication overhead and limited resources at edge nodes hinder the practical implementation of federated learning. In response to the challenges in deploying federated learning, including uneven data distribution, communication bottlenecks, and resource limitations at edge nodes, this paper introduces an individualized federated learning framework based on model pruning. This framework effectively adapts the client's local model to the personalized distribution of local data while meeting the model aggregation requirements on the server. Utilizing sparse operations, the framework achieves personalized model pruning, efficiently compresses model parameters, and reduces computational load on edge nodes. Presently, our approach demonstrates a compression ratio of 3.8% on the non-IID dataset Feminist without compromising final training accuracy, resulting in a 12.3% acceleration in training speed.