Questions tagged [machine-learning]
Implementation questions about machine learning algorithms. General questions about machine learning (concepts, theory, methodology, terminology, etc.) should be posted to their specific communities.
machine-learning
56,062
questions
-3
votes
0
answers
13
views
any one can please tell why we use Correct parameter grid for fine tune a prediction accuracy
parameters = {
'n_estimators': [100, 200],
'learning_rate': [0.01, 0.1],
'max_depth': [3, 5],
'subsample': [0.8, 1.0],
'colsample_bytree': [0.8, 1.0],
'gamma': [0, 0.1],
'...
-2
votes
0
answers
15
views
Machine Learning (Logistic Regression) using an array as a feature/independent variable? [closed]
Sorry if this is more of a general/beginner question but I'm not finding any luck searching for an answer online - maybe I am googling the wrong things.
So essentially let's say I have a dataframe of:
...
0
votes
0
answers
14
views
CrossEntropyLoss on PyTorch LSTM model with one classification per timestep
I am trying to make an LSTM model that will detect anomalies in timeseries data. It takes 5 inputs and produces 1 boolean output (True/False if anomaly is detected). The anomaly pattern will usually ...
-3
votes
0
answers
30
views
Is artificial intelligence the way to go? [closed]
How is everyone? I'm a film industry professional and as everyone probably knows, it sucks to be in this industry at the moment. There's one thing I'm fascinated by and that's AI. I don't believe it's ...
0
votes
0
answers
13
views
Cannot run facenet or machine learning in react native
This my code for AttendanceScreen, when I run it I get the error error detecting face: [typeerror: network request failed] error error confirming photo: [typeerror: network request failed]
import ...
0
votes
0
answers
7
views
Variable size input for CNN
I would like to create an AI that could guess the next image in a sequence of images and I have the idea to feed a CNN with 1,2,3,...,n-1 images as input running it through an LSTM and the output is ...
-1
votes
0
answers
7
views
Dependency management and execution environment in apache flink
we are evaluating apache flink for deploying streaming ml applications.
How is dependency management handled in apache flink and especially the execution environment?
Imagine python tasks with ...
-2
votes
0
answers
16
views
Trying to implement the MiDas model for Monocular Depth estimation in tensorflow and values for distance are off the charts [closed]
Downloaded Tflite MiDas model from Kaggle.
Looked at a few articles for MiDas and Monocular Depth Estimation(Basically finding the distance of an object from the camera using pixels)
This is for ...
0
votes
0
answers
13
views
Error in Boosted Regression Tree model with offset
I'm working with boosted regression tree models (BRTs) to predict the probability of occurence of a dolphin species. For that I have presence/absence data and several environmental variables. The ...
-2
votes
0
answers
15
views
keras BackupAndRestore resuming a model but shows lower accuracy and higher loss
I am using google colab gpu and i need to save model as many as i can and then restart training model in a new google colab below is my code but fave lower accuracy and higher loss for example in ...
-1
votes
0
answers
18
views
How to train Yolo 3D for NYU dataset
I have had trained my Yolo 3D model in KITTI dataset and now I would like to train it on NYU dataset. What changes must I do in the NYU dataset in order to train it in YOLO 3D model?
I would like to ...
-3
votes
0
answers
26
views
How to make predictions from trained keras model without keras
I have a 1D CNN that I created and trained with keras, and I've saved the weights in an h5 file and the architecture in a JSON file. I'd now like to be able to read the architecture and weights and ...
-2
votes
1
answer
22
views
Which are the most efficient models for shape detection in an image? [closed]
I want to create a Python algorithm that detects objects appearing and disappearing between 2 photos. Thos photos are not taken exactly from the same spot. My idea is to use a pretrained model that ...
0
votes
1
answer
20
views
Joint Angles of PyBullet's Walker2D
I am using the Walker2D environment from pybullet_envs and I am trying to get the 6 joint angles in order to use them for an actual bipedal robot controlled by an Arduino.
I tried but didn't manage to ...
-1
votes
0
answers
14
views
How can I find the corners of a cube with known dimensions in an RGB image?
How can I find the corners of a cube with known dimensions (30cm each side) in an RGB image real time? The cube will be monochrome (one color) but the color information is not known.
I searched 2d ...