Breast cancer is one of the most dangerous diseases and the second largest cause of female cancer death. Breast cancer starts when malignant, cancerous lumps start to grow from the breast cells. Self-tests and Periodic clinical checks help to early diagnosis and thereby improve the survival chances significantly. The breast cancer classification is a medical method that provides researchers and scientists with a great challenge. Neural networks have recently become a popular tool in cancer data classification. Deep learning (DL) technologies are becoming a buzzword these days, especially for breast histopathology image tasks, such as diagnosing, due to the high performance obtained in image classification. Among deep learning types, Convolutional Neural Networks (CNN) are the most common types of DL models utilized for medical image diagnosis and analysis. However, CNN suffers from high computation cost to be implemented and may require to adapt huge number of parameters. Thus, and in order to address this issue; several pre-trained models have been established with the predefined network architecture. In this study, we trained VGG-16 ResNet-18 on Breast images. a transfer learning model based on Visual Geometry Group with 16-layer deep model architecture (VGG16) is utilized to extract high-level features and ResNet-18 with 18 layers. The empirical outcomes confirm that the application of ResNet-18 provides the most reliable performance for accuracy where accuracy with ResNet-18 was 98.89% while accuracy with VGG-16 was 94.44%.