TensorFlow 服务对象检测答案

【问题标题】：TensorFlow Serving Object DetectionTensorFlow 服务对象检测
【发布时间】：2022-06-27 19:07:37
【问题描述】：

我在为 TensorFlow 对象检测模型提供服务时遇到问题。我从 tensorflow 模型存储库中训练了一个模型，并设置了一个 tensorflow 服务实例。但是当我提出请求时，维度存在问题。我正在使用 tolist() 方法将图像的 numpy 数组转换为 json 编码器可以使用的东西。 tolist() 函数似乎通过使列表相互递归来维护 numpy 数组的结构，所以我不确定 tf-serving 在哪里得到一个形状为 [339450,3] 的张量。提出请求时是否必须指定图像的形状？

错误：

Data: {"signature_name": "serving_default", "instances": ... 58, 63], [35, 59, 63], [37, 58, 63], [43, 67, 71]]]}
{'error': 'Specified a list with shape [?,?,3] from a tensor with shape [339450,3]\n\t [[{{function_node __inference_call_func_9686}}{{node map/TensorArrayUnstack/TensorListFromTensor}}]]'}

发出请求的代码：

import requests
import json
from PIL import Image
import numpy

# Load image
img = Image.open("Hilarious-Car-License-Plates-1.jpg")
img_np = numpy.array(img.getdata())
img_np.resize(tuple([1] + list(img_np.shape)))
data = json.dumps({"signature_name": "serving_default", "instances": img_np.tolist()})
print('Data: {} ... {}'.format(data[:50], data[len(data)-52:]))

headers = {"content-type": "application/json"}
json_response = requests.post('http://localhost:8501/v1/models/plate_detect:predict', data=data, headers=headers)
response = json.loads(json_response.text)

print(response)

模型元数据：

{
"model_spec":{
 "name": "plate_detect",
 "signature_name": "",
 "version": "1"
}
,
"metadata": {"signature_def": {
 "signature_def": {
  "serving_default": {
   "inputs": {
    "input_tensor": {
     "dtype": "DT_UINT8",
     "tensor_shape": {
      "dim": [
       {
        "size": "1",
        "name": ""
       },
       {
        "size": "-1",
        "name": ""
       },
       {
        "size": "-1",
        "name": ""
       },
       {
        "size": "3",
        "name": ""
       }
      ],
      "unknown_rank": false
     },
     "name": "serving_default_input_tensor:0"
    }
   },
   "outputs": {
    "detection_boxes": {
     "dtype": "DT_FLOAT",
     "tensor_shape": {
      "dim": [
       {
        "size": "1",
        "name": ""
       },
       {
        "size": "100",
        "name": ""
       },
       {
        "size": "4",
        "name": ""
       }
      ],
      "unknown_rank": false
     },
     "name": "StatefulPartitionedCall:1"
    },
    "raw_detection_boxes": {
     "dtype": "DT_FLOAT",
     "tensor_shape": {
      "dim": [
       {
        "size": "1",
        "name": ""
       },
       {
        "size": "1917",
        "name": ""
       },
       {
        "size": "4",
        "name": ""
       }
      ],
      "unknown_rank": false
     },
     "name": "StatefulPartitionedCall:6"
    },
    "detection_scores": {
     "dtype": "DT_FLOAT",
     "tensor_shape": {
      "dim": [
       {
        "size": "1",
        "name": ""
       },
       {
        "size": "100",
        "name": ""
       }
      ],
      "unknown_rank": false
     },
     "name": "StatefulPartitionedCall:4"
    },
    "raw_detection_scores": {
     "dtype": "DT_FLOAT",
     "tensor_shape": {
      "dim": [
       {
        "size": "1",
        "name": ""
       },
       {
        "size": "1917",
        "name": ""
       },
       {
        "size": "2",
        "name": ""
       }
      ],
      "unknown_rank": false
     },
     "name": "StatefulPartitionedCall:7"
    },
    "detection_anchor_indices": {
     "dtype": "DT_FLOAT",
     "tensor_shape": {
      "dim": [
       {
        "size": "1",
        "name": ""
       },
       {
        "size": "100",
        "name": ""
       }
      ],
      "unknown_rank": false
     },
     "name": "StatefulPartitionedCall:0"
    },
    "detection_multiclass_scores": {
     "dtype": "DT_FLOAT",
     "tensor_shape": {
      "dim": [
       {
        "size": "1",
        "name": ""
       },
       {
        "size": "100",
        "name": ""
       },
       {
        "size": "2",
        "name": ""
       }
      ],
      "unknown_rank": false
     },
     "name": "StatefulPartitionedCall:3"
    },
    "detection_classes": {
     "dtype": "DT_FLOAT",
     "tensor_shape": {
      "dim": [
       {
        "size": "1",
        "name": ""
       },
       {
        "size": "100",
        "name": ""
       }
      ],
      "unknown_rank": false
     },
     "name": "StatefulPartitionedCall:2"
    },
    "num_detections": {
     "dtype": "DT_FLOAT",
     "tensor_shape": {
      "dim": [
       {
        "size": "1",
        "name": ""
       }
      ],
      "unknown_rank": false
     },
     "name": "StatefulPartitionedCall:5"
    }
   },
   "method_name": "tensorflow/serving/predict"
  },
  "__saved_model_init_op": {
   "inputs": {},
   "outputs": {
    "__saved_model_init_op": {
     "dtype": "DT_INVALID",
     "tensor_shape": {
      "dim": [],
      "unknown_rank": true
     },
     "name": "NoOp"
    }
   },
   "method_name": ""
  }
 }
}
}
}

【问题讨论】：

标签： tensorflow tensorflow2.0 object-detection tensorflow-serving object-detection-api

【解决方案1】：

我通过切换到https://tfhub.dev/tensorflow/ssd_mobilenet_v2/2 设法解决了这个问题

我这样保存了我的模型：

MODULE_HANDLE = 'https://tfhub.dev/tensorflow/ssd_mobilenet_v2/2'
ts = int(time.time())
detector = hub.load(MODULE_HANDLE)
file_path = "./models/object_detector/{}/".format(str(ts))
tf.saved_model.save(detector, file_path)

【讨论】：