56,198
questions
-1
votes
0
answers
19
views
Measuring Crack Width from Labeled Images Using MATLAB and Roboflow [closed]
I have a dataset of images containing cracks that I labeled using pixel labeling in MATLAB. I trained a model with these labeled images using Roboflow. Now, I want to measure the width of the cracks ...
-1
votes
0
answers
18
views
Input 0 of layer "edsr_model" is incompatible with the layer: expected shape=(None, None, None, 3), found shape=(1, 16, 24, 24, 3)
I'm trying to train edsr model to upscale images. I completed the model section training without any issues and tried to visualize the results. I got this error:
ValueError: Input 0 of layer "...
-6
votes
1
answer
23
views
Need technical flow for pattern machining [closed]
I want something that can tell me which actions should be done for certain IDs in my data. For instance, should we update or ignore an ID that is of the type "xyz"? This choice ought to be ...
-1
votes
0
answers
13
views
Scaling a super right skewed dependant
I'm working on a dataset for online articles and measuring popularity depending on the number of shares of the article. The Dependent variable (the shares) is super skewed to the right, as in the ...
-1
votes
0
answers
15
views
Kernel Density Estimation, Bandwidth selection via Cross validation
I am trying to use kernel density estimate to non-parametrically smooth an option implied density. The shape of the distribution is highly dependent on the bandwidth. For my research purposes I would ...
0
votes
0
answers
11
views
Object of type CustomScaler is not registered/supported with gurobi_ml
I have built a CustomScaler to scale my data in sklearn.pipeline.make_pipeline. It contained transform and inversetransform function. When I used gurobipy to optimise the regression model, I got the ...
0
votes
0
answers
25
views
Unable to return a boolean variable from Pytorch Dataset's __get_item__
I have a pytorch Dataset subclass and I create a pytorch DataLoader out of it. It works when I return two tensors from DataSet's __getitem__() method. I tried to create minimal (but not working, more ...
0
votes
0
answers
26
views
Problems loading a model saved in .h5 after upgrading Tensorflow from 2.15.0 to 2.17.0
I created an LSTM model with the tensorflow library version 2.15.0.
I now have to use the model created in a new project, but in this project I have to use all the updated libraries and also the last ...
-2
votes
0
answers
22
views
Should I ensemble or average SHAP values across partitioned models with imbalanced classes in XGBoost? [closed]
I have built a classification model using XGBoost, but my classes are highly imbalanced. I have around 2,000 instances of the positive class and 130,000 instances of the negative class. Instead of ...
-3
votes
0
answers
16
views
What are the reasons for the huge deviation of loss? [closed]
my loss
my loss function
These is my loss value, and I find it looked unstable.
I would like to ask, what are the reasons for the huge deviation of loss?
May be caused by the design of loss function? ...
0
votes
0
answers
19
views
Flask Server Not Accessible from Mobile Device: Image Classification Issue
I have a Flask server running on my local machine that is set up to classify images using a pre-trained TensorFlow model. The Flask server runs successfully on my computer and can process requests ...
0
votes
0
answers
21
views
Facing build Issue in the MLC-LLM Android App
I've tried to run the MLC-LLM Android App with the below link, I can't able to run the app due to the error which is shown in the screenshot below:
Git Repository
I've cloned and runned the MLC-AI/...
0
votes
0
answers
123
views
ImportError: DLL load failed while importing onnx_cpp2py_export: A dynamic link library (DLL) initialization routine failed
I'm trying to set up and test the OCR model from the doctr library provided by Mindee
(https://github.com/mindee/doctr)
within a VSCode. I installed the package in run.ipynb using the following ...
0
votes
0
answers
23
views
How to set a cmap = 'hsv' in tensorboard logger add_image?
I have one channel images and want to add them to the tensorboard logger by using writer.add_image, as follows:
generated_images_to_show = torch.cat(gtimage_cpu, predimage_cpu), dim=0)
...
-1
votes
1
answer
42
views
How to re-train ML model [closed]
I was playing around with AWS Sagemaker, trained a model with some labeled data, deployed it to endpoint and set up Lambda for serving predictions.
All good, but I want to re-train my model regularly, ...