For questions about machine learning modelling, architectures and design choices, as well as traditional models (AlexNet, VGGNet, Inception, ResNet, etc).
Questions tagged [machine-learning-model]
131 questions
2
votes
1 answer
How to de-normalize data with tidy-models in r
With tidymodels as the new workflow for developing models in R, how do I denormalize/Invert Power transformation data using tidymodels.
dd <- data.frame(x1=1:5,x2 = 11:15,y=6:10).
Now using the tidy model framework:
model_recipe <- recipe(y ~ .,…
Azam Yahya
- 646
- 1
- 7
- 10
2
votes
1 answer
How to predict values from many R model in Power BI
I have many models, like:
iris2 <- data.frame(zzz= sample(c(0, 1),size = length(iris$Sepal.Length), replace = TRUE), iris)
for (i in unique(iris$Species)) {
saveRDS(glm(zzz ~ Sepal.Length+Sepal.Width+Petal.Length+Petal.Width, data = …
Márcio Mocellin
- 274
- 5
- 18
2
votes
3 answers
How to save a trained model in Keras to use it in an application?
I have trained a model in Keras, and saved it in different ways like;
model.save("filename")
or
model.to_json()
model.save_weights("filename")
But when I load the trained model in another program to make predictions, I get very different…
Atilla
- 33
- 2
- 9
2
votes
1 answer
How to save and restore my sklearn model?
I am using pickle to store my machine learning model like this:
import pickle
with open('mymodel','wb') as f:
pickle.dump(gbc,f)
Now, in another computer i wanted to test this model. So i am restoring my model and passing data like…
Imran Ahmad Ghazali
- 605
- 1
- 10
- 16
2
votes
2 answers
Unable to save and restore a trained TensorFlow Model
I just read the Deep MNIST for Experts tutorial and modified the mnist_deep.py code to save the trained model using
saver = tf.train.Saver() before creating the session and
saver.save(sess, './mnist_deep_model', global_step=2000) after the for…
Bug Raptor
- 261
- 6
- 15
2
votes
1 answer
Is it possible to save a trained Spark ML model or crossvalidator to postgree database?
Is it possible to save a trained Spark ML model or crossvalidator to postgree database ? I could find ways to save it to disk or HDFS but can we save it in RDBMS(e.g. Postgree) table ?
Deva
- 85
- 5
2
votes
1 answer
Alternate methods to supply data for machine learning (Other than using CSV files)
I have a question which is relating to machine learning application in real world. It might be sounds stupid lol.
I've been self study machine learning for a while and most of the exercise was using the csv file as data source (both processed and…
不好笑
- 105
- 3
- 14
2
votes
2 answers
Error preparing CoreML model: "" is not supported for CoreML code generation
I am modifying the code from this tutorial and I'm getting this error:
Error preparing CoreML model "Resnet50.mlmodel" for code generation:
Target's predominant language "Swift Interface" is not supported for
CoreML code generation. Please set…
mm24
- 9,280
- 12
- 75
- 170
1
vote
2 answers
How can I save an Azure ML sklearn model to a specific blob storage container?
Saving an sklearn model to blob storage from AzureML
Simply put, I have a sklearn model in Azure ML. I want to write the model to a specific blob storage container to save it. I've already authenticated the connection to the right blob container.…
Mary
- 11
- 1
1
vote
1 answer
Predicting with model gives different predictions for same inputs and loading the model throws "doesnt save pytorch_model.bin cannot be opened" error
I am predicting my model like this:
def predict_label(text,username):
# input_ids = torch.tensor(tokenizer.encode(text)).unsqueeze(0)
model=getmodelfromusername(username)
input_ids=tokenizer(text, padding=True, truncation=True,…
tidekis doritos
- 47
- 6
1
vote
0 answers
Can TensorFlow Lite can detect material of object and object itself at a time in android studio?
Is there any way to simultaneously detect the material of any specific object and the object itself in android studio for android applications?
Twisha Kotecha
- 1,082
- 1
- 4
- 18
1
vote
1 answer
How to save the return of viz.visualize_image_attr as image Python
I need to use the return value of
viz.visualize_image_attr(fa_attr_without_max[0].cpu().detach().permute(1, 2, 0).numpy(), sign="all", title="Integrated Gradients")
as an image.
This method returns: 2-element tuple of *figure, **axis*; their data…
Arwa Esam
- 13
- 2
1
vote
1 answer
Can I use Reinforcment Learning for a problem that has a non continous observation space?
I want to train a agent to place a polyomino (only one for example a square of the measure of 2x2) on a 9x9 field, that is either empty or already contains multiple OTHER (not the 2x2 square one) polyominos. So the observation space would not be…
FlorianFusseder
- 43
- 5
1
vote
0 answers
Why autoencoder is not learning?
The loss function is MSE which is not decreasing (2.32 to 2.24). What is the problem AE architecture or the way I train the AE? After 100 epochs the loss doesn't change. Is the input data(200,1,52) can't be compressed? Should I increase the…
Harshit Gupta
- 63
- 5
1
vote
0 answers
How to use a custom PyTorch HoVer-Net model in the TIAToolBox for Nucleus Segmentation?
I want to use the TIAToolBox to segment nuclei in tissue images. The pretrained models don't fit my demands. Therfore I trained a custom HoVer-Net model on the PanNuke dataset to detect/count nuclei in tissue images.
The output I got is a .pt…
WilliWespe
- 65
- 1
- 9