The importance of the classification of forest fires through computational methods lies in their applicability for early detection and timely warning to prevent their spread. According to the state of the art, the classification of forest fires was approached by proposals based on machine learning (ML) and deep learning (DL), more specifically on Convolutional Neural Networks (CNN). In practice, DL-based methods prove to be superior to traditional ML methods. Recently, FFireNet, a CNN model that presents optimal results for classifying images of forest fires, was proposed. On this basis, in thiswork, we present a methodology to create CNN models by transfer learning applied specifically to the classification of forest fires, where techniques such as data augmentation, transfer learning, transfer learning and fine tuning were included. The proposal allowed us to define E-FFireNet, an efficient model with superior results than FFireNet. The experiments showed classification results of 99,73 (accuracy), 99,48 (precision), 100,0 (recall) and 0,263 (error).