23,848 questions
-1
votes
1
answer
33
views
Returning a torch::Tensor causes seg fault in Python when returning from a C++ binding with pybind11
I have data from a device that is being captured in Python as arrays and then sent to a C++ binding to speed up some post processing that must happen to format the data properly and convert into a ...
- 21
2
votes
1
answer
53
views
Using Python ctypes Array and c_int as an argument in C++ function binding with pybind11
I have data from a device that is being captured in Python directly as a ctypes.Array of ctypes.c_uint16. I'm working PyTorch to create a new Tensor after some post-processing that must after data ...
- 21
Advice
0
votes
0
replies
36
views
Regarding's MONAI WarmupCosineSchedule with AdamW, should scheduler.step() be called per batch, and does optimizer lr define the peak lr?
I am training a PyTorch segmentation model and using:
torch.optim.AdamW
monai.optimizers.WarmupCosineSchedule
My optimizer:
optimizer = torch.optim.AdamW(
model.parameters(),
lr=1e-4,
...
- 163
1
vote
0
answers
49
views
How to reduce the perceptual discontinuity at end-of-speech in MuseTalk real-time lip sync?
I'm running MuseTalk v1.5 for real-time avatar lip sync on an RTX 4090 at 25fps, streamed over WebRTC. Code is forked from Linly-Talker-Stream (a fork of LiveTalking).
How the pipeline works: during ...
- 11
Advice
0
votes
2
replies
70
views
Do you use raw pytorch or some wrapper or such?
I recently started a course about machine-learning as a part of my master that is apparently essentially a course in PyTorch, since starting the course i have learned that PyTorch is actually used a ...
- 15
0
votes
1
answer
84
views
Kaggle Wheel Build Failed while installing causal-conv1d and mamba-ssm
I am trying to install the mamba-ssm in the kaggle. I am using the h100 GPU. These are the current configuration
pytorch-ignite 0.5.3
pytorch-lightning ...
-1
votes
1
answer
42
views
Why does my LSTM time series prediction show periodic sharp downward spikes on test data?
I am trying to predict google stock price using LSTM model from PyTorch.
However after training my model and plotting the predicted results vs the real value, I see periodic sharp downward spikes.
...
-1
votes
1
answer
95
views
'mat1 and mat2 shapes cannot be multiplied', but shape doesn't actually match the data? [closed]
I'm using PyTorch to train a regression model on 5 datasets separately, each 10x3361.
However, when I run PyTorch, it returns the error RuntimeError: mat1 and mat2 shapes cannot be multiplied (10x[...
- 79
Advice
0
votes
8
replies
164
views
PyTorch training issue with EfficientNetB3 | Validation Accuracy plateu
Metrics
Before I start, I wanted to add that I��m relatively new to deep learning, so my setup may be overly complex or suboptimal.
I’m training an image classification model (EfficientNet-B3 on ...
- 1
2
votes
1
answer
85
views
Pytorch engine saves the batch size : how do I save the model in a way allowing me to input one image at a time?
I'm using pytorch ignite to be able to get metrics easily, so I'm using their checkpoint system to save my model.
I want to be able to test one image at a time for a user interface, but when I try to ...
- 23
Advice
1
vote
0
replies
86
views
Book Recommendation in PyTorch
I am looking to find a book on PyTorch that is suitable for beginners, Ive used sklearn in the past for ML its a simple workflow for me prepare the X and Y data, fit/train a model, and make ...
- 1
0
votes
0
answers
21
views
DLL initialization routine failed on package import
I have tried loading PyTorch in iPython but get a DLL initialization error. In a normal python console it works fine, as below. Windows 10, Miniconda installation.
Can anyone advise how I need to ...
- 1
0
votes
1
answer
59
views
How to make a 2 Label Confusion Matrix and exporting into a json file?
I have to train a convolutional neural network on a dataset. The NN itself works and does what it's supposed to but now I want to make a confusion matrix and export it into a json file for further ...
- 1
Advice
1
vote
1
replies
36
views
Reproducibility Hugging Face Transformer models
If I'm using any transformer model loaded from the Hugging Face Hub with Python, is it somehow possible to reproduce all the seeds, that have been used for the model training/fine-tuning?
Seeds/...
- 5
Advice
0
votes
1
replies
38
views
Is the torch.fx traced graph topologically sorted?
Dependency layer: The layers whose outputs are passed to the current layer. Basically, The current layer is dependent on the outputs of the dependency layers.
For a project, I need to know if the ...
