Stack Overflow
Stack Overflow

Questions tagged [imagenet]

200 questions
2
votes
0 answers

Google colab keeps crashing when training the model (resnet18/densenet) with tiny-imagenet-200 data

My Google colab crashes immediately as soon as it starts training on tiny-imagenet with 0.1 million images and 200 classes of size 64*64 Colab log shows WARNING:root:kernel 1fe0be22-c98a-4519-a16a-69c9fb4be1da restarted KernelRestarter: restarting…
user13335
  • 21
  • 1
2
votes
1 answer

What is meant by "stationarity of statistics" in the context of CNNs?

I was reading the AlexNet paper (namely "ImageNet Classification with Deep Convolutional Neural Networks"). The Introduction section states "stationarity of statistics" and "locality of pixel dependencies" as the two strong assumptions made in…
Vaibhav Jain
  • 195
  • 1
  • 10
2
votes
0 answers

CNN for single image camera calibration

I've been reading a paper A Perceptual Measure for Deep Single Image Camera Calibration where they adopt DenseNet with a last layer replaced by three separate heads. I take DenseNet from keras: base_model = DenseNet169(include_top = False, weights =…
alex
  • 21
  • 1
2
votes
1 answer

ResNet34 - Pretrained model on imagenet using tensorflow

Can someone point me to the Resnet34 pre-trained model on image-net using tensorflow? I am not sure but TF-slim trained model are same or would there be difference?
Milind Deore
  • 2,887
  • 5
  • 25
  • 40
2
votes
1 answer

Getting RuntimeError: Graph disconnected: cannot obtain value for tensor

I want to create a custom model of ResNet101 by retrieving one of its layer called 'avg_pool' and convert it to my custom layer. I have done this similar thing another pre-trained Imagnet model named resnet50, but getting an error in Resnet101. I am…
Rabel Ahmed
  • 1,131
  • 13
  • 12
2
votes
2 answers

Are there any rules of Wordnet synset ID?

I am new to Imagenet and Wordnet database. I am trying to re-classify the images and categories of Imagenet more roughly (e.g. 'plant', 'fish', 'people', ...). I understand that the images can be downloaded at…
hikaru
  • 617
  • 6
  • 18
2
votes
2 answers

Does training a multi-labeling CNNs on single-class data hinder accuracy?

I built a CNN for a multi-label classification, i.e. predicting multiple labels per image. I noticed that ImageNet and many of the other dataset actually include a set of examples per label. The way they structured the data is such that given a…
Chewbacca
  • 241
  • 1
  • 3
  • 4
2
votes
3 answers

ImageNet: Validation categories in ILSVRC2012

I am using flow_from_directory in ImageDataGenerator from keras to train my convolution neural network. I downloaded the ILSVRC2012 images from this link and I am trying to train and validate my network. The training folder has images categorized in…
Prabaha
  • 879
  • 2
  • 9
  • 19
2
votes
2 answers

how to choose batch size in caffe

I understand that bigger batch size gives more accurate results from here. But I'm not sure which batch size is "good enough". I guess bigger batch sizes will always be better but it seems like at a certain point you will only get a slight…
MoneyBall
  • 2,343
  • 5
  • 26
  • 59
2
votes
1 answer

Caffe | data augmentation by random cropping

I am trying to train my own network on Caffe, similar to Imagenet model. But I am confused with the crop layer. Till the point I understand about crop layer in Imagenet model, during training it will take random 227x227 image crops and train the…
Dharma
  • 2,425
  • 3
  • 26
  • 40
2
votes
2 answers

Classification imagenet - caffe/caffe.hpp: No such a file or directory

I trained net using my own dataset via caffe, now I want to write a classification code using C++. My machine (linux) works with CPU only! (I train the net in VM with GPU's). When I try to "include" specific Caffe header: #include …
Z.Kal
  • 426
  • 4
  • 18
2
votes
1 answer

Convolutional ImageNet network is invariant to flipping images

I am using Deep learning caffe framework for image classification. I have coins with faces. Some of them are left directed some of them are right. To classify them I am using common aproach - take weights and structure from pretrained ImageNet…
Oleg
  • 3,080
  • 3
  • 40
  • 51
2
votes
1 answer

Deep learning - finetuning on top of Conv net model

I am fine-tuning on top of image net model using Alexnet architecture. My data set is quite small (7 images per class without augmentation) . I have to drop last FC layer("FC8") weights but what about other fully connected layers. For "FC6" and…
vinay
  • 57
  • 1
  • 12
2
votes
1 answer

Get ImageNet label for a specific index in the 1000-dimensional output tensor in torch

I have the output Tensor of a forward pass for a Facebook implementation of the ResNet model with a cat image. That is a 1000-dimensional Tensor with the classification probabilities. Using torch.topk I can obtain the top-5 probabilities and their…
Manuel Araoz
  • 15,962
  • 24
  • 71
  • 95
1
vote
0 answers

How to download ImageNet VID dataset?

I want to download the ImageNet VID dataset. I have already signed up on their website ImageNet Site, intending to download the Object Detection from Video (VID) section of ILSVRC2015. However, it appears that the link they provided is not…
Parisa
  • 11
  • 1
1 2
3
…
13 14