modify bug of Squeeze-residual and ssd export mindir failed

model_zoo/official/cv/squeezenet/squeezenet_residual_cifar10_config.yaml

@@ -11,6 +11,7 @@ data_path: "/cache/data"
 output_path: "/cache/train"
 load_path: "/cache/checkpoint_path/"
 device_num: 1
+device_id: 0
 device_target: 'Ascend'
 checkpoint_path: './checkpoint/'
 checkpoint_file_path: 'suqeezenet_residual_cifar10-150_195.ckpt'

model_zoo/official/cv/ssd/README.md

@@ -182,9 +182,6 @@ Create a container layer over the created image and start it
 bash scripts/docker_start.sh ssd:20.1.0 [DATA_DIR] [MODEL_DIR]
 ```
 
-如果要在modelarts上进行模型的训练，可以参考modelarts的官方指导文档(https://support.huaweicloud.com/modelarts/)
-开始进行模型的训练和推理，具体操作如下：
-
 If you want to run in modelarts, please check the official documentation of [modelarts](https://support.huaweicloud.com/modelarts/), and you can start training and evaluation as follows:
 
 ```python

model_zoo/official/cv/ssd/export.py

@@ -27,6 +27,13 @@ if config.device_target == "Ascend":
     context.set_context(device_id=config.device_id)
 
 if __name__ == '__main__':
+    if hasattr(config, 'num_ssd_boxes') and config.num_ssd_boxes == -1:
+        num = 0
+        h, w = config.img_shape
+        for i in range(len(config.steps)):
+            num += (h // config.steps[i]) * (w // config.steps[i]) * config.num_default[i]
+        config.num_ssd_boxes = num
+
     if config.model_name == "ssd300":
         net = SSD300(ssd_mobilenet_v2(), config, is_training=False)
     elif config.model_name == "ssd_vgg16":
@@ -38,13 +45,6 @@ if __name__ == '__main__':
     else:
         raise ValueError(f'config.model: {config.model_name} is not supported')
 
-    if hasattr(config, 'num_ssd_boxes') and config.num_ssd_boxes == -1:
-        num = 0
-        h, w = config.img_shape
-        for i in range(len(config.steps)):
-            num += (h // config.steps[i]) * (w // config.steps[i]) * config.num_default[i]
-        config.num_ssd_boxes = num
-
     net = SsdInferWithDecoder(net, Tensor(default_boxes), config)
 
     param_dict = load_checkpoint(config.checkpoint_file_path)