Stack Overflow
Stack Overflow

Questions tagged [imagenet]

200 questions
336
votes
1 answer

How to get chosen class images from Imagenet?

Background I have been playing around with Deep Dream and Inceptionism, using the Caffe framework to visualize layers of GoogLeNet, an architecture built for the Imagenet project, a large visual database designed for use in visual object…
8-Bit Borges
  • 9,643
  • 29
  • 101
  • 198
41
votes
6 answers

What is the resolution of an image in ImageNet dataset?

Does anyone know the resolution of an image in the ImageNet dataset? I'm sorry, but I couldn't find it on their website or in any of the papers.
Shiqing Fan
  • 688
  • 2
  • 8
  • 14
17
votes
4 answers

How can I find Imagenet data labels?

I have two questions about how to load Imagenet datas. I downloaded ILSVRC2012 validation sets(Cause training sets are too large) but I have two problems. I can't understand how can I find out the labels. There are only jpeg files with file names…
Curious_man
  • 169
  • 1
  • 1
  • 5
11
votes
1 answer

Pytorch ImageNet dataset

I am unable to download the original ImageNet dataset from their official website. However, I found out that pytorch has ImageNet as one of it’s torch vision datasets. Q1. Is that the original ImageNet dataset? Q2. How do I get the classes for the…
reginald
  • 123
  • 1
  • 1
  • 4
11
votes
2 answers

Retrain Tensorflow final layer but still use previous Imagenet classes

My objective is to "add" more classes to the existing 1000 Imagenet classes that came with Tensorflow Inception. Now I could just re-run the whole thing by training from scratch using bazel-bin/inception/imagenet_train but that would take a long…
HP.
  • 19,226
  • 53
  • 154
  • 253
11
votes
2 answers

Training Tensorflow Inception-v3 Imagenet on modest hardware setup

I've been training Inception V3 on a modest machine with a single GPU (GeForce GTX 980 Ti, 6GB). The maximum batch size appears to be around 40. I've used the default learning rate settings specified in the inception_train.py file:…
Dominiek
  • 111
  • 1
  • 3
10
votes
3 answers

TensorFlow: Adding Class to Pre-trained Inception Model & Outputting Full Image Hierarchy

Two questions: 1) Does anyone know if I can add new image classes to the pre-trained Inception-v3 model? For example, I wanted to train TensorFlow on a multitude of national flags, but I need to make sure that I can still recognize the images from…
Mink
  • 857
  • 2
  • 11
  • 24
8
votes
1 answer

Cropping/Scaling ImageNet Images

ImageNet images are all different sizes, but neural networks need a fixed size input. One solution is to take a crop size that is as large as will fit in the image, centered around the center point of the image. This works but has some drawbacks.…
Frobot
  • 1,224
  • 3
  • 16
  • 33
7
votes
2 answers

Access to ImageNet data download

I've already been granted by the ImageNet website http://www.image-net.org/download-images to download the image data. And the page shows: You have been granted access to the the whole ImageNet database through our site. By doing so you agree to the…
Flicic Suo
  • 597
  • 1
  • 5
  • 10
7
votes
2 answers

ImportError: cannot import name 'string_int_label_map_pb2'

I compiled the files with the following command. protoc object_detection/protos/*.proto --python_out=. and as a result compiled into .py files. However, I received the following error…
송준석
  • 991
  • 1
  • 16
  • 32
7
votes
2 answers

VGG16 trained on grayscale imagenet

I have found the VGG16 network pre-trained on the (color) imagenet database (as .npy). Is there a VGG16 network pre-trained on a gray-scale version of the imagenet database available? (The usual 'tricks' for using the 3-channel filters of the…
MathMits
  • 91
  • 1
  • 4
6
votes
0 answers

Use pre-trained ResNet 50 in Keras for images with 4 channels

Is there any way I can use the ImageNet weights for ResNet50 for my project which has images of shape (224,224,4)? The image has R,G,B,Y channels. At the moment, I am simply using model = ResNet50(include_top=True, weights=None,…
Rangan Das
  • 323
  • 2
  • 11
6
votes
1 answer

Where can i find ImageNet VID dataset?

ImageNet Large-Scale Visual Recognition Challenge 2015 (ILSVRC2015) introduced a task called object-detection-from-video(VID) with a new dataset. So I go to the ILSVER2015 website and try to find the…
王智寬
  • 415
  • 1
  • 5
  • 17
5
votes
2 answers

How to speed up the "ImageFolder" for ImageNet

I am in an university, and all the file system are in a remote system, wherever I log in with my account, I could aways access my home directory. even though I log into the GPU servers through SSH command. This is the condition where I employ the…
Kevin Sun
  • 452
  • 4
  • 14
5
votes
1 answer

Why is there a discrepancy in the imagenet dataset labels?

Are the labels used for training and the ones used for validation the same? I thought they should be the same; however, there seem to be a discrepancy in the labels that are available online. When I downloaded the imagenet 2012 labels for its…
kwotsin
  • 2,882
  • 9
  • 35
  • 62
1
2 3
…
13 14