The assessment of food intake is an important aspect in the promotion of healthy living, particularly in Nigeria, where the challenges that exist in the estimation of the energy value of food consumed have led to the increase of lifestyle diseases such as obesity, diabetes, and heart-related problems. This research aimed at addressing the problem of food estimation through the creation of a machine learning model for the estimation of the calories contained in raw food consumed in Nigeria. The model was developed based on the use of a wide range of food items, 184, which exist in Nigeria. These food items were used, rotated, flipped, and zoomed to improve the accuracy of the model. The CNN algorithm was used for the classification. The accuracy of the model was tested using the Mean Absolute Error, Mean Square Error, and R-square value. The model achieved an R-square value of 0.99. The accuracy of the model was validated based on the existing studies that have been conducted on the estimation of calories through the use of images of food. The model developed can be used for the control of diet for patients on regulated nutrition