Data science tools and info

Best regards. Here I enable an online tuberculosis diagnosis using the Microscopic observation drug susceptibility (MODS)  assay [1]. This tool has been developed using Convolutional Neural Networks , with 15 layers. The performance this model got: Dev set.- Images: 256, specificity: 0.8828, sensitiviy: 0.7969, accuracy: 0.8398. Test-set: Images 5104,  specificity:  0.5329, sensitivity: 0.9510, accuracy: 0.7420 This is a test example to put future models online. This is part of the work being developed at Cayetano Heredia Peruvian Univeristy, R&D Laboratories, Bioinformatics and Molecular Biology laboratory. This is not the best performance achieved though. This tool will classify a MODS image into positive or negative and will show the score for this selection.  The backend is hosted in heroku with a free plan so it might be slow, have failures of communication and might really take a long time for the first run after ...

Have you experienced that when using  tf.contrib.layers.batch_norm during test time, the performance is diminished or is completely a mess? If yes, this post is for you. Quick summary: 1) As suggested in [1]:   you have do add this additional code:   update_ops = tf . get_collection ( tf . GraphKeys . UPDATE_OPS )   with tf . control_dependencies ( update_ops ):     train_op = optimizer . minimize ( loss ) 2) You have to use a placeholder to indicate that you are training or not, so you put this in the batch_norm param  is_training = your_place_holder, True for training. 3) If after this it doesn't show a good behavior, change the default  decay = 0.999, to a lower value such as  0.5. Other way to apply batch norm is presented in [2], for a manual setup. Nonetheless, if by using this second approach you still have a bad performance, use the point 3). If you want to use this second approach with Convolutional Neural Netw...