sess = tf.InteractiveSession() with sess.as_default(): print('Loading model') model = unet(inputshape=(patch_w, patch_h, n_channels), conv_depth=conv_depth) model.load_weights(args.weights) print('Reformating data') test_x = np.zeros((test_gen.__len__(), patch_w, patch_h, n_channels)) test_y = np.zeros((test_gen.__len__(), patch_w, patch_h, 1)) test_charge = np.zeros((test_gen.__len__(), patch_w, patch_h, 1)) test_energy = np.zeros((test_gen.__len__(), patch_w, patch_h, 1)) for i in range(test_gen.__len__()): test_x[i], test_y[i] = test_gen.__getitem__(i) test_charge[i] = test_gen.getitembykey(i, 'wire') test_energy[i] = test_gen.getitembykey(i, 'energy') # FIXME # test_x = test_x[:8] # test_y = test_y[:8] # test_charge = test_charge[:8] # test_energy = test_energy[:8] print('Making predictions') predictions = model.predict(test_x, batch_size=8, verbose=1) del test_x, test_y print('Made predictions') q_flat = test_charge[..., 0].flatten() flat = predictions.flatten()[q_flat > 0.1]
sess = tf.InteractiveSession() with sess.as_default(): print('Loading model') model = unet(inputshape=(patch_w, patch_h, n_channels), conv_depth=conv_depth) model.load_weights(args.weights) print('Loading charge info') if steps == 0: test_charge = np.zeros( (test_gen.__len__() * batch_size, patch_w, patch_h, 1)) test_energy = np.zeros( (test_gen.__len__() * batch_size, patch_w, patch_h, 1)) for i in range(test_gen.__len__()): wires = test_gen.getitembykey(i, 'wire') energies = test_gen.getitembykey(i, 'energy') for j in range(batch_size): test_charge[(i * batch_size) + j] = wires[j] test_energy[(i * batch_size) + j] = energies[j] else: test_charge = np.zeros((steps * batch_size, patch_w, patch_h, 1)) test_energy = np.zeros((steps * batch_size, patch_w, patch_h, 1)) for i in range(steps): wires = test_gen.getitembykey(i, 'wire') energies = test_gen.getitembykey(i, 'energy') for j in range(batch_size): test_charge[(i * batch_size) + j] = wires[j] test_energy[(i * batch_size) + j] = energies[j] print('Making predictions')
print('Loading model') model = unet(inputshape=(patch_w, patch_h, n_channels), conv_depth=conv_depth) model.load_weights(args.weights) print('Reformating data') test_x = np.zeros((test_gen.__len__(), patch_w, patch_h, n_channels)) test_y = np.zeros((test_gen.__len__(), patch_w, patch_h, 1)) test_true = np.zeros((test_gen.__len__(), patch_w, patch_h, 1)) test_charge = np.zeros((test_gen.__len__(), patch_w, patch_h, 1)) test_energy = np.zeros((test_gen.__len__(), patch_w, patch_h, 1)) test_e = np.zeros((test_gen.__len__(), 1)) test_n = np.zeros((test_gen.__len__(), 1)) for i in range(test_gen.__len__()): test_x[i], test_y[i] = test_gen.__getitem__(i) test_true[i] = test_gen.getitembykey(i, 'trueEnergy') test_charge[i] = test_gen.getitembykey(i, 'wire') test_energy[i] = test_gen.getitembykey(i, 'energy') test_e[i] = test_gen.getenergy(i) test_n[i] = test_gen.getitembykey(i, 'nTrue')[0, 0, 0] print('Making predictions') predictions = model.predict(test_x, batch_size=8, verbose=1) print('Made predictions') q_flat = test_charge[..., 0].flatten() flat = predictions.flatten()[q_flat > 0.1] true_flat = test_y.flatten()[q_flat > 0.1] e_flat = test_energy[..., 0].flatten()[q_flat > 0.1] q_flat = q_flat[q_flat > 0.1]