Google cloud platform '；gcloud beta ai平台解释'；LSTM模型三维输入阵列的误差分析

我有一个成功训练的3d输入keras模型，以下是模型摘要：

Model: "model"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 5, 1815)]         0         
_________________________________________________________________
bidirectional (Bidirectional (None, 5, 64)             473088    
_________________________________________________________________
bidirectional_1 (Bidirection (None, 5, 64)             24832     
_________________________________________________________________
output (TimeDistributed)     (None, 5, 25)             1625      
=================================================================
Total params: 499,545
Trainable params: 499,545
Non-trainable params: 0
_________________________________________________________________

定义估计器并创建服务后，如下所示：

# Convert our Keras model to an estimator
keras_estimator = tf.keras.estimator.model_to_estimator(keras_model=model, model_dir='export')

# We need this serving input function to export our model in the next cell
serving_fn = tf.estimator.export.build_raw_serving_input_receiver_fn(
    {'input_1': model.input}
)

#export the model to bucket
export_path = keras_estimator.export_saved_model(
  'gs://' + BUCKET_NAME + '/explanations',
  serving_input_receiver_fn=serving_fn
).decode('utf-8')
print(export_path)

解释元数据定义定义并复制到所需目标，如下所示：

explanation_metadata = {
    "inputs": {
      "data": {
        "input_tensor_name": "input_1:0",
        "input_baselines": [np.mean(data_X, axis=0).tolist()],
        "encoding": "bag_of_features", 
        "index_feature_mapping": feature_X.tolist()
      }
    },
    "outputs": {
      "duration": {
        "output_tensor_name": "output/Reshape_1:0"
      }
    },
  "framework": "tensorflow"
  }

# Write the json to a local file
with open('explanation_metadata.json', 'w') as output_file:
  json.dump(explanation_metadata, output_file)
!gsutil cp explanation_metadata.json $export_path

发布模型已创建且版本定义为：

# Create the model if it doesn't exist yet (you only need to run this once)
!gcloud ai-platform models create $MODEL --enable-logging --regions=us-central1

# Create the version with gcloud
explain_method = 'integrated-gradients'
!gcloud beta ai-platform versions create $VERSION \
--model $MODEL \
--origin $export_path \
--runtime-version 1.15 \
--framework TENSORFLOW \
--python-version 3.7 \
--machine-type n1-standard-4 \
--explanation-method $explain_method \
--num-integral-steps 25

在此步骤之前，一切正常，但现在当我创建并发送解释请求时：

prediction_json = {'input_1': data_X[:5].tolist()}
with open('diag-data.json', 'w') as outfile:
  json.dump(prediction_json, outfile)

#Send the request to google cloud
!gcloud beta ai-platform explain --model $MODEL --json-instances='diag-data.json'

我得到以下错误：

{
  "error": "Explainability failed with exception: <_InactiveRpcError of RPC that terminated with:\n\tstatus = StatusCode.INVALID_ARGUMENT\n\tdetails = \"transpose expects a vector of size 4. But input(1) is a vector of size 3\n\t [[{{node bidirectional/forward_lstm_1/transpose}}]]\"\n\tdebug_error_string = \"{\"created\":\"@1586068796.692241013\",\"description\":\"Error received from peer ipv4:10.7.252.78:8500\",\"file\":\"src/core/lib/surface/call.cc\",\"file_line\":1056,\"grpc_message\":\"transpose expects a vector of size 4. But input(1) is a vector of size 3\\n\\t [[{{node bidirectional/forward_lstm_1/transpose}}]]\",\"grpc_status\":3}\"\n>"
}

我现在的

已经走到了死胡同！gcloud beta ai platform explain--model$model--json instances='diag-data.json'

，并从SO社区寻求急需的帮助

---

此外，为了便于实验，笔记本可以从

中访问。从predict的工作描述中，您是否尝试对explain进行同样的操作？从您的帖子中不清楚您是否：

prediction_json = {'input_1': data_X[:5].reshape(-1,1815).tolist()}
with open('diag-data.json', 'w') as outfile:
  json.dump(prediction_json, outfile)

#send the predict request
!gcloud beta ai-platform explain --model $MODEL --json-instances='diag-data.json'

prediction_json = {'input_1': data_X[:5].reshape(-1,1815).tolist()}
with open('diag-data.json', 'w') as outfile:
  json.dump(prediction_json, outfile)

#send the predict request
!gcloud beta ai-platform explain --model $MODEL --json-instances='diag-data.json'