1,716 questions
Tooling
0
votes
0
replies
37
views
Fast keypoint annotation tool
I’m currently working on annotating a human pose dataset (specifically of people swimming) and I’m struggling to find a tool that fits my workflow.
I’m looking for a click‑based labeling workflow, ...
Advice
0
votes
1
replies
55
views
SLEAP model training question and communicate
I am currently working on a project focused on automated computer vision-based behavior recognition for captive dolphins. I would like to ask about your experience using SLEAP for model training—...
- 1
Advice
0
votes
2
replies
80
views
How to train a text datasets?
Everyone!!
I'm a BSIT student and currently in a development of a capstone project which is a translation app which focuses on the 2 major languages in the Philippines which is Cebuano and Tagalog
I ...
2
votes
1
answer
94
views
skforecast insample predictions
Using skforecast, it's straightforward to perform out-of-sample predictions starting from the dates in the last_window_.index of a ForecasterRecursive object. However, I’m unable to find a clear ...
- 488
0
votes
1
answer
121
views
AttributeError: 'list' object has no attribute 'to' (samples are actually a Tensor) [closed]
EDIT:
I'm training a model using a custom dataloader. The outcome from the dataloader is a list of tensors which cannot be processed by the main model because I have defined the sampler as samples = ...
2
votes
1
answer
73
views
plot CART tree using a new dataset
I am a first-time CART user, and using the approach outlined in https://rpubs.com/camguild/803096 , I first split my data into two equally-sized training and test datasets. Next, I fit a CART on the ...
- 21
0
votes
0
answers
73
views
lstm-unicharset file is unable to be created during tesseract training
I am trying to fine-tune an Optical Character Recognition (OCR) model on Tesseract's provided tesstrain repository for Japanese . I tried encoding the bash commands into Python in VSCode as I wanted ...
- 11
0
votes
1
answer
351
views
Validation raises CUDA Out Of Memory Error despite training being fine
I am trying to train a model for spell check errors and corrections using T5-small model in colab notebook using T4 GPU. Initially I started with 10k reviews but gradually reduced it to 2k since I was ...
6
votes
3
answers
6k
views
How to fix the transformer installation issue?
I am trying to train a T5 model based on spellcheck by providing it with a sample csv file in google colab. Initially I ran the code with my personal device (python locally installed) and it executed ...
1
vote
0
answers
96
views
Error When Using Batch Size Greater Than 1 in PyTorch
I'm building a neural network to predict how an image will be partitioned during compression using VVC (Versatile Video Coding). The model takes a single Y-frame from a YUV420 image as input and uses ...
- 11
0
votes
1
answer
54
views
Train LSTM for time series with varying lengths
I'm training a LSTM for time series prediction, where data comes from sensors at irregular intervals. I'm using the last 5 min data to predict the next value, but some sequences are larger than others....
- 11
-1
votes
1
answer
69
views
Keyboard detection algorithm
I am working on an algorithm for detecting keys and keyboard body from an image. The model of the keyboard is known, so a blender env. has been created to generate images with random lighting, angle, ...
0
votes
0
answers
74
views
How can I get more images after augmenting each image?
I'm new to tensorflow. I want to generate more images after image augmentation but images and labels are (10, None, 400, 400, 3) and (10, None, 1) respectively and I guess it artifically count as 1 ...
- 9
1
vote
0
answers
47
views
Low Accuracy on MNLI Validation Set Using Hugging Face DistilBERT Model
I'm encountering low accuracy (7.90) when evaluating my Hugging Face DistilBERT model on the MNLI validation set. I suspect that I might not be training or preparing the model correctly. Could someone ...
- 11
2
votes
0
answers
70
views
kernel died when I run : dataset = Dataset.from_dict(data_dict)
I am fine-tuning sam model for my dataset containing train_images and train_masks. I am able to create dict, but when calling last command i.e. to load dataset from dict, kernel dies. It happened ...
- 21
0
votes
1
answer
122
views
R message: all the Accuracy metric values are missing when trying to make an ada model [duplicate]
I have a dataset about credit risk and have preprocessed my data, now I am trying to train and test on an ada boost model but it gives me the following error message: Something is wrong; all the ...
0
votes
1
answer
365
views
Yolo 11 nano dataset structured incorrectly
I'm new to working with Yolo and trying for the first time to structure my database. This is how my directory is structured.
Project_Name/
├── datasets/
│ ├── images/
│ │ ├── train/ ...
- 15
0
votes
1
answer
62
views
Tensorflow - Training error at the end of each epoch in progbar.py (keras)
After changing laptops, the training of my transformer (a simple translator) fails at the end of the first epoch.
The code is pretty long but I use model.fit() and overridden train_step().
h = ...
- 7,443
1
vote
0
answers
53
views
yolov5 trained my data set on my laptop how I send it to my Raspberry Pi
I got yolov5 and trained my data set on my laptop now I want to send it to my Raspberry Pi 4b module for work. how I do it
direct copy to raspberry pi but not working
(myenv) h@raspberrypi:~/project/...
0
votes
1
answer
47
views
How capture the error value for each epoch in MATLAB?
everyone!
I'm having a problem regarding my Deep Learning project, in the image regression task, and I would like to know how I could obtain the RMSE value at each epoch of my model's execution, and ...
0
votes
0
answers
103
views
Fixing the train-test resolution discrepancy in a YOLO model
I have trained a yolov8 model in order to detect handwritten digits on paper with MNIST dataset. The problem is that the images on the dataset are 416x416 and once the model is trained it gets really ...
1
vote
1
answer
120
views
How do I implement training a neural network when generating the data on spot?
I would like to construct a surrogate model of a physics simulation. Thus I am able to generate the data by myself. The data itself is very big, so it makes sense to generate a few data samples (e.g. ...
1
vote
0
answers
165
views
When I was trying to train the ConvNeXt, I met an issue
Traceback (most recent call last):
File "tools/train.py", line 162, in <module>
main()
File "tools/train.py", line 158, in main
runner.train()
File "C:\...
-1
votes
1
answer
58
views
Machine learning-does repeatedly training on data cause overfit?
So I have a machine learning model that has been trained and there is no overfit or underfit, this model is perfect and can detect objects correctly. However, after that I try what if I train this ...
1
vote
1
answer
160
views
YoloV8 model doesn't detect old dataset after retraining with new dataset
I'm trying to re-train a model which has been created with a sequence of a film.
After that, I want to re-train it with another sequence with the same labels, to see if it detects both sequences. But ...
0
votes
1
answer
345
views
Why is the YOLOv8 model not detecting objects in the training data but detecting them in the validation data instead?
Every time I tried to train a model it takes the images from the validation folder. Actually I have 299 images in training folder and 85 images in validation folder but during the training I found ...
0
votes
0
answers
65
views
(Beginner)My AI(U-net) isnt training/testing properly
I'm new to AI and Python, so I've been trying to use U-net to create an AI that can identify and segment cracks. My results are like this:
Epoch 5/25
20/20 [==============================] - 42s 2s/...
1
vote
1
answer
348
views
train yolov8 on colab runtimeerror
/usr/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a ...
0
votes
1
answer
28
views
When should I do characteristic selection?
I am running some Machine Learning algorithms in order to train a model.
Until now I've been doing a correlation matrix in order to select the characteristics with highest correlaction to my target ...
- 37
1
vote
0
answers
72
views
why was the discriminator in the GAN model set as nontrainable?
So I am training a CycleGAN for a face aging task, I am following digital sreeni cycle gan tutorial, he set the generator as trainable, and the corresponding discriminator and other generator are set ...
- 11
0
votes
0
answers
34
views
Data is ambiguous. Make sure all arrays contain the same number of samples
I'm attempting to train a model to predict privacy based on labels in JSON files. However, after training the model, I encountered this error: "ValueError: Data cardinality is ambiguous. Make ...
1
vote
0
answers
146
views
yolov5 running custom model, do I have a training problem?
I have this dataset from Roboflow and I want to train it and run it locally. I have trained it and all looks good but when I run the py script in terminal it gives me like errors.
It works when I
...
- 11
0
votes
0
answers
111
views
Efficient Pair Sampling with Pytorch
I have a dataset of around 150k images and 150k audios. Each image, has a corresponding audio. I want my network to learn to map one audio onto another using the image data.
When I create these source ...
0
votes
1
answer
24
views
higher coefficient of determination values in the testing phase compared to the training phase
I developed seven different hybrid ML models using metaheuristic algorithms and ANN. Interestingly, the coefficient of determination values for most of these models are higher in the testing phase ...
- 121
1
vote
0
answers
325
views
Loading the pre-trained model from the .h5 file (Works on Colab but does not work on Local)
Hello I'm struggling with loading pre-trained model for a while and cant solve this issue yet.
On Colab:
from google.colab import drive
drive.mount('/content/drive')
from keras.models import ...
- 11
1
vote
0
answers
260
views
How to finetune the LLM to output the text with SSML tags?
I need to train a model to add the SSML tags and punctuation to the input text.
For example, from the sentence "Hello world." I'd like to get the
<speak> Hello! world. </speak> ...
- 11
0
votes
1
answer
70
views
How many images should I label from the training set?
We have 10,000 images and we want to implement a deep-learning model to extract the vegetation. What's the minimum number of images we should label if we want an 80% training set?
We want to use ...
0
votes
1
answer
432
views
Should I use training or validation set for parameter otimization?
I am training a model using Decision Tree and parameter otimization.
I read that the objective of the validation set is to assess model performance during training and help tune parameters.
With this ...
- 37
0
votes
1
answer
72
views
Generate TRAIN_DATA for spacy from xml
I have xml data, which looks like this:
<item n="main"><anchor type="b" ana="regO.lemID_12" xml:id="TidB13" />Stuttgart<anchor type="e" ...
- 1
1
vote
0
answers
139
views
Does scikit-learn train_test_split copy data?
Does the train_test_split method of scikit-learn duplicate the data? In other words, if I work with a large dataset, X, y, does it mean that after performing something like
X_train, X_test, y_train, ...
- 803
0
votes
1
answer
660
views
YOLOv8 custom model not making predictions
I use a custom trained Yolov8 model to predict whether a physical door is closed or open. I have trained Yolov8 on a custom dataset but it does not make any detections even when passing the same data ...
-2
votes
3
answers
1k
views
ValueError: Expected input data to be non-empty
This is my code:
x_test = []
y_test = dataset[training_data_len:, :]
for i in range (60,len(test_data)):
x_test.append(test_data[i - 60 :i, 0])
x_test = np.array(x_test)
x_test = np.reshape(...
- 1
1
vote
0
answers
440
views
tesseract combine_tessdata eng. Combining tessdata files Error: traineddata file must contain at least (a unicharset file
i am trying to train tesseract for that i am following this How to Create Traineddata file For Tesseract 4.1.0
step 1
tesseract eng.ocrb.exp0.jpeg eng.ocrb.exp0 batch.nochop makebox
step 2
tesseract ...
- 3,575
1
vote
0
answers
52
views
Tensorflow - self.metrics does not contain compiled metrics in train_step()
In the code below, I overridded train_step(), but self.metrics does not contain compiled metrics.
As a result the verbose of fit() does not show the compiled metrics and the history does not contains ...
- 7,443
1
vote
1
answer
601
views
M2 Mac YOLOv8 Training: RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half'
I want to train a Yolov8 model on a custom dataset with my Mac and this is my first time working on deep learning. Unfortunately, I experienced an error,
RuntimeError: "...
- 11
1
vote
1
answer
405
views
How do I calculate the accuracy of my Vision Transformer?
I'm new to PyTorch, and want to find the accuracy of each epoch. I know that accuracy is # of correct predictions / the total samples, but I don't know how to integrate this into my code.:
for epoch ...
- 11
0
votes
0
answers
71
views
Problem with keras.Dense. The last dimension of the inputs to a Dense layer should be defined. Found None. Full input shape received: (None, None)
I wrote some python code to develop a siamese network. The sub-clase from keras.Model is:
class modelSIAMESE(keras.Model):
def init(self):
super().init()
input_shape = target_shape + (3,)
input_a = ...
2
votes
0
answers
501
views
GUI for making Tesseract-OCR 5 training files from existing images of text?
I have some (19th century printed) text that has non-standard domain-specific symbols in it that Tesseract currently does not detect as letters. I want some software that will:
break the text into ...
- 23
0
votes
2
answers
1k
views
GPU out of memory immediately after starting to train Llama-2 using Huggingface
I am getting the following error when running a training script for a multi-label classification task on the Llama-2 7B model using the Huggingface Trainer. My training data contains a binary list of ...
- 1
-1
votes
1
answer
438
views
How to create our own image dataset for cnn
I have two different folders containing my images and random images how to spilit it to train and test in a cnn model
I tried to spilt it as training data and testing data but i dont know how to do ...
