Skip to main content
Stack Overflow
  1. About
  3. For Teams
Filter by
Sorted by
Tagged with
3 votes
1 answer
1k views

I’m working on a PyTorch model where I compute a "global representation" through a forward pipeline. This pipeline is subsequently used in an extra sampling procedure later on in the network. When I ...
2 votes
0 answers
155 views

I'm concerning mixed precision in deep learning LLM. The intermediates are mostly F32 and weights could be any other type like BF16, F16, even quantized type Q8_0, Q4_0. it would be much useful if ...
1 vote
1 answer
203 views

I have been analyzing the maximum throughput I can get from my device for a specific CNN model using a GPU. My GPU has CUDA cores as well as Tensor cores. So I want to simultaneous run the model on ...
-1 votes
1 answer
1k views

I'm trying to save memory while training a model that uses single precision weights by doing the calculations in half precision. I tried using autocast, and the model does prediction in half precision ...
0 votes
2 answers
859 views

I am using Tensorflow 2.10 in windows with a NVIDIA RTX 2060 SUPER (with tensor cores) for deep learning. But when enabling mixed precision of float16 the time per epoch actually becomes slower than ...
3 votes
1 answer
707 views

I want to figure out how the torch.cuda.amp.autocast works. Therefore, I conducted an experiment. The code is as following: class CustomModel(nn.Module): def __init__(self, input_size, hidden_size,...
1 vote
0 answers
1k views

I have a complex model that I would like to train in mixed precision. To do this, I use the torch.amp package. I can enable AMP for the whole model using with torch.cuda.amp.autocast(enabled=...
3 votes
1 answer
2k views

Before I knew about automatic mixed precision, I manually halved the model and data using half() for training with half precision. But the training result is not good at all. Then I used the automatic ...
2 votes
1 answer
6k views

i'm trying to train a deep learning model on vs code so i would like to use the GPU for that. I have cuda 11.6 , nvidia GeForce GTX 1650, TensorFlow-gpu==2.5.0 and pip version 21.2.3 for windows 10. ...
1 vote
1 answer
1k views

In order to improve the latency of a trained model, I tried to use Tensorflow mixed-precision. Just setting the policy as mentioned in https://www.tensorflow.org/guide/mixed_precision does not seem to ...
0 votes
1 answer
1k views

I am saving my model, optimizer, scheduler, and scaler in a general checkpoint. Now when I load them, they load properly but after the first iteration the scaler.step(optimizer) throws this error: ...
0 votes
1 answer
3k views

In my torch model, the last layer is a torch.nn.Sigmoid() and the loss is the torch.nn.BCELoss. In the training step, the following error has occurred: RuntimeError: torch.nn.functional....
0 votes
0 answers
298 views

I don't manage to use Automatic Mixed Precision with TensorFlow 2.3.2 (on Windows 10). I have a TF_ENABLE_AUTO_MIXED_PRECISION variable set to 1 in my system environment. I have enabled memory growth ...
2 votes
1 answer
3k views

I am trying to infer results out of a normal resnet18 model present in torchvision.models attribute. The model is simply trained without any mixed precision learning, purely on FP32. However, I want ...
1 vote
0 answers
429 views

System information OS Platform and Distribution : MacOS TensorFlow installed from : Colab TensorFlow version : 2.5.0 Python version: python 3.7 GPU model and memory: Tesla T4 Error TypeError: Input '...

15 30 50 per page
1
2

AltStyle によって変換されたページ (->オリジナル) /