The cooperative manipulators can execute a wide range of tasks, such as carrying large or heavy payloads, which are difficult for a single manipulator. Dual arm manipulators are in typically operative configuration to mimic human, which are of highly flexibility and dexterity. In this paper, we propose a novel coarse-to-fine deep learning model along with investigating the grasp prior loss based on the well-known antipodal force-closure property. The proposed deep learning model predicts the contact configurations in grasping over-loaded and over-sized objects for dual arm manipulators directly from raw RGB images. We first apply detection network to locate the coarse bounding box of objects, further apply a fine-predicting network on the bounding box clipped images to precisely generate two contact configurations via minimizing regression loss and the antipodal grasp prior loss. Extensive experimental results under dense clutter and occlusion strongly demonstrate the effectiveness and robustness of the proposed method.