Stack Overflow
Stack Overflow

Questions tagged [mxnet-gluon]

22 questions
3
votes
0 answers

Pass image to gradient function for yolo3 from GlounCV model Zoo

I am trying to get the gradient with respect to a specific images (sitting in adv_loader). These images are loaded in adv_loader. I tried just taking the code that was calculating the gradient in the backprop step but Yolo3 doesn’t seem to have a…
mlanier
  • 167
  • 2
  • 3
  • 14
3
votes
0 answers

Forecast based on gluonts deepstate model is slow when it is run on Linux OS

It is observed that the GluonTS deep state time series model is performing differently in different operating systems. The prediction takes around 3 seconds when it is run over docker container on Mac OS (Quad core, Physical VM, intel i7 @2.3 GHz);…
Rama Rao Bandreddi
  • 31
  • 2
1
vote
1 answer

Error with MXNET and CUDA in Google Colab: no kernel image is available for execution on the device

I am following a tutorial to fin-tune a SOTA model with MXNet. I am doing it in Google Colab: https://cv.gluon.ai/build/examples_action_recognition/finetune_custom.html However, I am unable to make it work. I believe it has to do with the version…
Beatriz
  • 33
  • 4
1
vote
1 answer

Fine-tuning SOTA video models on your own dataset - Sign Language

I am trying to implement a sign classifier using gluoncv API as part of my final year college project. Data set: http://facundoq.github.io/datasets/lsa64/ I followed the Fine-tuning SOTA video models on your own dataset tutorial and…
Aslam-Ep
  • 61
  • 5
1
vote
1 answer

MXNet AdamW optimizer

Adam optimizer has flaws when used with weight decay. In 2018, AdamW optimizer has been proposed. Is there any standard way to implement AdamW in MXNet framework (python implementation)? There is mxnet.optimizer.Adam class, but no…
Emil
  • 629
  • 2
  • 7
  • 24
0
votes
0 answers

Error in training YOLOv3 model with custom dataset using Gluon CV: TBlob.get_with_shape mismatch

I'm currently training a YOLOv3 model on a custom dataset using the script from Gluon CV's GitHub repository. Here's the link to the script: https://github.com/dmlc/gluon-cv/blob/master/scripts/detection/yolo/train_yolo3.py. During training, I…
courage
  • 806
  • 1
  • 8
  • 9
0
votes
0 answers

Mxnet, append elements and remove oldest one

I have an MxNet array representing 4 sequences, each formed by 5 RGB images with dimension (224x224), so that the batch shape is: total_batch.shape = (4, 5, 224, 224, 3) This is just for a visual representation (each square is a 224x224x3…
Carlo
  • 1,321
  • 12
  • 37
0
votes
0 answers

Relative or absolute time stamps for DeepAR training data?

Suppose we would like to use DeepAR gluonts implementation to forecast the views of videos which are created at different times. Is it necessary / better to use the relative time stamps e.g. t_{created}, t_{created}+1,t_{created}+2,... thereby…
shiftyscales
  • 441
  • 4
  • 20
0
votes
0 answers

Can't downgrade Numpy version, multiple errors arrive

I am trying to downgrade my numpy version to 1.16.6 due to a dependency on installing mxnet package, which only works with python<=1.17.0. I already understood that mxnet installation is very consuming so I tried to perform the downgrading of…
rurjais
  • 1
  • 1
0
votes
0 answers

GluonTS SimpleFeedForward Estimator Loss Values

I am using the GluonTS package to produce some probabilistic forecasts on a small dataset (60 observations, 57 training, and 3 test). The reason I have selected the GluonTS is other packages were not really successful to produce some reasonable…
binaryskull
  • 34
  • 5
0
votes
0 answers

Neural Network's parameters turning nan with MXNet

I'm training a neural network with MXNet and turn out that some net's parameters become nan after some training iterations. I'll let the mains part of my code for explanation: Data preparation import mxnet as mx from mxnet import gluon, autograd,…
PabloCarlete
  • 11
  • 1
0
votes
0 answers

i3d_resnet50, shape error when replacing head with Global Average Pooling

I'm working with activity recognition models implemented in GluonCV/MxNet, and I wanted to try replacing the fully connected layer of the model by using global average pooling. I have 4 output classes, so the idea was to: remove the current model…
Carlo
  • 1,321
  • 12
  • 37
0
votes
0 answers

How to check Tensor elements are in list?

I would like to check which elements of an mxnet Tensor are in a python list. How can I do it? For example, let's say I've got the Tensor [[1 2 3] [4 5 6]] and I ask if elements are in list [2, 5], then I should get the answer [[0 1 0] [0 1 0]]
cserpell
  • 716
  • 1
  • 7
  • 17
0
votes
1 answer

How to train deepAR on multiple time series?

I am trying to use the GluonTS implementation of deepAR to train deepAR on multiple time series(using the m5 dataset). However, when I train deepAR on a single time series in the data set, the training takes just as little time as it does to train…
Sebastian Chejniak
  • 1
  • 3
0
votes
0 answers

Running into a tuple index error while creating a deepVAR model

The following is the code I wrote so far for my gluonts deepvar model. I'm trying to use multiple time series to make a prediction and gluonts seemed to be a good option for that. The following below are screenshots of what I've done so far and the…
Humza Haroon
  • 11
  • 2
1
2