I am testing an FCN-VGG16 network in Caffe. Instead of resizing the input images to a fixed size, I reshape the network each time to the image size. I tried this in both matcaffe and pycaffe. In both cases, it seems that it is able to run for small images (for example, 500x500). However, when I have a larger sized image (e.g. 1920 x 1080), I get this error "Check failed: error == cudaSuccess (2 vs. 0) out of memory". I am running this on a Quadro M6000 GPU with 12 GB memory. Any help/advice would be appreciated.
Testing FCN on large image sizes
562 Views Asked by user6137678 At
1
There are 1 best solutions below
Related Questions in CAFFE
- Python interface of Caffe: Error in "import caffe"
- compiling caffe on Yosemite
- [Caffe]: Check failed: ShapeEquals(proto) shape mismatch (reshape not set)
- Caffe layer registry error
- Error in creating LMDB database file in Python for Caffe
- Caffe net.predict() outputs random results (GoogleNet)
- How to convert Mat from opencv to caffe format
- How to create an caffemodel file from training image and its labeled?
- Error when using classify in caffe
- Two errors while running Caffe
- How to speed up caffe classifer in python
- installing caffe cmake error
- Error while installing deepdish
- Caffe Framework Runtest Core dumped error
- Generate caffemodel file
Related Questions in PYCAFFE
- Transfer weights from caffe to tensorflew
- How does Caffe determine test set accuracy?
- How to set the bias_term false in a convolutional layer pycaffe?
- How did you run FCN code semantic segmentation?
- Is it possible to forward the output of a deep-learning network to another network with caffe / pycaffe?
- How to create LMDB files for semantic segmentation?
- Issues during 'make pycaffe' on OSX
- How to change between GPU mode and CPU mode in caffe?
- caffe / unet: Could not compute map between tops; are they connected by spatial layers?
- Do I have to use a Scale-Layer after every BatchNorm Layer?
- Faster-RCNN bbox/image normalization
- He-initialization for Caffe?
- I am getting error with caffe.io.array_to_datum() for single channel images, how to solve?
- Do I have to transpose my gray scale image while creating LMDB database?
- Error using Caffe: "This tool requires OpenCV; compile with USE_OPENCV."
Related Questions in MATCAFFE
- How did you run FCN code semantic segmentation?
- Do I have to transpose my gray scale image while creating LMDB database?
- Getting error on [base_conv_layer.cpp:122] Check failed: channels_ % group_ == 0 (1 vs. 0) , how to solve it?
- I am getting Incorrect data field size error while generating the mean image of training data, even after generating by using create_imagenet.sh,why?
- What parts an parameters of train_val.prototxt, solver.prototxt, and deploy.prototxt should be changed based on our own data?
- caffe forward net in a for loop not working
- How do you export .caffemodels to other applications?
- Extract Caffe features with variable batch size in Matlab
- Data augmentation on-the-fly for semantic segmentation, Is my python layer definition correct?
- What kind of on-the-fly artificial data augmentation can be applied for semantic segmentation?
- Does scaling the values to [0,1] affect the CNN learning procedure?
- Testing FCN on large image sizes
- Caffe regression wrong no. of outputs in final layer
- Interpret Caffe FCN output classes
- How can I use matcaffe in Windows?
Trending Questions
- UIImageView Frame Doesn't Reflect Constraints
- Is it possible to use adb commands to click on a view by finding its ID?
- How to create a new web character symbol recognizable by html/javascript?
- Why isn't my CSS3 animation smooth in Google Chrome (but very smooth on other browsers)?
- Heap Gives Page Fault
- Connect ffmpeg to Visual Studio 2008
- Both Object- and ValueAnimator jumps when Duration is set above API LvL 24
- How to avoid default initialization of objects in std::vector?
- second argument of the command line arguments in a format other than char** argv or char* argv[]
- How to improve efficiency of algorithm which generates next lexicographic permutation?
- Navigating to the another actvity app getting crash in android
- How to read the particular message format in android and store in sqlite database?
- Resetting inventory status after order is cancelled
- Efficiently compute powers of X in SSE/AVX
- Insert into an external database using ajax and php : POST 500 (Internal Server Error)
Popular Questions
- How do I undo the most recent local commits in Git?
- How can I remove a specific item from an array in JavaScript?
- How do I delete a Git branch locally and remotely?
- Find all files containing a specific text (string) on Linux?
- How do I revert a Git repository to a previous commit?
- How do I create an HTML button that acts like a link?
- How do I check out a remote Git branch?
- How do I force "git pull" to overwrite local files?
- How do I list all files of a directory?
- How to check whether a string contains a substring in JavaScript?
- How do I redirect to another webpage?
- How can I iterate over rows in a Pandas DataFrame?
- How do I convert a String to an int in Java?
- Does Python have a string 'contains' substring method?
- How do I check if a string contains a specific word?
I know it's obvious from the message, but you do have to reduce the input size: the GPU doesn't have enough on-board memory for everything you fed it. Can you reduce your batch size? If not, do you really need the entire 2M pixels? Most models do quite well with cropped or reduced images. Do this as part of the input processing (on the CPU), and parametrize it for any sine input.
Resizing the network is expensive in memory, especially if you resize all layers, scaling with the input dimensions. In the case you gave, this will increase your memory requirements by roughly 8x.
As a check on the size you can have, watch the memory figures as you initialize the network; I believe that Caffe reports memory requirements by layer.