-
Support image segmentation in labelling tasks and Visual ML
I have a couple of use cases where I need to train image (instance) segmentation models (as opposed to predicting bounding boxes in object detection). I'd love for the ML labelling to support image segmentation approaches. For example using SAM (Segment Anything Model) to pre-segment images which can then be annotated by…
-
How do i create a categorisation model for a reviews dataset
Hi there - new to dataiku, Lets say i have an excel sheet of 2 columns where one has app reviews and the other has dates they were posted. Is there a video tutorial anywhere or example where i can create a model to categorise the app reviews into categories eg) ux/ui problem or customer service problem as well as include…
-
How to save a keras model from a python recipe in a folder ?
I would like to save a keras model in a folder. I can not figure out how to save the weights of my models because I do not find the correct filepath. The needed code to achieve this goal is : model.save_weights(filepath) Even with this syntax : path = str(trained_LSTM_info['accessInfo']['root'])…
-
Torch backend for visual deep learning
Hi, As of now, "visual deep learning" interface implies that the model must use keras, and is forced to a tensorflow backend. Keras can use other backends, such as torch (About Keras 3) ; following this article I ran into various issues, leading me to believe that it is not supported by dataiku at the time of writing. Is…
-
Are there different ways to set up code environments?
I am trying to install pytorch in python3 in a code environment in data science studio. I can install it in the python3.5 install on the system that Data Science Studio is installed on. I've tried putting torch in the REQUESTED PACKAGES (PIP) part of the code environment administration but that doesn't work because pytorch…
-
TensorFlow slices method using containerized execution
Hi Experts, I am using the tensorflow slices to batch process my images for CNN model. The snapshot of the code is as follows and it runs very well in a Jupyter notebook in dataiku using local execution. When I run the same code in dataiku containerized execution it gives the following errors, I have seen documentation on…
-
torch.cuda.is_available() is False
I am trying to load a pickle file of a pre-trained model to my code recipe but get the following error message: I have already selected the "ai-exec-t4-gpu" in the "Containerized Execution" tab of the environment. I do not understand exactly what could be going wrong here. Appreciate your help!
-
Turn a custom model in the flow into a model object
I was told that it was possible to turn a custom trained model, typically stored in a managed folder, into a visual model object in the flow. Currently our flow looks like this: but we would like to see something like this in the flow: I couldn’t find any documentation on how to do this, so I’m turning to the Dataiku…
-
time series forecasting using prophet model get error during run time
######## python and prophet version details prophet version=1.1.4 python_version=3.9.12 I am using the same version in my local machine its working file. but i am facing error on DATAIKU ########### Code Sample ######## lag_periods = [1,5, 10, 15] for lag in lag_periods: df_prophet[f'Lag_{lag}'] =…
-
Custom Object Detection model with MLFlow tracking
I am trying to get the Yolov8 object detection model as a MLFlow python function to then automatically score and evaluate from the saved model. When I am setting mlflow_extension.set_run_inference_info and project.create_mlflow_pyfunc_model to "OTHER" prediction type, I cant use the mlflow_version.evaluate method on the…