Introducing the Keras Sequential API on Vertex AI Platform Reviews

Andrea C. · Reviewed 5 months ago

Damir M. · Reviewed 5 months ago

Kazushige O. · Reviewed 5 months ago

David Israel P. · Reviewed 5 months ago

Scott B. · Reviewed 5 months ago

Oscar R. · Reviewed 5 months ago

Benhur O. · Reviewed 5 months ago

Shankar M. · Reviewed 5 months ago

Amina Z. · Reviewed 5 months ago

Abhra D. · Reviewed 5 months ago

Abhilasa S. · Reviewed 5 months ago

Nils G. · Reviewed 5 months ago

File /opt/conda/lib/python3.10/site-packages/google/cloud/aiplatform/models.py:1827, in Endpoint._deploy_call(cls, api_client, endpoint_resource_name, model, endpoint_resource_traffic_split, network, deployed_model_display_name, traffic_percentage, traffic_split, machine_type, min_replica_count, max_replica_count, accelerator_type, accelerator_count, tpu_topology, service_account, explanation_spec, metadata, deploy_request_timeout, autoscaling_target_cpu_utilization, autoscaling_target_accelerator_duty_cycle, enable_access_logging, disable_container_logging, deployment_resource_pool) 1815 operation_future = api_client.deploy_model( 1816 endpoint=endpoint_resource_name, 1817 deployed_model=deployed_model, (...) 1820 timeout=deploy_request_timeout, 1821 ) 1823 _LOGGER.log_action_started_against_resource_with_lro( 1824 "Deploy", "model", cls, operation_future 1825 ) -> 1827 operation_future.result(timeout=None) File /opt/conda/lib/python3.10/site-packages/google/api_core/future/polling.py:261, in PollingFuture.result(self, timeout, retry, polling) 256 self._blocking_poll(timeout=timeout, retry=retry, polling=polling) 258 if self._exception is not None: 259 # pylint: disable=raising-bad-type 260 # Pylint doesn't recognize that this is valid in this case. --> 261 raise self._exception 263 return self._result FailedPrecondition: 400 Model server exited unexpectedly. Model server logs can be found at https://console.cloud.google.com/logs/viewer?project=667152570772&resource=aiplatform.googleapis.com%2FEndpoint&advancedFilter=resource.type%3D%22aiplatform.googleapis.com%2FEndpoint%22%0Aresource.labels.endpoint_id%3D%225927820128572932096%22%0Aresource.labels.location%3D%22us-central1%22.

Goziem M. · Reviewed 5 months ago

could be easier if there was more time since deploy part takes long

Mona H. · Reviewed 5 months ago

Islam A. · Reviewed 5 months ago

MACHINE_TYPE = "e2-standard-2" endpoint = uploaded_model.deploy( machine_type=MACHINE_TYPE, accelerator_type=None, accelerator_count=None, ) ne marche pas correctement

Timothé L. · Reviewed 5 months ago

Llorenç V. · Reviewed 5 months ago

Wonseuk H. · Reviewed 5 months ago

Pablo G. · Reviewed 5 months ago

Deploy really slow

Francesca A. · Reviewed 5 months ago

Anísio P. · Reviewed 5 months ago

Kamel S. · Reviewed 5 months ago

Cesare C. · Reviewed 5 months ago

Goziem M. · Reviewed 5 months ago

Rajesh A. · Reviewed 5 months ago