mindir_suffix

model_zoo/official/cv/cnnctc/export.py

@@ -26,7 +26,7 @@ context.set_context(mode=context.GRAPH_MODE, device_target="Ascend")
 
 parser = argparse.ArgumentParser(description='CNNCTC_export')
 parser.add_argument('--ckpt_file', type=str, default='./ckpts/cnn_ctc.ckpt', help='CNN&CTC ckpt file.')
-parser.add_argument('--output_file', type=str, default='cnn_ctc.air', help='CNN&CTC output air name.')
+parser.add_argument('--output_file', type=str, default='cnn_ctc', help='CNN&CTC output air name.')
 args_opt = parser.parse_args()
 
 if __name__ == '__main__':

model_zoo/official/cv/deeplabv3/export.py

@@ -39,4 +39,4 @@ if __name__ == '__main__':
     # load the parameter into net
     load_param_into_net(network, param_dict)
     input_data = np.random.uniform(0.0, 1.0, size=[32, 3, 513, 513]).astype(np.float32)
-    export(network, Tensor(input_data), file_name=args.model+'-300_11.air', file_format='AIR')
+    export(network, Tensor(input_data), file_name=args.model+'-300_11', file_format='AIR')

model_zoo/official/cv/googlenet/src/config.py

@@ -33,8 +33,8 @@ cifar_cfg = edict({
     'device_id': 0,
     'keep_checkpoint_max': 10,
     'checkpoint_path': './train_googlenet_cifar10-125_390.ckpt',
-    'onnx_filename': 'googlenet.onnx',
-    'air_filename': 'googlenet.air'
+    'onnx_filename': 'googlenet',
+    'air_filename': 'googlenet'
 })
 
 imagenet_cfg = edict({
@@ -54,8 +54,8 @@ imagenet_cfg = edict({
     'device_id': 0,
     'keep_checkpoint_max': 10,
     'checkpoint_path': None,
-    'onnx_filename': 'googlenet.onnx',
-    'air_filename': 'googlenet.air',
+    'onnx_filename': 'googlenet',
+    'air_filename': 'googlenet',
 
     # optimizer and lr related
     'lr_scheduler': 'exponential',

model_zoo/official/cv/inceptionv3/export.py

@@ -26,7 +26,7 @@ from src.inception_v3 import InceptionV3
 
 parser = argparse.ArgumentParser(description='inceptionv3 export')
 parser.add_argument('--ckpt_file', type=str, required=True, help='inceptionv3 ckpt file.')
-parser.add_argument('--output_file', type=str, default='inceptionv3.air', help='inceptionv3 output air name.')
+parser.add_argument('--output_file', type=str, default='inceptionv3', help='inceptionv3 output air name.')
 parser.add_argument('--file_format', type=str, choices=["AIR", "ONNX", "MINDIR"], default='AIR', help='file format')
 parser.add_argument('--width', type=int, default=299, help='input width')
 parser.add_argument('--height', type=int, default=299, help='input height')

model_zoo/official/cv/lenet/src/config.py

@@ -29,5 +29,5 @@ mnist_cfg = edict({
     'image_width': 32,
     'save_checkpoint_steps': 1875,
     'keep_checkpoint_max': 10,
-    'air_name': "lenet.air",
+    'air_name': "lenet",
 })

model_zoo/official/cv/lenet_quant/export.py

@@ -54,4 +54,4 @@ if __name__ == "__main__":
 
     # export network
     inputs = Tensor(np.ones([1, 1, cfg.image_height, cfg.image_width]), mindspore.float32)
-    export(network, inputs, file_name="lenet_quant.mindir", file_format='MINDIR', quant_mode='AUTO')
+    export(network, inputs, file_name="lenet_quant", file_format='MINDIR', quant_mode='AUTO')

model_zoo/official/cv/mobilenetv2/src/config.py

@@ -42,7 +42,7 @@ def set_config(args):
         "platform": args.platform,
         "activation": "Softmax",
         "export_format": "MINDIR",
-        "export_file": "mobilenetv2.mindir"
+        "export_file": "mobilenetv2"
     })
     config_gpu = ed({
         "num_classes": 1000,
@@ -66,7 +66,7 @@ def set_config(args):
         "run_distribute": args.run_distribute,
         "activation": "Softmax",
         "export_format": "MINDIR",
-        "export_file": "mobilenetv2.mindir"
+        "export_file": "mobilenetv2"
     })
     config_ascend = ed({
         "num_classes": 1000,
@@ -93,7 +93,7 @@ def set_config(args):
         "run_distribute": int(os.getenv('RANK_SIZE', '1')) > 1.,
         "activation": "Softmax",
         "export_format": "MINDIR",
-        "export_file": "mobilenetv2.mindir"
+        "export_file": "mobilenetv2"
     })
     config = ed({"CPU": config_cpu,
                  "GPU": config_gpu,

model_zoo/official/cv/mobilenetv2_quant/export.py

@@ -51,5 +51,5 @@ if __name__ == '__main__':
     # export network
     print("============== Starting export ==============")
     inputs = Tensor(np.ones([1, 3, cfg.image_height, cfg.image_width]), mindspore.float32)
-    export(network, inputs, file_name="mobilenet_quant.mindir", file_format='MINDIR', quant_mode='AUTO')
+    export(network, inputs, file_name="mobilenet_quant", file_format='MINDIR', quant_mode='AUTO')
     print("============== End export ==============")

model_zoo/official/cv/mobilenetv3/src/config.py

@@ -34,5 +34,5 @@ config_gpu = ed({
     "keep_checkpoint_max": 500,
     "save_checkpoint_path": "./checkpoint",
     "export_format": "MINDIR",
-    "export_file": "mobilenetv3.mindir"
+    "export_file": "mobilenetv3"
 })

model_zoo/official/cv/nasnet/src/config.py

@@ -51,6 +51,6 @@ nasnet_a_mobile_config_gpu = edict({
     "loss_scale": 1,
 
     ### onnx&air Config
-    'onnx_filename': 'nasnet_a_mobile.onnx',
-    'air_filename': 'nasnet_a_mobile.air'
+    'onnx_filename': 'nasnet_a_mobile',
+    'air_filename': 'nasnet_a_mobile'
 })

model_zoo/official/cv/resnet_thor/export.py

@@ -41,4 +41,4 @@ if __name__ == '__main__':
     load_param_into_net(net, param_dict)
 
     inputs = np.random.uniform(0.0, 1.0, size=[1, 3, 224, 224]).astype(np.float32)
-    export(net, Tensor(inputs), file_name='resnet-42_5004.air', file_format='AIR')
+    export(net, Tensor(inputs), file_name='resnet-42_5004', file_format='AIR')

model_zoo/official/cv/resnext50/src/config.py

@@ -44,5 +44,5 @@ config = ed({
     "rank": 0,
     "group_size": 1,
     "export_format": "MINDIR",
-    "export_file": "resnext50.mindir"
+    "export_file": "resnext50"
 })

model_zoo/official/cv/squeezenet/export.py

@@ -39,8 +39,8 @@ if __name__ == '__main__':
     else:
         num_classes = 1000
 
-    onnx_filename = args_opt.net + '_' + args_opt.dataset + '.onnx'
-    air_filename = args_opt.net + '_' + args_opt.dataset + '.air'
+    onnx_filename = args_opt.net + '_' + args_opt.dataset
+    air_filename = args_opt.net + '_' + args_opt.dataset
 
     net = squeezenet(num_classes=num_classes)
 

model_zoo/official/cv/ssd/export.py

@@ -26,7 +26,7 @@ parser = argparse.ArgumentParser(description='SSD export')
 parser.add_argument("--device_id", type=int, default=0, help="Device id")
 parser.add_argument("--batch_size", type=int, default=1, help="batch size")
 parser.add_argument("--ckpt_file", type=str, required=True, help="Checkpoint file path.")
-parser.add_argument("--file_name", type=str, default="ssd.air", help="output file name.")
+parser.add_argument("--file_name", type=str, default="ssd", help="output file name.")
 parser.add_argument('--file_format', type=str, choices=["AIR", "ONNX", "MINDIR"], default='AIR', help='file format')
 args = parser.parse_args()
 

model_zoo/official/cv/unet/export.py

@@ -23,7 +23,7 @@ from src.unet.unet_model import UNet
 parser = argparse.ArgumentParser(description='Export ckpt to air')
 parser.add_argument('--ckpt_file', type=str, default="ckpt_unet_medical_adam-1_600.ckpt",
                     help='The path of input ckpt file')
-parser.add_argument('--air_file', type=str, default="unet_medical_adam-1_600.air", help='The path of output air file')
+parser.add_argument('--air_file', type=str, default="unet_medical_adam-1_600", help='The path of output air file')
 args = parser.parse_args()
 
 net = UNet(n_channels=1, n_classes=2)

model_zoo/official/cv/vgg16/export.py

@@ -27,7 +27,7 @@ context.set_context(mode=context.GRAPH_MODE, device_target="Ascend")
 parser = argparse.ArgumentParser(description='VGG16 export')
 parser.add_argument('--dataset', type=str, choices=["cifar10", "imagenet2012"], default="cifar10", help='ckpt file')
 parser.add_argument('--ckpt_file', type=str, required=True, help='vgg16 ckpt file.')
-parser.add_argument('--output_file', type=str, default='vgg16.air', help='vgg16 output air name.')
+parser.add_argument('--output_file', type=str, default='vgg16', help='vgg16 output air name.')
 parser.add_argument('--file_format', type=str, choices=["AIR", "ONNX", "MINDIR"], default='AIR', help='file format')
 args = parser.parse_args()
 

model_zoo/official/cv/yolov3_darknet53/export.py

@@ -26,7 +26,7 @@ parser = argparse.ArgumentParser(description='yolov3_darknet53 export')
 parser.add_argument("--device_id", type=int, default=0, help="Device id")
 parser.add_argument("--batch_size", type=int, default=1, help="batch size")
 parser.add_argument("--ckpt_file", type=str, required=True, help="Checkpoint file path.")
-parser.add_argument("--file_name", type=str, default="yolov3_darknet53.air", help="output file name.")
+parser.add_argument("--file_name", type=str, default="yolov3_darknet53", help="output file name.")
 parser.add_argument('--file_format', type=str, choices=["AIR", "ONNX", "MINDIR"], default='AIR', help='file format')
 args = parser.parse_args()
 

model_zoo/official/cv/yolov3_darknet53_quant/export.py

@@ -27,7 +27,7 @@ parser = argparse.ArgumentParser(description='yolov3_darknet53_quant export')
 parser.add_argument("--device_id", type=int, default=0, help="Device id")
 parser.add_argument("--batch_size", type=int, default=1, help="batch size")
 parser.add_argument("--ckpt_file", type=str, required=True, help="Checkpoint file path.")
-parser.add_argument("--file_name", type=str, default="yolov3_darknet53_quant.mindir", help="output file name.")
+parser.add_argument("--file_name", type=str, default="yolov3_darknet53_quant", help="output file name.")
 parser.add_argument('--file_format', type=str, choices=["AIR", "ONNX", "MINDIR"], default='MINDIR', help='file format')
 args = parser.parse_args()
 

model_zoo/official/cv/yolov3_resnet18/export.py

@@ -26,7 +26,7 @@ parser = argparse.ArgumentParser(description='yolov3_resnet18 export')
 parser.add_argument("--device_id", type=int, default=0, help="Device id")
 parser.add_argument("--batch_size", type=int, default=1, help="batch size")
 parser.add_argument("--ckpt_file", type=str, required=True, help="Checkpoint file path.")
-parser.add_argument("--file_name", type=str, default="yolov3_resnet18.air", help="output file name.")
+parser.add_argument("--file_name", type=str, default="yolov3_resnet18", help="output file name.")
 parser.add_argument('--file_format', type=str, choices=["AIR", "ONNX", "MINDIR"], default='AIR', help='file format')
 args = parser.parse_args()
 

model_zoo/official/cv/yolov4/export.py

@@ -26,7 +26,7 @@ parser.add_argument("--device_id", type=int, default=0, help="Device id")
 parser.add_argument("--batch_size", type=int, default=1, help="batch size")
 parser.add_argument("--testing_shape", type=int, default=608, help="test shape")
 parser.add_argument("--ckpt_file", type=str, required=True, help="Checkpoint file path.")
-parser.add_argument("--file_name", type=str, default="yolov4.air", help="output file name.")
+parser.add_argument("--file_name", type=str, default="yolov4", help="output file name.")
 parser.add_argument('--file_format', type=str, choices=["AIR", "ONNX", "MINDIR"], default='AIR', help='file format')
 args = parser.parse_args()
 

model_zoo/official/nlp/bert/export.py

@@ -34,7 +34,7 @@ parser.add_argument('--downstream_task', type=str, choices=["NER", "CLS", "SQUAD
 parser.add_argument('--num_class', type=int, default=41, help='The number of class, default is 41.')
 parser.add_argument('--label_file_path', type=str, default="", help='label file path, used in clue benchmark.')
 parser.add_argument('--ckpt_file', type=str, required=True, help='Bert ckpt file.')
-parser.add_argument('--output_file', type=str, default='Bert.air', help='bert output air name.')
+parser.add_argument('--output_file', type=str, default='Bert', help='bert output air name.')
 parser.add_argument('--file_format', type=str, choices=["AIR", "ONNX", "MINDIR"], default='AIR', help='file format')
 args = parser.parse_args()
 

model_zoo/official/nlp/tinybert/export.py

@@ -26,7 +26,7 @@ from src.tinybert_model import BertModelCLS
 
 parser = argparse.ArgumentParser(description='tinybert task distill')
 parser.add_argument('--ckpt_file', type=str, required=True, help='tinybert ckpt file.')
-parser.add_argument('--output_file', type=str, default='tinybert.air', help='tinybert output air name.')
+parser.add_argument('--output_file', type=str, default='tinybert', help='tinybert output air name.')
 parser.add_argument('--task_name', type=str, default='SST-2', choices=['SST-2', 'QNLI', 'MNLI'], help='task name')
 args = parser.parse_args()
 

model_zoo/official/recommend/wide_and_deep/export.py

@@ -56,5 +56,5 @@ if __name__ == '__main__':
     ids = Tensor(np.ones([widedeep_config.eval_batch_size, widedeep_config.field_size]).astype(np.int32))
     wts = Tensor(np.ones([widedeep_config.eval_batch_size, widedeep_config.field_size]).astype(np.float32))
     input_tensor_list = [ids, wts]
-    export(net, *input_tensor_list, file_name='wide_and_deep.onnx', file_format="ONNX")
-    export(net, *input_tensor_list, file_name='wide_and_deep.air', file_format="AIR")
+    export(net, *input_tensor_list, file_name='wide_and_deep', file_format="ONNX")
+    export(net, *input_tensor_list, file_name='wide_and_deep', file_format="AIR")

serving/example/export_model/add_model.py

@@ -35,7 +35,7 @@ def export_net():
     y = np.ones([2, 2]).astype(np.float32)
     add = Net()
     output = add(Tensor(x), Tensor(y))
-    export(add, Tensor(x), Tensor(y), file_name='tensor_add.mindir', file_format='MINDIR')
+    export(add, Tensor(x), Tensor(y), file_name='tensor_add', file_format='MINDIR')
     print(x)
     print(y)
     print(output.asnumpy())

tests/st/quantization/lenet_quant/test_lenet_quant.py

@@ -147,7 +147,7 @@ def export_lenet():
 
     # export network
     inputs = Tensor(np.ones([1, 1, cfg.image_height, cfg.image_width]), mstype.float32)
-    export(network, inputs, file_name="lenet_quant.mindir", file_format='MINDIR', quant_mode='AUTO')
+    export(network, inputs, file_name="lenet_quant", file_format='MINDIR', quant_mode='AUTO')
 
 
 @pytest.mark.level0

tests/ut/python/utils/test_serialize.py

@@ -331,7 +331,7 @@ def test_export():
 def test_mindir_export():
     net = MYNET()
     input_data = Tensor(np.random.randint(0, 255, [1, 3, 224, 224]).astype(np.float32))
-    export(net, input_data, file_name="./me_binary_export.mindir", file_format="MINDIR")
+    export(net, input_data, file_name="./me_binary_export", file_format="MINDIR")
 
 
 class PrintNet(nn.Cell):