Stack Overflow
Stack Overflow

Questions tagged [nvidia-digits]

NVIDIA Deep Learning GPU Training System (DIGITS) is a GUI for training and developing deep neural networks.

See more on NVIDIA's site.
You can also help developing DIGITS on its github.

91 questions
7
votes
2 answers

Ubuntu 17.10: Where is Caffe installed?

The package Digits requires an environment variable to be set with the location of Caffe install directory. The simple way to install Caffe is apt-get install caffe-cuda. However, I can't figure out where it is installed. It is not installed in…
Chuck Carlson
  • 977
  • 8
  • 26
7
votes
2 answers

Multiple pretrained networks in Caffe

Is there a simple way (e.g. without modifying caffe code) to load wights from multiple pretrained networks into one network? The network contains some layers with same dimensions and names as both pretrained networks. I am trying to achieve this…
Igor Ševo
  • 5,459
  • 3
  • 35
  • 80
3
votes
0 answers

JPEG files loaded with Pillow and OpenCV are different. Is this a problem for live image processing?

I used NVIDIA DIGITS to train an image classifier. The training images are in JPG format. DIGITS uses Pillow to load images. I noticed that, at inference time, there are relevant differences in accuracy if the JPG images are loaded with OpenCV…
firion
  • 296
  • 3
  • 12
3
votes
0 answers

Why the same configuration network in caffe and pytorch behaves so differently?

the code in pytorch is here, I only used the vgg19 arch. In order to make the cifar10 dataset preprocessed same in caffe and pytorch, I remove all the transforms in main.py but toTensor(). I found the cifar10 dataset's range is [0,1] in pytorch, but…
不爱吃猫的鱼
  • 76
  • 5
3
votes
0 answers

Using RCNN to autocrop an image

I am new to machine learning. I've been messing around with NVIDIA Digits to train a new dataset. My dataset however is too inaccurate and I think it is because there is too much background in the image that it is getting confused as to what the…
Kroden
  • 31
  • 3
2
votes
2 answers

Error message ' No Algorithm worked' in CNN using Tensorflow2 and NVIDIA RTX 2080 Max-Q

I have used standard code to download MNIST_Fashion dataset and run a CNN, using Tensorflow 2 (2.3.1) and Keras (2.4.0). The code works fine on a normal laptop without GPU. However, on a laptop with NVIDIA RTX 2080 Max-Q I get error message: 'No…
Rob van Bommel
  • 41
  • 1
  • 3
2
votes
1 answer

Loss starts to jump around after few epochs

I am trying to train a neural network to detect steganographic images. I used Nvidia Digits with Tensorflow. My problem is the loss starts to gradually decrease and then starts to jump around. My Neural Network is - from model import Tower from…
Shenath Silva
  • 77
  • 6
2
votes
0 answers

how to convert LMDB data format in NVIDIA DIGITS to CSV to use in Torch?

I want to use Torch for training. I have my image data in LMDB format and I have done the conversion using NVIDIA DIGITS (caffe). How can I convert this .lmdb format to csv or .t7 so that I can use it in Torch?
azzz
  • 91
  • 7
2
votes
1 answer

NVidia DIGITS DetectNet alternatives

I am looking for detection/localization CNNs to run within the NVidia DIGITS training platform. So far it seems they only support their homebrew DetectNet for this purpose. Looking around it seems that other SOTA networks such as faster-RCNN, SSD,…
Bondolin
  • 2,793
  • 7
  • 34
  • 62
2
votes
2 answers

ERROR: Top blob 'data' produced by multiple sources

I have six channel image (2 RGB image concatenated). I want to train the model with these images using AlexNet. I packed the images into lmdb. Then I used the OTHER option for dataset and model, however I am getting the following error when I am…
cpwah
  • 141
  • 1
  • 3
  • 13
2
votes
1 answer

Face Recognition based on Deep Learning (Siamese Architecture)

I want to use pre-trained model for the face identification. I try to use Siamese architecture which requires a few number of images. Could you give me any trained model which I can change for the Siamese architecture? How can I change the network…
Video Analysis Deep Learning
  • 338
  • 2
  • 12
2
votes
2 answers

Convert TensorRT output to Caffe

My network contains some specific layers which are not supported by current tensorRT. so I want to run the conv layers and pooling layers on tensorRT and then use the output from tensorRT as the input of my caffe model which contains some specific…
wanglinski
  • 114
  • 9
2
votes
1 answer

Basic questions about linear regression example from NVIDIA DIGITS

I've a lot of values from all days over one entire year. I'm wanna verify if they have a kind of similarity for each month (verify if these days values correspond to the correct month and/or predict for future same months from another future year).…
Eduardo Andrade
  • 111
  • 1
  • 1
  • 13
2
votes
1 answer

Error using pre-trained model in DIGITS with different dataset. How to modify layers based on new datasets?

I try to use pretrained model (VGG 16) to DIGITS but I got this error. ERROR: Check failed: error == cudaSuccess (2 vs. 0) out of memory and conv2_2 does not need backward computation. relu2_1 does not need backward computation. conv2_1 does not…
Farshid PirahanSiah
  • 761
  • 6
  • 22
2
votes
1 answer

Deploy network is missing a Softmax layer

I try to use pretrained model (VGG 19) to DIGITS but I got this error. ERROR: Your deploy network is missing a Softmax layer! Read the documentation for custom networks and/or look at the standard networks for examples I try to test with my…
Video Analysis Deep Learning
  • 338
  • 2
  • 12
1
2 3 4 5 6 7