EfficientNet is a family of convolutional neural networks (CNNs) developed by Google that aim to achieve high accuracy with fewer computational resources. It uses a novel scaling method called compound scaling, which uniformly scales the network's depth, width, and resolution to balance performance and efficiency. EfficientNet models, ranging from EfficientNet-B0 to EfficientNet-B7, demonstrate state-of-the-art performance on various image classification tasks while being significantly more efficient than previous models like ResNet and Inception. The base model, EfficientNet-B0, is designed using neural architecture search (NAS), optimizing for both accuracy and computational cost..
Image classification is a fundamental problem in computer vision where the goal is to assign a label or category to an image based on its content. This task is critical for a variety of applications, including medical imaging, autonomous vehicles, content-based image retrieval, and social media tagging.
If you find this project useful, please give it a star to show your support and help others discover it!
To get started with this project, clone the repository using the following command:
git clone https://github.com/TruongNV-hut/AIcandy_Efficientnet_ImageClassification_rlbyvacq.git
Before running the scripts, you need to install the required libraries. You can do this using pip:
pip install -r requirements.txt
To train the model, use the following command:
python aicandy_efficientnet_train_xcprktlu.py --train_dir ../dataset --num_epochs 10 --batch_size 32 --model_path aicandy_model_out_vailsuom/aicandy_model_pth_ppxascdt.pth
After training, you can test the model using:
python aicandy_efficientnet_test_gmbpqtln.py --image_path ../image_test.jpg --model_path aicandy_model_out_vailsuom/aicandy_model_pth_ppxascdt.pth --label_path label.txt
To convert the model to ONNX format, run:
python aicandy_efficientnet_convert_onnx_laghxeeb.py --model_path aicandy_model_out_vailsuom/aicandy_model_pth_ppxascdt.pth --onnx_path aicandy_model_out_vailsuom/aicandy_model_onnx_expbpybk.onnx --num_classes 2
To learn more about this project, see here.
To learn more about knowledge and real-world projects on Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL), visit the website aicandy.vn.
❤️❤️❤️