Image captioning is a task to make an image description, which needs recognizing the important attributes and also their relationships in the image. This task requires to generate semantically and syntactically correct sentences. Most image captioning models are based on RNN and MLE methods, but we propose a novel model based on GAN networks where it generates the caption of the image through the representation of the image by utilizing the generator adversarial network and it does not need any secondary learning algorithm like policy gradient. Due to the complexity of benchmark datasets such as Flickr and Coco, in both volume and complexity, we introduce a new dataset and perform the experiments on it. The experimental results show the effectiveness of our model compared to the state-of-the-art image captioning methods.