如果你后面要跑 CNN 微调，还需要装 TensorFlow 或 PyTorch，但那是可选步骤，先把基础链路跑通再说。 提示：不要用 pip install opencv-python 不带版本号，它会拉最新版，很可能和你的 Python 版本不匹配。

A deep learning project for classifying images into six categories using a custom Convolutional Neural Network (CNN) and MobileNetV2 transfer learning with TensorFlow and Keras. Image classification ...

Smart Waste Segregation System is an AI-powered image classification application designed to identify different categories of waste from uploaded images. - TechyGautam/-Smart-Waste-Segregation-System ...

A knowledge-distilled pyramid transformer with reduced attention achieved F1-scores of 90.92%, 97.76% and 94.59% on three 32 ...

A new framework combining reinforcement learning and Siamese convolutional networks with blockchain-secured routing reports ...

A compact 3D CNN (105,307 parameters), designed and trained from scratch for multi-class classification of 28×28×28 CT bounding-box volumes into 11 body organs, released with something most model ...

A CNN model trained on ImageNet. It certainly achieves over 95% accuracy in 1000-class image classification. However, as many ...

Confusion matrix (rows = true, columns = predicted): vessel 267 correct / 72 read as aneurysm; aneurysm 22 read as vessel / 21 correct. The failure analysis (full record in ...

DEEPX is bringing vision and language AI inference to the Raspberry Pi 5 through the Sixfab AI HAT+, which uses the company’s ...

I took a course called GCI (Global Consumer Intelligence) from April 21 to August 4, 2026, so I will write about what I ...