Unanswered Questions tagged with Amazon SageMaker
Content language: English
Select up to 5 tags to filter
Sort by most recent
Browse through the questions and answers listed below or filter and sort to narrow down your results.
Hi, everyone!
After training the model with autopilot, metrics and best model performance are not shown so I can evaluate it. I had no problem with this in previous trainings. I receive the following...
0
answers
1
votes
82
views
asked a year agolg...
I'd like to host models which need to use BLS on GPU-backed realtime inference with MME. I'd like to be able to scale to hundreds or thousands of such models behind one endpoint. Will this work out of...
0
answers
0
votes
104
views
asked a year agolg...
Simply using the Home/Launcher button called "Open Launcher" or the Launcher "Create notebook" button throws an error trying the open the jupyte![Enter image description...
0
answers
0
votes
79
views
asked a year agolg...
I'm trying to launch an inference endpoint on an ml.g4dn.2xlarge with a ~44GB model image. Every time I try to create the endpoint, it is in the creating state for 30-40 minutes and then fails with an...
0
answers
0
votes
137
views
asked a year agolg...
I have an ML model from Huggingface, which essentially looks as follows:
```
import torch
from transformers import BloomTokenizerFast, BloomForCausalLM
device = torch.device('cuda' if...
0
answers
0
votes
97
views
asked a year agolg...
I used the training script from [https://sagemaker.readthedocs.io/en/stable/frameworks/xgboost/using_xgboost.html](here),and trying to train the model. And the here is the code I used for configuring...
0
answers
0
votes
220
views
asked a year agolg...
Hi
I have some confusion to use in between Sagemaker Studio and Dataiku in terms of scalability and pricing. I didn't get any source from where I can get satisfactory answers regarding this.
Please...
0
answers
0
votes
80
views
asked a year agolg...
I have a PyTorch model that I've saved following [https://docs.aws.amazon.com/sagemaker/latest/dg/neo-compilation-preparing-model.html]() into a .tar.gz file
I uploaded it to S3, and then tried to...
0
answers
0
votes
88
views
asked a year agolg...
I have millions of logs in CloudWatch of the following type:
"POST /invocations HTTP/1.1" 200 5 "-" "AHC/2.0"
I am assuming these logs are generated when InvokeEndpoint is called for a...
0
answers
0
votes
61
views
asked a year agolg...
Im using sagemaker for train the data
It has pre-trained model
“tensorflow-od1-ssd-resnet50-v1-fpn-640x640-coco17-tpu-8”
**Create the SageMaker model instance. Note that we need to pass Predictor...
0
answers
0
votes
143
views
asked a year agolg...
I have set up few steps in sagemaker pipeline , to process and train data. but in the event where i need a custom script for inference , i want to able to just run the model re-packaging step. is it...
0
answers
0
votes
108
views
asked a year agolg...
I have a YOLOv5-trained model. Exported as Tensorflow, I'm trying to compile and deploy to my device as a Greengrass Noe edge component.
Device configs are,
device: NVIDIA Jetson AGX...
0
answers
0
votes
92
views
asked a year agolg...