def ssd_eval(dataset_path, ckpt_path, anno_json): """SSD evaluation.""" batch_size = 1 ds = create_ssd_dataset(dataset_path, batch_size=batch_size, repeat_num=1, is_training=False, use_multiprocessing=False) if config.model == "ssd300": net = SSD300(ssd_mobilenet_v2(), config, is_training=False) elif config.model == "ssd_vgg16": net = ssd_vgg16(config=config) elif config.model == "ssd_mobilenet_v1_fpn": net = ssd_mobilenet_v1_fpn(config=config) elif config.model == "ssd_resnet50_fpn": net = ssd_resnet50_fpn(config=config) else: raise ValueError(f'config.model: {config.model} is not supported') net = SsdInferWithDecoder(net, Tensor(default_boxes), config) print("Load Checkpoint!") param_dict = load_checkpoint(ckpt_path) net.init_parameters_data() load_param_into_net(net, param_dict) net.set_train(False) total = ds.get_dataset_size() * batch_size print("\n========================================\n") print("total images num: ", total) print("Processing, please wait a moment.") eval_param_dict = {"net": net, "dataset": ds, "anno_json": anno_json} mAP = apply_eval(eval_param_dict) print("\n========================================\n") print(f"mAP: {mAP}")
def ssd_eval(dataset_path, ckpt_path, anno_json): """SSD evaluation.""" batch_size = 1 ds = create_ssd_dataset(dataset_path, batch_size=batch_size, repeat_num=1, is_training=False, use_multiprocessing=False) if config.model == "ssd300": net = SSD300(ssd_mobilenet_v2(), config, is_training=False) elif config.model == "ssd_vgg16": net = ssd_vgg16(config=config) elif config.model == "ssd_mobilenet_v1_fpn": net = ssd_mobilenet_v1_fpn(config=config) elif config.model == "ssd_resnet50_fpn": net = ssd_resnet50_fpn(config=config) else: raise ValueError(f'config.model: {config.model} is not supported') net = SsdInferWithDecoder(net, Tensor(default_boxes), config) print("Load Checkpoint!") param_dict = load_checkpoint(ckpt_path) net.init_parameters_data() load_param_into_net(net, param_dict) net.set_train(False) i = batch_size total = ds.get_dataset_size() * batch_size start = time.time() pred_data = [] print("\n========================================\n") print("total images num: ", total) print("Processing, please wait a moment.") for data in ds.create_dict_iterator(output_numpy=True, num_epochs=1): img_id = data['img_id'] img_np = data['image'] image_shape = data['image_shape'] output = net(Tensor(img_np)) for batch_idx in range(img_np.shape[0]): pred_data.append({ "boxes": output[0].asnumpy()[batch_idx], "box_scores": output[1].asnumpy()[batch_idx], "img_id": int(np.squeeze(img_id[batch_idx])), "image_shape": image_shape[batch_idx] }) percent = round(i / total * 100., 2) print(f' {str(percent)} [{i}/{total}]', end='\r') i += batch_size cost_time = int((time.time() - start) * 1000) print(f' 100% [{total}/{total}] cost {cost_time} ms') mAP = metrics(pred_data, anno_json) print("\n========================================\n") print(f"mAP: {mAP}")
parser.add_argument('--file_format', type=str, choices=["AIR", "MINDIR"], default='AIR', help='file format') parser.add_argument("--device_target", type=str, choices=["Ascend", "GPU", "CPU"], default="Ascend", help="device target") args = parser.parse_args() context.set_context(mode=context.GRAPH_MODE, device_target=args.device_target) if args.device_target == "Ascend": context.set_context(device_id=args.device_id) if __name__ == '__main__': if config.model == "ssd300": net = SSD300(ssd_mobilenet_v2(), config, is_training=False) elif config.model == "ssd_vgg16": net = ssd_vgg16(config=config) elif config.model == "ssd_mobilenet_v1_fpn": net = ssd_mobilenet_v1_fpn(config=config) elif config.model == "ssd_resnet50_fpn": net = ssd_resnet50_fpn(config=config) else: raise ValueError(f'config.model: {config.model} is not supported') net = SsdInferWithDecoder(net, Tensor(default_boxes), config) param_dict = load_checkpoint(args.ckpt_file) net.init_parameters_data() load_param_into_net(net, param_dict) net.set_train(False) input_shp = [args.batch_size, 3] + config.img_shape input_array = Tensor(np.random.uniform(-1.0, 1.0, size=input_shp), mindspore.float32) export(net, input_array, file_name=args.file_name, file_format=args.file_format)
def main(): args_opt = get_args() rank = 0 device_num = 1 if args_opt.run_platform == "CPU": context.set_context(mode=context.GRAPH_MODE, device_target="CPU") else: context.set_context(mode=context.GRAPH_MODE, device_target=args_opt.run_platform, device_id=args_opt.device_id) if args_opt.distribute: device_num = args_opt.device_num context.reset_auto_parallel_context() context.set_auto_parallel_context( parallel_mode=ParallelMode.DATA_PARALLEL, gradients_mean=True, device_num=device_num) init() if config.model == "ssd_resnet50_fpn": context.set_auto_parallel_context( all_reduce_fusion_config=[90, 183, 279]) if config.model == "ssd_vgg16": context.set_auto_parallel_context( all_reduce_fusion_config=[20, 41, 62]) else: context.set_auto_parallel_context( all_reduce_fusion_config=[29, 58, 89]) rank = get_rank() mindrecord_file = create_mindrecord(args_opt.dataset, "ssd.mindrecord", True) if args_opt.only_create_dataset: return loss_scale = float(args_opt.loss_scale) if args_opt.run_platform == "CPU": loss_scale = 1.0 # When create MindDataset, using the fitst mindrecord file, such as ssd.mindrecord0. use_multiprocessing = (args_opt.run_platform != "CPU") dataset = create_ssd_dataset(mindrecord_file, repeat_num=1, batch_size=args_opt.batch_size, device_num=device_num, rank=rank, use_multiprocessing=use_multiprocessing) dataset_size = dataset.get_dataset_size() print(f"Create dataset done! dataset size is {dataset_size}") ssd = ssd_model_build(args_opt) if ("use_float16" in config and config.use_float16) or args_opt.run_platform == "GPU": ssd.to_float(dtype.float16) net = SSDWithLossCell(ssd, config) # checkpoint ckpt_config = CheckpointConfig(save_checkpoint_steps=dataset_size * args_opt.save_checkpoint_epochs) save_ckpt_path = './ckpt_' + str(rank) + '/' ckpoint_cb = ModelCheckpoint(prefix="ssd", directory=save_ckpt_path, config=ckpt_config) if args_opt.pre_trained: param_dict = load_checkpoint(args_opt.pre_trained) if args_opt.filter_weight: filter_checkpoint_parameter_by_list(param_dict, config.checkpoint_filter_list) load_param_into_net(net, param_dict, True) lr = Tensor( get_lr(global_step=args_opt.pre_trained_epoch_size * dataset_size, lr_init=config.lr_init, lr_end=config.lr_end_rate * args_opt.lr, lr_max=args_opt.lr, warmup_epochs=config.warmup_epochs, total_epochs=args_opt.epoch_size, steps_per_epoch=dataset_size)) if "use_global_norm" in config and config.use_global_norm: opt = nn.Momentum( filter(lambda x: x.requires_grad, net.get_parameters()), lr, config.momentum, config.weight_decay, 1.0) net = TrainingWrapper(net, opt, loss_scale, True) else: opt = nn.Momentum( filter(lambda x: x.requires_grad, net.get_parameters()), lr, config.momentum, config.weight_decay, loss_scale) net = TrainingWrapper(net, opt, loss_scale) callback = [TimeMonitor(data_size=dataset_size), LossMonitor(), ckpoint_cb] if args_opt.run_eval: eval_net = SsdInferWithDecoder(ssd, Tensor(default_boxes), config) eval_net.set_train(False) mindrecord_file = create_mindrecord(args_opt.dataset, "ssd_eval.mindrecord", False) eval_dataset = create_ssd_dataset(mindrecord_file, batch_size=args_opt.batch_size, repeat_num=1, is_training=False, use_multiprocessing=False) if args_opt.dataset == "coco": anno_json = os.path.join( config.coco_root, config.instances_set.format(config.val_data_type)) elif args_opt.dataset == "voc": anno_json = os.path.join(config.voc_root, config.voc_json) else: raise ValueError( 'SSD eval only support dataset mode is coco and voc!') eval_param_dict = { "net": eval_net, "dataset": eval_dataset, "anno_json": anno_json } eval_cb = EvalCallBack(apply_eval, eval_param_dict, interval=args_opt.eval_interval, eval_start_epoch=args_opt.eval_start_epoch, save_best_ckpt=True, ckpt_directory=save_ckpt_path, besk_ckpt_name="best_map.ckpt", metrics_name="mAP") callback.append(eval_cb) model = Model(net) dataset_sink_mode = False if args_opt.mode == "sink" and args_opt.run_platform != "CPU": print("In sink mode, one epoch return a loss.") dataset_sink_mode = True print( "Start train SSD, the first epoch will be slower because of the graph compilation." ) model.train(args_opt.epoch_size, dataset, callbacks=callback, dataset_sink_mode=dataset_sink_mode)