Questions tagged [pytorch]
PyTorch is a deep learning framework that implements a dynamic computational graph, which allows you to change the way your neural network behaves on the fly and capable of performing backward automatic differentiation.
29 questions
3
votes
1
answer
76
views
Managing a global backend/device state when making a deep learning framework
I have been making a deep learning framework modelled after Pytorch in pure Python. I have made good progress but my framework is currently not seamless to use because the end user of the framework ...
- 303
4
votes
2
answers
201
views
Class for validating code in different Conda environments with PyTorch
I wrote the Validator class. In the project, the presented code is located at the path ".../validator/init.py". It is needed for testing code in different virtual Conda environments, in the ...
- 143
3
votes
1
answer
103
views
Follow up - Deep Learning Project for House Plant Identification on Kaggle Notebook
The code is based on feedback that I received from my previous question regarding this project.
I've developed the initial code for a deep learning project focused on identifying house plants within a ...
- 459
4
votes
2
answers
104
views
Kaggle Notebook for Identifying House Plants
I'm working on a personal deep learning project on identifying house plants. I have developed the initial code in Kaggle Notebook. I'll later transform it into a Flask app.
I have just finished the ...
- 459
2
votes
1
answer
85
views
I have a pytorch module that takes in some parameters and predicts the difference between one of it inputs and the target
One instance of the following module uses up to almost 75% of my vram. So, I was wondering how I could improve that without slowing down runtime too much. The code is below:
...
3
votes
2
answers
116
views
Video Frame-by-Frame Deraining with MFDNet
After checking the repository of MFDNet, single image rain streaks removal with the provided model is given in test.py. I am trying to modify the code to process frame-by-frame rain streaks removal in ...
- 7,575
6
votes
1
answer
124
views
Transformer based on pytorch nn.Transformer to predict protein secondary structure
I'm working on a transformer as my final project in high school. Since I'm kinda new to ML (3 months of experience), I need someone to check my implementation, if I made any mistakes or bugs that I ...
- 61
4
votes
1
answer
185
views
3
votes
1
answer
129
views
Pytorch code running slow for Deep Q learning (Reinforcement Learning)
I'm a new student in reinforcement learning. Below is the code that I wrote for deep Q learning:
...
2
votes
1
answer
58
views
One-layer linear neural network to solve a regression problem in PyTorch
Good morning everyone,
I am trying to figure out how deep learning works. My approach is mainly theoretical but I have decided to code a few deep learning projects to get a better feel of the kind of ...
0
votes
0
answers
84
views
Convolution to reduce popcorn noise in black and white video
I have a black & white video as a tensor with the shape [Time, Width, Height] with popcorn noise and I would like to reduce the noise by naively convolving along the time dimension.
Using a ...
- 1,617
3
votes
1
answer
129
views
Randomly rotate an image through right angles
I'm new to Python, and coming from Typescript, I tried to include types, but it's not obvious sometimes.
Currently this is the way I type objects:
Write own simple types
Import type from a library ...
user231318
3
votes
2
answers
182
views
Neural network that determines the gender of a word
I wrote a neural network in Python using PyTorch which determines the gender of a word in Russian. As a training set: a file containing a word and a number from 0 to 2 (0-masculine, 1-feminine and 2-...
user269440
2
votes
0
answers
110
views
Higher order derivatives with functorch
I'm computing higher order derivatives using nested jacobian from pytorch/functorch.
$$f(x, y, z, \dots) : R^{m_x} \times R^{m_y}...
- 121
1
vote
0
answers
181
views
Binary classification with pytorch
I wrote a simple neural network binary classification algorithm using Pytorch. It uses the dataset from https://www.kaggle.com/pritsheta/heart-attack, which consists of a table with 300 rows and 14 ...
- 163