Distinguishing normal from malignant and determining the tumor type are critical components of brain tumor diagnosis. Two different kinds of dataset are investigated using state-of-the-art CNN models in this research work. One dataset(binary) has images of normal and tumor types, while another(multi-class) provides all images of tumors classified as glioma, meningioma, or pituitary. The experiments were conducted in these dataset with transfer learning from pre-trained weights from ImageNet as well as initializing the weights randomly. The experimental environment is equivalent for all models in this study in order to make a fair comparison. For both of the dataset, the validation set are same for all the models where train data is 60% while the rest is 40% for validation. With the proposed techniques in this research, the EfficientNet-B5 architecture outperforms all the state-of-the-art models in the binary-classification dataset with the accuracy of 99.75% and 98.61% accuracy for the multi-class dataset. This research also demonstrates the behaviour of convergence of validation loss in different weight initialization techniques.