print "starting post-testing on training dataset" post_mlp.test(data=pre_test_train_probs, labels=train_set_labels, **cs_args["test_args"]) print "starting post-testing on the dataset" post_mlp.test(data=pre_test_test_probs, labels=test_set_labels, **cs_args["test_args"]) if __name__=="__main__": print "Loading the dataset" ds = Dataset() data_path_40k = "/RQusagers/gulcehre/dataset/pentomino/pieces/pento64x64_40k_seed_39112222.npy" data_path = "/RQusagers/gulcehre/dataset/pentomino/experiment_data/pento64x64_80k_seed_39112222.npy" data_new_60k =\ "/RQexec/gulcehre/datasets/pentomino/pento_64x64_8x8patches/pento64x64_60k_64patches_seed_975168712_64patches.npy" patch_size=(8, 8) ds.setup_pretraining_obj_patch_dataset(data_path=data_new_60k, patch_size=patch_size, normalize_inputs=False) x = T.matrix('x') n_hiddens = [2048] no_of_patches = 3 no_of_classes = 11 prmlp = PatchBasedMLP(x, n_in=patch_size[0] * patch_size[1], n_hiddens=n_hiddens, n_out=11, no_of_patches=no_of_patches, activation=NeuralActivations.Rectifier, use_adagrad=False) post_mlp = PostMLP(x, n_in=no_of_patches * no_of_classes, n_hiddens=[98], n_out=1, use_adagrad=False) pre_training(patch_mlp=prmlp, post_mlp=post_mlp, ds=ds)