Questions tagged [chainercv]

13 questions
3
votes
1 answer

How to accumulate gradient across mini-batch and then back-propagation in Chainer?

I am doing classifying video sequence, I need 2 things: Because of limited GPU memory, I want to accumulate gradient across mini-batch, and then average gradient value, and then back propagation. I need to know how to shuffle between mini-batch but…
machen
  • 283
  • 2
  • 10
1
vote
1 answer

How to load Chainer training checkpoint from npz?

I am using Chainer to train (fine-tune) a Resnet model and then use the checkpoint for evaluation. The checkpoint is a npz file with the following structure: When I am loading the model for evaluation with chainer.serializers.load_npz(args.load,…
user2277994
  • 77
  • 2
  • 12
1
vote
1 answer

How to measure time per layer in Chainer

How can I measure the time taken by each layer? This should include both forward and backward pass. For instance, in the case of VGG, I wanna know the time each of the layers takes. Part of the code is shown below. h = F.relu(self.conv1_2(h)) …
ankahira
  • 87
  • 1
  • 11
1
vote
1 answer

ChainerCV input image data format

I have an imageset of 250 images of shape (3, 320, 240) and 250 annotation files. I am using ChainerCV to detect and recognize two classes in the image: ball and player. Here we are using SSD300 model pre-trained on ImageNet dataset. EDIT: CLASS TO…
TulakHord
  • 422
  • 7
  • 15
1
vote
1 answer

What does generate_anchor_base()'s arguments mean?

Github page Looking generate_anchor_base method, which is Faster R-CNN util method in ChainerCV. What is the base_size = 16? I saw in the Documentation that it is The width and the height of the reference window. But what does "reference…
floyd
  • 1,431
  • 2
  • 12
  • 18
0
votes
0 answers

how to save figure in vis_bbox without white background, when plotting with matplotlib?

i'm trying to save the image after vis_bbox prediction with its original image dimension. my code: from PIL import Image, ImageChops import cv2 img = utils.read_image('/home/ubuntu/ui.jpg', color=True) bboxes, labels,scores =…
0
votes
1 answer

Shift from single gpu to multiple gpu.Throws an error TypeError: '<' not supported between instances of 'list' and 'int'

I had shifted from using single gpu to multiple gpu. The Code throws an error epoch main/loss validation/main/loss elapsed_time Exception in main training loop: '<' not supported between instances of 'list' and 'int' …
user11640939
0
votes
0 answers

How to deal with NaN and 0 for Loss and Validation during Training

I am using SSD512(imagenet pre-trained model) and Faster_R-CNN(pre-trained) while training, the loss and confidence displays nan and validation as 0. [Basketball-ChainerCV]…
0
votes
1 answer

ChainerCV SSD512 MODEL not training

I have used SSD300(imagenet pre-trained model) for detection and recognition for two class classification:[Basketball-ChainerCV] (https://github.com/atom2k17/Basketball-ChainerCV/blob/master/basketballproject.py). The training and predictions are…
TulakHord
  • 422
  • 7
  • 15
0
votes
1 answer

VOCBboxDataset returns incorrect dataset size when applied to my dataset

I have a 250 image dataset and 250 annotation files with two classes: ball and player. The folder also has three text files train.txt, val.txt, test.txt containing lists of training,testing and validation images respectively. bball_labels =…
0
votes
3 answers

MultiprocessIterator throws error when changing batch_size

I want to train a Faster R-CNN with ChainerCV. As a first test I mostly copied the provided example, I only changed the lines corresponding the dataset to use my custom dataset. I checked if my dataset is fully functional with all operations…
tdiekel
  • 21
  • 6
0
votes
1 answer

How to install ChainerCV

I am using Win 10. I tried installing ChainerCV through pip. I want to know what can be done to solve this problem. Also what is behind this issue: not having VisualStudio, dependency issues or any other thing. Is having CUDA necessary to run…
TulakHord
  • 422
  • 7
  • 15
0
votes
1 answer

Not getting proper output while running 'detection' demo of ChainerCV

I am trying to run a 'detection' demo of ChainerCV from here, https://github.com/chainer/chainercv/tree/master/examples/detection I am running this demo in BitFusion Ubuntu 14.04 Chainer AMI on AWS with a p2.xlarge instance which uses a single…
Hardik Chauhan
  • 2,750
  • 15
  • 30