All Questions
66 questions
0
votes
0
answers
52
views
Stable torch, ultralytics, tensorflow packages for requirements.txt
I'm writing a requirements.txt for a real-time sports video analysis project and testing various libraries such as YOLOv8, Torch, TensorFlow, etc.
I've tried multiple Python versions but encountered ...
- 59
1
vote
1
answer
63
views
Get directional elements in matrix
Lets suppose that I have a point of interest in my matrix that is NxN. The point is located in the position ij. So, given the index ij, is there a simple way to get the line elements passing trough ij ...
- 13
0
votes
0
answers
32
views
PyTorch huge dataset constraints?
I'm training a model in Pytorch to do image-to-image processing. My data is huge, shape is (64152, 3, 5, 2, 64, 144). I'm using memmapping to save on memory as much as humanly possible.
The issues ...
0
votes
1
answer
484
views
segment_anything causing error with numpy.uint8
I am trying to run https://github.com/facebookresearch/segment-anything/blob/main/notebooks/onnx_model_example.ipynb locally, on an M2 MacBook with Sonoma 14.5. However, I keep running into the ...
- 3,191
0
votes
1
answer
99
views
Center an image and adding a background at export
I want to automate all of this:
Select an object in an image
Crop my image on this object
Crop to 1:1 aspect ratio, leaving a slight gap around this object
Export my image in JPG format in 800x800px ...
- 1
0
votes
0
answers
232
views
TypeError: new(): invalid data type 'str' when creating PyTorch Geometric Data object
labeled_X and unlabeled_X are node features (that is gene/protein expressions) matrices for the annotated reference dataset and target unannotated dataset, respectively. They should be numpy arrays ...
- 1,545
0
votes
0
answers
85
views
Pytorch in GPU is much slower than numpy on CPU？
I've run across the problem that in an MNIST training pytorch GPU method is much slower than merely applying numpy on CPU.
the MNIST data is in the form of csv.
torch method
import os
import time
...
- 1
-2
votes
1
answer
85
views
How to create a tensor based on another one - Studying PyTorch in practice?
I'm studying IA using PyTorch and implementing some toy examples.
First, I created a one-dimensional tensor (X) and a second tensor (y), derived from the first one:
X = torch.arange(0, 100, 1.0)....
0
votes
1
answer
40
views
Problem in defining a ML model for my Npy dataset
I need help in defining a torch model for my data. I have tried various methods but nothing seems to be working out. Error after error related to input size and shaping. How can I resolve these issues?...
0
votes
3
answers
425
views
Simple RNN with more than one layer in Pytorch for squential prediction
I got sequential time series data. At each time stamp, there is only variable to observe (if my understanding is correct this means number of features = 1). I want to train a simple RNN with more than ...
- 1,596
1
vote
1
answer
1k
views
Trying to train model, but got AttributeError: 'list' object has no attribute 'to' with DataLoader PyTorch
I'm trying to train model, but getting AttributeError. I'm first time with PyTorch, so I don't know its problem with pre-processing or with DataLoader etc., so need to discover where's problem
Data ...
- 63
-1
votes
1
answer
43
views
MNIST number guesser stuck at 9.84% accuracy
I built a MNIST dataset through watching yt tutorials. Every tutorial was using numpy but since pytorch is a newer technology I decided to build mine using pytorch. The problem is that my model is ...
- 1
0
votes
1
answer
447
views
Training a BARTForSequenceClassification returns data with ununiform dimentsions
I am trying to fine-tune a BART-base model on a dataset that I have. The dataset looks like this: It has columns "id", "text", "label" and "dataset_id". The &...
- 122
1
vote
2
answers
96
views
numpy assert_equals for nested floating point
I got a strange behaviour regarding an equal check for the weights for the vgg16 machine learning model
loading two times the model
import torch
from torch import nn
from torchvision.models import ...
- 4,647
0
votes
1
answer
548
views
Why are my model weights different each time I check?
I finetuned the PyTorch vgg16 pretrained model with CIFAR-10 data.
Now, I load this model via load_state_dict() and check the model weights using model.parameters(). I noticed, that some of the ...
- 25