Stack Overflow
Stack Overflow

Questions tagged [pycaffe]

The Python interface – pycaffe – is the caffe module and its scripts in caffe/python.

Pycaffe is a Python-based library which has been developed over at UC Berkeley Vision and Learning Center (BVLC). It offers high performance and modularity for implementing [deep] models.

Useful Links:

523 questions
4
votes
1 answer

cp: not writing through dangling symlink '/usr/lib/x86_64-linux-gnu/libhdf5.so'

I am facing this issue, Could you please give me some hints how to solve this: $sudo cp ~/anaconda2/lib/libhdf5* /usr/lib/x86_64-linux-gnu/ cp: not writing through dangling symlink '/usr/lib/x86_64-linux-gnu/libhdf5.so' cp: not writing through…
S.EB
  • 1,966
  • 4
  • 29
  • 54
4
votes
2 answers

How good is training in pycaffe compared to caffe?

I want to try using pycaffe interface to train caffe models. Particularly I want to use a python layer for input data. Will this training be slow or will pycaffe just act as an interface to actual caffe?What are the effects? Any attempts to…
curio17
  • 660
  • 1
  • 6
  • 15
4
votes
0 answers

libprotobuf.so.8 cannot open shared object file

I installed caffe on Ubuntu 16.04. In the terminal I type into Python and import caffe, no error tips. When I run a Python script use 'python demo.PY' I get one error with the following tip: from ._caffe import Net SGDSolver... import error…
yann
  • 652
  • 7
  • 14
4
votes
2 answers

Modify threshold in ReLU in Caffe framework

I am new to Caffe, and now I need to modify the threshold values in ReLU layers in a convolution neural network. The way I am using now to modify thresholds is to edit the C++ source code in caffe/src/caffe/layers/relu_layer.cpp, and recompile it.…
zbqv
  • 79
  • 8
4
votes
1 answer

fast-r-cnn: caffe.LayerParameter" has no field named "roi_pooling_param

When I tried to run ./tools/demo.py of fast-r-cnn. working on UBUNTU 16.04 I got the following error, although the caffe is successfully installed!! ./tools/demo.py WARNING: Logging before InitGoogleLogging() is written to STDERR W0823…
user1217585
4
votes
1 answer

Caffe: what's the difference between train_test.prototxt and deploy.prototxt?

In pertained models like GoogleNet https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet we can see two .prototxt file describing the network, what's the differences between them? deploy.txt and train_test.prototxt My key question is ,…
Long
  • 366
  • 4
  • 13
4
votes
1 answer

pyplot axes title not showing

I have written this code to check object bounding box but when I give title to the axes, it doesn't show up. (I was going to give the file number as title). #!/home/ckim/anaconda2/bin/python #%pylab import os.path as osp import sys import cv2 import…
Chan Kim
  • 5,177
  • 12
  • 57
  • 112
4
votes
1 answer

caffe fully convolutional cnn - how to use the crop parameters

I am trying to train a fully convolutional network for my problem. I am using the implementation https://github.com/shelhamer/fcn.berkeleyvision.org . I have different image sizes. I am not sure how to set the 'Offset' param in the 'Crop' layer.…
user570593
  • 3,420
  • 12
  • 56
  • 91
4
votes
1 answer

Accuracy is not improving further

I am using pre-trained GoogLeNet and then fine tuned it on my dataset for classifying 11 classes. I tried the following configurations with different base_learning rate, but the accuracy is not improving further. I used pre-trained GoogLeNet model…
fkeufss
  • 85
  • 4
4
votes
2 answers

Issues in save - load apollocaffe models

I am saving my trained model using following command: net.save(model_name) And then loading it using following command: net.load(model_name) But after loading the model, when I am trying to print blobs using net.blobs(), it gives me an empty…
Shweta
  • 1,111
  • 3
  • 15
  • 30
4
votes
2 answers

Limit Caffe CPU core usage?

Is there a way to limit Caffe's CPU core usage? For my instance I have a Xeon E5-2699 and I'd like to limit Caffe to using 9 cores, so 50 percent of the CPU. Most of the training is done on the GPU and I have some other development I would like to…
Dimitri S
  • 81
  • 4
4
votes
2 answers

Caffe shape mismatch error using pretrained VGG-16 model

I am using PyCaffe to implement a neural network inspired by the VGG 16 layer network. I want to use the pre-trained model available from their GitHub page. Generally this works by matching layer names. For my "fc6" layer I have the following…
marcman
  • 3,233
  • 4
  • 36
  • 71
4
votes
1 answer

Caffe feature extraction is too slow? caffe.Classifier or caffe.Net

I have trained a model with images. And now would like to extract the fc-6 features to .npy files. I'm using caffe.set_mode_gpu()to run the caffe.Classifier and extract the features. Instead of extracting and saving the feature per frame. I save…
Arsenal Fanatic
  • 3,663
  • 6
  • 38
  • 53
3
votes
0 answers

Is there a way to programmatically (e.g. pycaffe, etc.) given an existing caffe model .prototxt set all learning rates to zero in all layers?

I am trying to freeze a backbone of an already existing caffe model. There has to be a way to loop through layers and set the learning rates to zero.
Mabu
  • 161
  • 8
3
votes
1 answer

Invalid syntax error in rrule.py when importing caffe in python3.6

I built Caffe and Pycaffe successfully, however, there is something wrong which I could not figure it out myself. Upon importing caffe in python I'm getting this error : Python 3.6.4 |Anaconda, Inc.| (default, Jan 16 2018, 18:10:19) [GCC 7.2.0] on…
Hossein
  • 24,202
  • 35
  • 119
  • 224
1 2
3
…
34 35