23,844 questions
-4
votes
0
answers
40
views
How do I do maximum utilization of my GPUfor yolov11 training [closed]
I have an Nvidia RTX 6000 (48 GB VRAM) GPU, and the CPU is a 4 core CPU.
I am current training a Yolov11 pose model on my dataset using torch, and its only using 1% of my GPU.
In the YOLO training ...
-6
votes
0
answers
60
views
How to implement a Reaction-Diffusion (PDE) Loss for 3D Segmentation or 3D-unet [closed]
I am working on 3D brain tumor segmentation using Swin UNETR (MONAI) and the BraTS 2021 dataset. I want to add a Physics-Informed Loss term based on the Reaction-Diffusion equation to improve ...
- 1
0
votes
0
answers
58
views
Model accuracy and loss_fn is not increasing [closed]
So i started my model , a dummy model to be specific as i am learning DL.
However i keep getting stuck at a point in training loop of acc and loss
enter image description hereenter image description ...
-1
votes
1
answer
88
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 ...
- 23
2
votes
1
answer
76
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 ...
- 23
Advice
0
votes
0
replies
46
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
55
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
76
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
101
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
50
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
104
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
168
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
90
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
88
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
23
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
