def main(): tf.disable_eager_execution() parser = argparse.ArgumentParser() parser.add_argument("experiment_name") arguments = parser.parse_args() full_name = arguments.experiment_name.split('/') experiment_name = full_name.pop() experiment_group = full_name.pop() if len(full_name) > 0 else '' codebook, dataset = factory.build_codebook_from_name(experiment_name, experiment_group, return_dataset=True) workspace_path = os.environ.get('AE_WORKSPACE_PATH') log_dir = u.get_log_dir(workspace_path, experiment_name, experiment_group) ckpt_dir = u.get_checkpoint_dir(log_dir) train_cfg_file_path = u.get_train_config_exp_file_path( log_dir, experiment_name) train_args = configparser.ConfigParser() train_args.read(train_cfg_file_path) width = 960 height = 720 videoStream = WebcamVideoStream(0, width, height).start() gpu_options = tf.GPUOptions(allow_growth=True, per_process_gpu_memory_fraction=0.9) config = tf.ConfigProto(gpu_options=gpu_options) config.gpu_options.allow_growth = True with tf.Session(config=config) as sess: factory.restore_checkpoint(sess, tf.train.Saver(), ckpt_dir) while videoStream.isActive(): image = videoStream.read() if image is None or not image.any(): print("Failed to capture webcam image") exit(-1) # try your detector here: # bb_xywh = detector.detect(image) # image_crop = dataset.extract_square_patch(image, bb_xywh, train_args.getfloat('Dataset','PAD_FACTOR')) # Rs, ts = codebook.auto_pose6d(sess, image_crop, bb_xywh, K_test, 1, train_args) img = cv2.resize(image, (128, 128)) R = codebook.nearest_rotation(sess, img) pred_view = dataset.render_rot(R, downSample=1) print(R) cv2.imshow('resized webcam input', img) cv2.imshow('pred view rendered', pred_view) cv2.waitKey(1)
def __init__(self, test_configpath): test_args = configparser.ConfigParser() test_args.read(test_configpath) workspace_path = os.environ.get('AE_WORKSPACE_PATH') if workspace_path == None: print('Please define a workspace path:') print('export AE_WORKSPACE_PATH=/path/to/workspace') exit(-1) self._camPose = test_args.getboolean('CAMERA', 'camPose') self._camK = np.array(eval(test_args.get('CAMERA', 'K_test'))).reshape(3, 3) self._width = test_args.getint('CAMERA', 'width') self._height = test_args.getint('CAMERA', 'height') self._upright = test_args.getboolean('AAE', 'upright') self.all_experiments = eval(test_args.get('AAE', 'experiments')) self.class_names = eval(test_args.get('DETECTOR', 'class_names')) self.det_threshold = eval(test_args.get('DETECTOR', 'det_threshold')) self.icp = test_args.getboolean('ICP', 'icp') if self.icp: self._depth_scale = test_args.getfloat('DATA', 'depth_scale') self.all_codebooks = [] self.all_train_args = [] self.pad_factors = [] self.patch_sizes = [] config = tf.ConfigProto(allow_soft_placement=True) config.gpu_options.allow_growth = True config.gpu_options.per_process_gpu_memory_fraction = test_args.getfloat( 'MODEL', 'gpu_memory_fraction') self.sess = tf.Session(config=config) set_session(self.sess) self.detector = load_model( str(test_args.get('DETECTOR', 'detector_model_path')), backbone_name=test_args.get('DETECTOR', 'backbone')) #detector = self._load_model_with_nms(test_args) for i, experiment in enumerate(self.all_experiments): full_name = experiment.split('/') experiment_name = full_name.pop() experiment_group = full_name.pop() if len(full_name) > 0 else '' log_dir = utils.get_log_dir(workspace_path, experiment_name, experiment_group) ckpt_dir = utils.get_checkpoint_dir(log_dir) train_cfg_file_path = utils.get_train_config_exp_file_path( log_dir, experiment_name) print(train_cfg_file_path) # train_cfg_file_path = utils.get_config_file_path(workspace_path, experiment_name, experiment_group) train_args = configparser.ConfigParser() train_args.read(train_cfg_file_path) self.all_train_args.append(train_args) self.pad_factors.append( train_args.getfloat('Dataset', 'PAD_FACTOR')) self.patch_sizes.append( (train_args.getint('Dataset', 'W'), train_args.getint('Dataset', 'H'))) self.all_codebooks.append( factory.build_codebook_from_name(experiment_name, experiment_group, return_dataset=False)) saver = tf.train.Saver(var_list=tf.get_collection( tf.GraphKeys.GLOBAL_VARIABLES, scope=experiment_name)) factory.restore_checkpoint(self.sess, saver, ckpt_dir) # if self.icp: # assert len(self.all_experiments) == 1, 'icp currently only works for one object' # # currently works only for one object # from auto_pose.icp import icp # self.icp_handle = icp.ICP(train_args) if test_args.getboolean('ICP', 'icp'): from auto_pose.icp import icp self.icp_handle = icp.ICP(test_args, self.all_train_args)
workspace_path = os.environ.get('AE_WORKSPACE_PATH') log_dir = u.get_log_dir(workspace_path, experiment_name, experiment_group) ckpt_dir = u.get_checkpoint_dir(log_dir) train_cfg_file_path = u.get_train_config_exp_file_path(log_dir, experiment_name) train_args = configparser.ConfigParser() train_args.read(train_cfg_file_path) width = 960 height = 720 videoStream = WebcamVideoStream(0, width, height).start() with tf.Session() as sess: factory.restore_checkpoint(sess, tf.train.Saver(), ckpt_dir) while videoStream.isActive(): image = videoStream.read() # try your detector here: # bb_xywh = detector.detect(image) # image_crop = dataset.extract_square_patch(image, bb_xywh, train_args.getfloat('Dataset','PAD_FACTOR')) # Rs, ts = codebook.auto_pose6d(sess, image_crop, bb_xywh, K_test, 1, train_args) img = cv2.resize(image, (128, 128)) R = codebook.nearest_rotation(sess, img) pred_view = dataset.render_rot(R, downSample=1) print R cv2.imshow('resized webcam input', img)
def detection(detection_graph, category_index, score, expand): print("> Building Graph") print(category_index) # Session Config: allow seperate GPU/CPU adressing and limit memory allocation config = tf.ConfigProto(allow_soft_placement=True, log_device_placement=log_device) config.gpu_options.allow_growth = allow_memory_growth config.gpu_options.per_process_gpu_memory_fraction = 0.4 ###Jetson only cur_frames = 0 with detection_graph.as_default(): #run_meta = tf.RunMetadata() with tf.Session(graph=detection_graph, config=config) as sess: # Define Input and Ouput tensors image_tensor = detection_graph.get_tensor_by_name('image_tensor:0') detection_boxes = detection_graph.get_tensor_by_name( 'detection_boxes:0') detection_scores = detection_graph.get_tensor_by_name( 'detection_scores:0') detection_classes = detection_graph.get_tensor_by_name( 'detection_classes:0') num_detections = detection_graph.get_tensor_by_name( 'num_detections:0') if split_model: score_out = detection_graph.get_tensor_by_name( 'Postprocessor/convert_scores:0') expand_out = detection_graph.get_tensor_by_name( 'Postprocessor/ExpandDims_1:0') score_in = detection_graph.get_tensor_by_name( 'Postprocessor/convert_scores_1:0') expand_in = detection_graph.get_tensor_by_name( 'Postprocessor/ExpandDims_1_1:0') # Threading gpu_worker = SessionWorker("GPU", detection_graph, config) cpu_worker = SessionWorker("CPU", detection_graph, config) gpu_opts = [score_out, expand_out] cpu_opts = [ detection_boxes, detection_scores, detection_classes, num_detections ] gpu_counter = 0 cpu_counter = 0 for i, experiment_name in enumerate(arguments.experiment_names): full_name = experiment_name.split('/') experiment_name = full_name.pop() experiment_group = full_name.pop( ) if len(full_name) > 0 else '' train_cfg_file_path = utils.get_config_file_path( workspace_path, experiment_name, experiment_group) train_args = configparser.ConfigParser() train_args.read(train_cfg_file_path) h_train, w_train, c = train_args.getint( 'Dataset', 'H'), train_args.getint('Dataset', 'W'), train_args.getint( 'Dataset', 'C') model_paths.append(train_args.get('Paths', 'MODEL_PATH')) all_train_args.append(train_args) log_dir = utils.get_log_dir(workspace_path, experiment_name, experiment_group) ckpt_dir = utils.get_checkpoint_dir(log_dir) all_codebooks.append( factory.build_codebook_from_name(experiment_name, experiment_group, return_dataset=False)) factory.restore_checkpoint( sess, tf.train.Saver(var_list=tf.get_collection( tf.GraphKeys.GLOBAL_VARIABLES, scope=experiment_name)), ckpt_dir) #opts = tf.profiler.ProfileOptionBuilder.float_operation() #flops = tf.profiler.profile(sess.graph, run_meta=run_meta, cmd='op', options=opts) #exit() # i_class_mapping = {v: k for k, v in class_i_mapping.iteritems()} renderer = meshrenderer_phong.Renderer(model_paths, 1) # Start Video Stream and FPS calculation fps = FPS2(fps_interval).start() video_stream = WebcamVideoStream(video_input, width, height).start() cur_frames = 0 print("> Press 'q' to Exit, 'a' to start auto_pose") print('> Starting Detection') while video_stream.isActive(): # actual Detection if split_model: # split model in seperate gpu and cpu session threads if gpu_worker.is_sess_empty(): # read video frame, expand dimensions and convert to rgb image = video_stream.read() image_expanded = np.expand_dims(cv2.cvtColor( image, cv2.COLOR_BGR2RGB), axis=0) # put new queue gpu_feeds = {image_tensor: image_expanded} if visualize: gpu_extras = image # for visualization frame else: gpu_extras = None gpu_worker.put_sess_queue(gpu_opts, gpu_feeds, gpu_extras) g = gpu_worker.get_result_queue() if g is None: # gpu thread has no output queue. ok skip, let's check cpu thread. gpu_counter += 1 else: # gpu thread has output queue. gpu_counter = 0 score, expand, image = g["results"][0], g["results"][ 1], g["extras"] if cpu_worker.is_sess_empty(): # When cpu thread has no next queue, put new queue. # else, drop gpu queue. cpu_feeds = {score_in: score, expand_in: expand} cpu_extras = image cpu_worker.put_sess_queue(cpu_opts, cpu_feeds, cpu_extras) c = cpu_worker.get_result_queue() if c is None: # cpu thread has no output queue. ok, nothing to do. continue cpu_counter += 1 time.sleep(0.005) continue # If CPU RESULT has not been set yet, no fps update else: cpu_counter = 0 boxes, scores, classes, num, image = c["results"][ 0], c["results"][1], c["results"][2], c["results"][ 3], c["extras"] else: # default session image = video_stream.read() image_expanded = np.expand_dims(cv2.cvtColor( image, cv2.COLOR_BGR2RGB), axis=0) boxes, scores, classes, num = sess.run( [ detection_boxes, detection_scores, detection_classes, num_detections ], feed_dict={image_tensor: image_expanded}) # Visualization of the results of a detection. H, W = image.shape[:2] img_crops = [] det_bbs = [] det_classes = [] det_scores = [] det_aae_bbs = [] det_aae_objects_k = [] #print vis_img.shape boxes = np.squeeze(boxes) scores = np.squeeze(scores) classes = np.squeeze(classes).astype(np.int32) highest_class_score = {clas: 0.0 for clas in classes} for box, score, clas in zip(boxes, scores, classes): if score > det_th and score > highest_class_score[clas]: highest_class_score[clas] = score ymin, xmin, ymax, xmax = (np.array(box) * np.array( [height, width, height, width])).astype(np.int32) h, w = (ymax - ymin, xmax - xmin) det_bbs.append([xmin, ymin, w, h]) det_classes.append(clas) det_scores.append(score) if clas in clas_k_map: det_aae_bbs.append([xmin, ymin, w, h]) det_aae_objects_k.append(clas_k_map[clas]) size = int( np.maximum(h, w) * train_args.getfloat('Dataset', 'PAD_FACTOR')) cx = xmin + (xmax - xmin) / 2 cy = ymin + (ymax - ymin) / 2 left = np.maximum(cx - size / 2, 0) top = np.maximum(cy - size / 2, 0) img_crop = image[top:cy + size / 2, left:cx + size / 2] img_crop = cv2.resize(img_crop, (h_train, w_train)) img_crop = img_crop / 255. img_crops.append(img_crop) if len(det_aae_bbs) > 0: Rs = [] ts = [] for k, bb, img_crop in zip(det_aae_objects_k, det_aae_bbs, img_crops): R, t = all_codebooks[k].auto_pose6d(sess, img_crop, bb, K_test, 1, all_train_args[k], upright=False) Rs.append(R.squeeze()) ts.append(t.squeeze()) Rs = np.array(Rs) ts = np.array(ts) bgr_y, _, _ = renderer.render_many( obj_ids=np.array(det_aae_objects_k).astype(np.int32), W=width / arguments.down, H=height / arguments.down, K=K_down, Rs=Rs, ts=ts, near=1., far=10000., random_light=False, # calc_bbs=False, # depth=False ) bgr_y = cv2.resize(bgr_y, (width, height)) g_y = np.zeros_like(bgr_y) g_y[:, :, 1] = bgr_y[:, :, 1] im_bg = cv2.bitwise_and(image, image, mask=(g_y[:, :, 1] == 0).astype( np.uint8)) image = cv2.addWeighted(im_bg, 1, g_y, 1, 0) for bb, score, clas in zip(det_bbs, det_scores, det_classes): xmin, ymin, xmax, ymax = bb[0], bb[ 1], bb[2] + bb[0], bb[1] + bb[3] cv2.putText( image, '%s : %1.3f' % (category_index[clas]['name'], score), (xmin, ymax + 20), cv2.FONT_ITALIC, .5, color_dict[clas - 1], 2) cv2.rectangle(image, (xmin, ymin), (xmax, ymax), color_dict[clas - 1], 2) if vis_text: cv2.putText(image, "fps: {}".format(fps.fps_local()), (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (77, 255, 9), 2) cv2.imshow('object_detection', image) # Exit Option key = cv2.waitKey(1) if key == ord('q'): break fps.update() # End everything if split_model: gpu_worker.stop() cpu_worker.stop() fps.stop() video_stream.stop() cv2.destroyAllWindows() print('> [INFO] elapsed time (total): {:.2f}'.format(fps.elapsed())) print('> [INFO] approx. FPS: {:.2f}'.format(fps.fps()))
def main(): ''' lxc: use_euclidean means the similarity between test embedding and template embedding are computed using Euclidean Distance ''' #use_euclidean = False parser = argparse.ArgumentParser() parser.add_argument('experiment_name') parser.add_argument('evaluation_name') parser.add_argument('--eval_cfg', default='eval.cfg', required=False) parser.add_argument('--at_step', default=None, required=False) arguments = parser.parse_args() full_name = arguments.experiment_name.split('/') experiment_name = full_name.pop() experiment_group = full_name.pop() if len(full_name) > 0 else '' evaluation_name = arguments.evaluation_name eval_cfg = arguments.eval_cfg at_step = arguments.at_step workspace_path = os.environ.get('AE_WORKSPACE_PATH') train_cfg_file_path = u.get_config_file_path(workspace_path, experiment_name, experiment_group) eval_cfg_file_path = u.get_eval_config_file_path(workspace_path, eval_cfg=eval_cfg) train_args = configparser.ConfigParser() eval_args = configparser.ConfigParser() train_args.read(train_cfg_file_path) eval_args.read(eval_cfg_file_path) #[DATA] # target data params dataset_name = eval_args.get('DATA', 'DATASET') obj_id = eval_args.getint('DATA', 'OBJ_ID') scenes = eval(eval_args.get( 'DATA', 'SCENES')) if len(eval(eval_args.get( 'DATA', 'SCENES'))) > 0 else eval_utils.get_all_scenes_for_obj(eval_args) cam_type = eval_args.get('DATA', 'cam_type') model_type = 'reconst' if dataset_name == 'tless' else '' # model_type set to reconst only for tless. data_params = dataset_params.get_dataset_params(dataset_name, model_type=model_type, train_type='', test_type=cam_type, cam_type=cam_type) target_models_info = inout.load_yaml( data_params['models_info_path']) # lxc # source data params, lxc source_dataset_name = 'toyotalight' # source_dataset_name = train_args.get('DATA','DATASET') # TODO train args no section DATA # source_obj_id = train_args.getint('DATA','OBJ_ID') # TODO train args no section DATA source_obj_id = int(train_cfg_file_path[-6:-4]) # TODO workaround source_data_params = dataset_params.get_dataset_params(source_dataset_name, model_type='', train_type='', test_type='', cam_type='') # for tless temporarily. # source_data_params = dataset_params.get_dataset_params(source_dataset_name, model_type='', train_type='', test_type='kinect', cam_type='kinect') source_models_info = inout.load_yaml( source_data_params['models_info_path']) print("source_models_info_path:", source_data_params['models_info_path']) # 'diameter' is not equal to sqrt(x^2+y^2+z^2) for hinterstoisser, rutgers, tless, tejaniDB. etc. # for toyotalight, 'diameter' == sqrt(...). target_models_3Dlength = np.linalg.norm([ target_models_info[obj_id][key] for key in ['size_x', 'size_y', 'size_z'] ]) source_models_3Dlength = np.linalg.norm([ source_models_info[source_obj_id][key] for key in ['size_x', 'size_y', 'size_z'] ]) target_source_length_ratio = target_models_3Dlength / source_models_3Dlength print("target_source_length_ratio:", target_source_length_ratio) print("source id {:02d}, target id {:02d}".format(source_obj_id, obj_id)) print('basepath: ', data_params['base_path']) #[BBOXES] estimate_bbs = eval_args.getboolean('BBOXES', 'ESTIMATE_BBS') #[METRIC] top_nn = eval_args.getint('METRIC', 'TOP_N') #[EVALUATION] icp = eval_args.getboolean('EVALUATION', 'ICP') evaluation_name = evaluation_name + '_icp' if icp else evaluation_name evaluation_name = evaluation_name + '_bbest' if estimate_bbs else evaluation_name data = dataset_name + '_' + cam_type if len(cam_type) > 0 else dataset_name log_dir = u.get_log_dir(workspace_path, experiment_name, experiment_group) ckpt_dir = u.get_checkpoint_dir(log_dir) eval_dir = u.get_eval_dir(log_dir, evaluation_name, data) # if eval_args.getboolean('EVALUATION','EVALUATE_ERRORS'): # eval_loc.match_and_eval_performance_scores(eval_args, eval_dir) # exit() if not os.path.exists(eval_dir): os.makedirs(eval_dir) shutil.copy2(eval_cfg_file_path, eval_dir) print "eval_args: ", eval_args codebook, dataset, decoder = factory.build_codebook_from_name( experiment_name, experiment_group, return_dataset=True, return_decoder=True) dataset.renderer gpu_options = tf.GPUOptions(allow_growth=True, per_process_gpu_memory_fraction=0.5) config = tf.ConfigProto(gpu_options=gpu_options) sess = tf.Session(config=config) factory.restore_checkpoint(sess, tf.train.Saver(), ckpt_dir, at_step=at_step) if estimate_bbs: #Object Detection, seperate from main # sys.path.append('/net/rmc-lx0050/home_local/sund_ma/src/SSD_Tensorflow') # from ssd_detector import SSD_detector # #TODO: set num_classes, network etc. # ssd = SSD_detector(sess, num_classes=31, net_shape=(300,300)) from rmcssd.bin import detector ssd = detector.Detector(eval_args.get('BBOXES', 'CKPT')) t_errors = [] R_errors = [] all_test_visibs = [] test_embeddings = [] for scene_id in scenes: test_imgs = eval_utils.load_scenes(scene_id, eval_args) test_imgs_depth = eval_utils.load_scenes( scene_id, eval_args, depth=True) if icp else None if estimate_bbs: print eval_args.get('BBOXES', 'EXTERNAL') if eval_args.get('BBOXES', 'EXTERNAL') == 'False': bb_preds = {} for i, img in enumerate(test_imgs): print img.shape bb_preds[i] = ssd.detectSceneBBs(img, min_score=.2, nms_threshold=.45) # inout.save_yaml(os.path.join(scene_res_dir,'bb_preds.yml'), bb_preds) print bb_preds else: bb_preds = inout.load_yaml( os.path.join(eval_args.get('BBOXES', 'EXTERNAL'), '{:02d}.yml'.format(scene_id))) test_img_crops, test_img_depth_crops, bbs, bb_scores, visibilities = eval_utils.generate_scene_crops( test_imgs, test_imgs_depth, bb_preds, eval_args, train_args) else: # test_img_crops: each crop contains some bbox(es) for specified object id. test_img_crops, test_img_depth_crops, bbs, bb_scores, visibilities = eval_utils.get_gt_scene_crops( scene_id, eval_args, train_args) if len(test_img_crops) == 0: print 'ERROR: object %s not in scene %s' % (obj_id, scene_id) exit() info = inout.load_info( data_params['scene_info_mpath'].format(scene_id)) Ks_test = [np.array(v['cam_K']).reshape(3, 3) for v in info.values()] ######remove gts = inout.load_gt(data_params['scene_gt_mpath'].format(scene_id)) visib_gts = inout.load_yaml(data_params['scene_gt_stats_mpath'].format( scene_id, 15)) ####### W_test, H_test = data_params['test_im_size'] icp_renderer = icp_utils.SynRenderer(train_args) if icp else None noof_scene_views = eval_utils.noof_scene_views(scene_id, eval_args) test_embeddings.append([]) scene_res_dir = os.path.join( eval_dir, '{scene_id:02d}'.format(scene_id=scene_id)) if not os.path.exists(scene_res_dir): os.makedirs(scene_res_dir) for view in xrange( noof_scene_views ): # for example, LINEMOD ape noof_scene_views = 1236 try: # only a specified object id is selected throughout the whole scene views. test_crops, test_crops_depth, test_bbs, test_scores, test_visibs = eval_utils.select_img_crops( test_img_crops[view][obj_id], test_img_depth_crops[view][obj_id] if icp else None, bbs[view][obj_id], bb_scores[view][obj_id], visibilities[view][obj_id], eval_args) except: print 'no detections' continue print view preds = {} pred_views = [] all_test_visibs.append(test_visibs[0]) t_errors_crop = [] R_errors_crop = [] for i, (test_crop, test_bb, test_score) in enumerate( zip(test_crops, test_bbs, test_scores)): # each test_crop is a ground truth patch if train_args.getint('Dataset', 'C') == 1: test_crop = cv2.cvtColor(test_crop, cv2.COLOR_BGR2GRAY)[:, :, None] start = time.time() '''modify here to change the pose estimation algorithm. lxc''' Rs_est, ts_est = codebook.auto_pose6d( sess, test_crop, test_bb, Ks_test[view].copy(), top_nn, train_args, target_source_length_ratio=target_source_length_ratio) ae_time = time.time() - start run_time = ae_time + bb_preds[view][0][ 'det_time'] if estimate_bbs else ae_time if eval_args.getboolean('PLOT', 'EMBEDDING_PCA'): test_embeddings[-1].append( codebook.test_embedding(sess, test_crop, normalized=True)) # icp = False if view<350 else True #TODO: Rs_est_old, ts_est_old = Rs_est.copy(), ts_est.copy() for p in xrange(top_nn): if icp: start = time.time() # icp only along tz R_est_refined, t_est_refined = icp_utils.icp_refinement( test_crops_depth[i], icp_renderer, Rs_est[p], ts_est[p], Ks_test[view].copy(), (W_test, H_test), depth_only=True, max_mean_dist_factor=5.0) print ts_est[p] print t_est_refined # x,y update,does not change tz: _, ts_est_refined = codebook.auto_pose6d( sess, test_crop, test_bb, Ks_test[view].copy(), top_nn, train_args, depth_pred=t_est_refined[2]) # commented by lxc # _, ts_est_refined, _ = codebook.auto_pose6d(sess, test_crop, test_bb, Ks_test[view].copy(), top_nn, train_args,depth_pred=t_est_refined[2]) t_est_refined = ts_est_refined[p] # rotation icp, only accepted if below 20 deg change R_est_refined, _ = icp_utils.icp_refinement( test_crops_depth[i], icp_renderer, R_est_refined, t_est_refined, Ks_test[view].copy(), (W_test, H_test), no_depth=True) print Rs_est[p] print R_est_refined icp_time = time.time() - start Rs_est[p], ts_est[p] = R_est_refined, t_est_refined preds.setdefault('ests', []).append({ 'score': test_score, 'R': Rs_est[p], 't': ts_est[p] }) run_time = run_time + icp_time if icp else run_time min_t_err, min_R_err = eval_plots.print_trans_rot_errors( gts[view], obj_id, ts_est, ts_est_old, Rs_est, Rs_est_old) t_errors_crop.append(min_t_err) R_errors_crop.append(min_R_err) if eval_args.getboolean('PLOT', 'RECONSTRUCTION'): eval_plots.plot_reconstruction_test( sess, codebook._encoder, decoder, test_crop) # eval_plots.plot_reconstruction_train(sess, decoder, nearest_train_codes[0]) if eval_args.getboolean('PLOT', 'NEAREST_NEIGHBORS') and not icp: for R_est, t_est in zip(Rs_est, ts_est): pred_views.append( dataset.render_rot(R_est, downSample=2)) eval_plots.show_nearest_rotation(pred_views, test_crop, view) if eval_args.getboolean('PLOT', 'SCENE_WITH_ESTIMATE'): eval_plots.plot_scene_with_estimate( test_imgs[view].copy(), icp_renderer.renderer if icp else dataset.renderer, Ks_test[view].copy(), Rs_est_old[0], ts_est_old[0], Rs_est[0], ts_est[0], test_bb, test_score, obj_id, gts[view], bb_preds[view] if estimate_bbs else None) if cv2.waitKey(1) == 32: cv2.waitKey(0) t_errors.append(t_errors_crop[np.argmin( np.linalg.norm(np.array(t_errors_crop), axis=1))]) R_errors.append(R_errors_crop[np.argmin( np.linalg.norm(np.array(t_errors_crop), axis=1))]) # save predictions in sixd format res_path = os.path.join(scene_res_dir, '%04d_%02d.yml' % (view, obj_id)) inout.save_results_sixd17(res_path, preds, run_time=run_time) if not os.path.exists(os.path.join(eval_dir, 'latex')): os.makedirs(os.path.join(eval_dir, 'latex')) if not os.path.exists(os.path.join(eval_dir, 'figures')): os.makedirs(os.path.join(eval_dir, 'figures')) '''evaluation code dataset_renderer renders source object model for evaluation; If we need target object model for evaluation, go get a new renderer. ''' if eval_args.getboolean('EVALUATION', 'COMPUTE_ERRORS'): eval_calc_errors.eval_calc_errors(eval_args, eval_dir, dataset_renderer=dataset.renderer) if eval_args.getboolean('EVALUATION', 'EVALUATE_ERRORS'): eval_loc.match_and_eval_performance_scores(eval_args, eval_dir) '''plot code''' cyclo = train_args.getint('Embedding', 'NUM_CYCLO') if eval_args.getboolean('PLOT', 'EMBEDDING_PCA'): embedding = sess.run(codebook.embedding_normalized) eval_plots.compute_pca_plot_embedding(eval_dir, embedding[::cyclo], np.array(test_embeddings[0]), obj_id=obj_id) if eval_args.getboolean('PLOT', 'VIEWSPHERE'): eval_plots.plot_viewsphere_for_embedding( dataset.viewsphere_for_embedding[::cyclo], eval_dir, obj_id=obj_id) if eval_args.getboolean('PLOT', 'CUM_T_ERROR_HIST'): eval_plots.plot_t_err_hist(np.array(t_errors), eval_dir, obj_id=obj_id) eval_plots.plot_t_err_hist2(np.array(t_errors), eval_dir, obj_id=obj_id) if eval_args.getboolean('PLOT', 'CUM_R_ERROR_HIST'): eval_plots.plot_R_err_hist(eval_args, eval_dir, scenes) eval_plots.plot_R_err_hist2(np.array(R_errors), eval_dir, obj_id=obj_id) if eval_args.getboolean('PLOT', 'CUM_VSD_ERROR_HIST'): eval_plots.plot_vsd_err_hist(eval_args, eval_dir, scenes) if eval_args.getboolean('PLOT', 'VSD_OCCLUSION'): eval_plots.plot_vsd_occlusion(eval_args, eval_dir, scenes, np.array(all_test_visibs)) if eval_args.getboolean('PLOT', 'R_ERROR_OCCLUSION'): eval_plots.plot_re_rect_occlusion(eval_args, eval_dir, scenes, np.array(all_test_visibs)) if eval_args.getboolean('PLOT', 'ANIMATE_EMBEDDING_PCA'): eval_plots.animate_embedding_path(test_embeddings[0]) if eval_args.getboolean('PLOT', 'RECONSTRUCTION_TEST_BATCH'): eval_plots.plot_reconstruction_test_batch(sess, codebook, decoder, test_img_crops, noof_scene_views, obj_id, eval_dir=eval_dir) # plt.show() # calculate 6D pose errors # print 'exiting ...' # eval_calc_errors.eval_calc_errors(eval_args, eval_dir) # calculate 6D pose errors report = latex_report.Report(eval_dir, log_dir) report.write_configuration(train_cfg_file_path, eval_cfg_file_path) report.merge_all_tex_files() report.include_all_figures() report.save(open_pdf=False)
workspace_path = os.environ.get('AE_WORKSPACE_PATH') if workspace_path == None: print 'Please define a workspace path:\n' print 'export AE_WORKSPACE_PATH=/path/to/workspace\n' exit(-1) log_dir = utils.get_log_dir(workspace_path, experiment_name, experiment_group) ckpt_dir = utils.get_checkpoint_dir(log_dir) codebook, dataset = factory.build_codebook_from_name(experiment_name, experiment_group, return_dataset=True) with tf.Session() as sess: factory.restore_checkpoint(sess, tf.train.Saver(), ckpt_dir, at_step=None) # try at_step = 2000 # Rpred_list = [] #lxc for file in files: im = cv2.imread(file) im = cv2.resize(im, (128, 128)) R = codebook.nearest_rotation(sess, im, top_n=3) print R # Rpred_list.append(R.reshape(1,-1)) #lxc pred_view = dataset.render_rot(R, downSample=1) cv2.imshow('resized img', cv2.resize(im / 255., (256, 256))) cv2.imshow('pred_view', cv2.resize(pred_view, (256, 256))) if cv2.waitKey(0): continue # np.savetxt('/media/lxc/6044A61C44A5F546/LXC/Graduate2Spring/Grasp/aae_workspace/experiments/exp_group/dolphin_stl/Rpred.txt', np.array(Rpred_list).squeeze(), fmt='%5.5f', delimiter=',')