init

2024-01-17 15:18:16 +08:00
commit 1bd4060e68
1514 changed files with 193581 additions and 0 deletions
@@ -0,0 +1,107 @@
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import json
+import numpy as np
+import time
+
+import fastdeploy as fd
+
+# triton_python_backend_utils is available in every Triton Python model. You
+# need to use this module to create inference requests and responses. It also
+# contains some utility functions for extracting information from model_config
+# and converting Triton input/output types to numpy types.
+import triton_python_backend_utils as pb_utils
+
+
+class TritonPythonModel:
+    """Your Python model must use the same class name. Every Python model
+    that is created must have "TritonPythonModel" as the class name.
+    """
+
+    def initialize(self, args):
+        """`initialize` is called only once when the model is being loaded.
+        Implementing `initialize` function is optional. This function allows
+        the model to intialize any state associated with this model.
+        Parameters
+        ----------
+        args : dict
+          Both keys and values are strings. The dictionary keys and values are:
+          * model_config: A JSON string containing the model configuration
+          * model_instance_kind: A string containing model instance kind
+          * model_instance_device_id: A string containing model instance device ID
+          * model_repository: Model repository path
+          * model_version: Model version
+          * model_name: Model name
+        """
+        # You must parse model_config. JSON string is not parsed here
+        self.model_config = json.loads(args['model_config'])
+        print("model_config:", self.model_config)
+
+        self.input_names = []
+        for input_config in self.model_config["input"]:
+            self.input_names.append(input_config["name"])
+        print("preprocess input names:", self.input_names)
+
+        self.output_names = []
+        self.output_dtype = []
+        for output_config in self.model_config["output"]:
+            self.output_names.append(output_config["name"])
+            dtype = pb_utils.triton_string_to_numpy(output_config["data_type"])
+            self.output_dtype.append(dtype)
+        print("preprocess output names:", self.output_names)
+        self.preprocessor = fd.vision.ocr.DBDetectorPreprocessor()
+
+    def execute(self, requests):
+        """`execute` must be implemented in every Python model. `execute`
+        function receives a list of pb_utils.InferenceRequest as the only
+        argument. This function is called when an inference is requested
+        for this model. Depending on the batching configuration (e.g. Dynamic
+        Batching) used, `requests` may contain multiple requests. Every
+        Python model, must create one pb_utils.InferenceResponse for every
+        pb_utils.InferenceRequest in `requests`. If there is an error, you can
+        set the error argument when creating a pb_utils.InferenceResponse.
+        Parameters
+        ----------
+        requests : list
+          A list of pb_utils.InferenceRequest
+        Returns
+        -------
+        list
+          A list of pb_utils.InferenceResponse. The length of this list must
+          be the same as `requests`
+        """
+        responses = []
+        for request in requests:
+            data = pb_utils.get_input_tensor_by_name(request,
+                                                     self.input_names[0])
+            data = data.as_numpy()
+            outputs, im_infos = self.preprocessor.run(data)
+            dlpack_tensor = outputs[0].to_dlpack()
+            output_tensor_0 = pb_utils.Tensor.from_dlpack(self.output_names[0],
+                                                          dlpack_tensor)
+            output_tensor_1 = pb_utils.Tensor(
+                self.output_names[1], np.array(
+                    im_infos, dtype=np.int32))
+            inference_response = pb_utils.InferenceResponse(
+                output_tensors=[output_tensor_0, output_tensor_1])
+            responses.append(inference_response)
+        return responses
+
+    def finalize(self):
+        """`finalize` is called only once when the model is being unloaded.
+        Implementing `finalize` function is optional. This function allows
+        the model to perform any necessary clean ups before exit.
+        """
+        print('Cleaning up...')
@@ -0,0 +1,37 @@
+# optional, If name is specified it must match the name of the model repository directory containing the model.
+name: "det_preprocess"
+backend: "python"
+max_batch_size: 1
+
+# Input configuration of the model
+input [
+  {
+    # input name
+    name: "INPUT_0"
+    # input type such as TYPE_FP32、TYPE_UINT8、TYPE_INT8、TYPE_INT16、TYPE_INT32、TYPE_INT64、TYPE_FP16、TYPE_STRING
+    data_type: TYPE_UINT8
+    # input shape， The batch dimension is omitted and the actual shape is [batch, c, h, w]
+    dims: [ -1, -1, 3 ]
+  }
+]
+
+# The output of the model is configured in the same format as the input
+output [
+  {
+    name: "OUTPUT_0"
+    data_type: TYPE_FP32
+    dims: [ 3, -1, -1 ]
+  },
+  {
+    name: "OUTPUT_1"
+    data_type: TYPE_INT32
+    dims: [ 4 ]
+  }
+]
+
+instance_group [
+  {
+      count: 1
+      kind: KIND_CPU
+  }
+]