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
0
votes
1 answer

Prebuilt Python Caffe for OSX

Is there any pre-built PyCaffe out there for OSX? I do see instructions on how to build it but I'm sure I'll have a lot of difficulties trying to build all of its dependencies. So, I'd appreciate it anyone knows where I can get the prebuilt PyCaffe…
Yasin
  • 609
  • 1
  • 10
  • 22
-1
votes
1 answer

FileNotFoundError: [Errno 2] No such file or directory: '/opt/caffe/build/tools/caffe': '/opt/caffe/build/tools/caffe'

I installed caffe-cpu on my Ubuntu v18 VM via the apt install command. I am struggling to figure out where the install directory is located, correct me if I'm wrong but I believe there is not a install directory. My NN model I'm trying to execute…
Sarim A.
  • 35
  • 2
  • 8
-1
votes
1 answer

UNet Caffe patch installation

I have installed caffe successfully. Have someone tried to install U-Net caffe patch which is including 2D and 3D UNet? Could you please guide if you have installed? Thank you.
user630317
  • 31
  • 8
-1
votes
1 answer

using caffe training model but get a error

I0329 20:38:56.742496 13649 layer_factory.hpp:77] Creating layer data [libprotobuf FATAL google/protobuf/stubs/common.cc:61] This program requires version 3.5.0 of the Protocol Buffer runtime library, but the installed version is 2.6.1. Please…
Huangxs
  • 3
  • 1
  • 2
-1
votes
1 answer

caffe: A CNN with two loss layers and two different label sets

I am interested to have a deep CNN with two loss layers, each of them having its own separate label set. For example, imagine a 10 layer CNN, loss1 is located in 5th layer using label1, then loss2 in the last layer using label2. Note: label1 (loss1)…
Nima
  • 433
  • 2
  • 8
-1
votes
1 answer

Why my feature extraction script fails?

I have used the following script , to extract features vectors of my dataset using AlexNet pretrained model. I extract feature vectors from fully connected layer 7 and save it on HICKLE format. The files that are used in the code below…
user7417788
  • 35
  • 1
  • 6
-1
votes
1 answer

Caffe NetParameter parsing error

I tried to load model and i got this error: Check failed: ReadProtoFromBinaryFile(param_file, param) Failed to parse NetParameter file:…
M. Bystrov
  • 27
  • 3
-1
votes
1 answer

Calling particular function at each input on testing or on prediction?

I want to call a function for every input in test time for MNIST dataset. For example, if the test data in MNIST is x1, ... , xn for every input xi at test time I want to call the function. I modified the code in…
S.AMEEN
  • 1,461
  • 4
  • 16
  • 23
-1
votes
2 answers

What output on this code means?

I'm using this tutorial as example to build my caffe custom training function. On section 15 there is the following code: def train(): niter = 200 test_interval = 25 train_loss = zeros(niter) test_acc = zeros(int(np.ceil(niter /…
Carlos Porta
  • 1,224
  • 5
  • 19
  • 31
-2
votes
1 answer

Caffe CNN: diversity of filters within a conv layer

I have the following theoretical questions regarding the conv layer in a CNN. Imagine a conv layer with 6 filters (conv1 layer and its 6 filters in the figure). 1) what guarantees the diversity of learned filters within a conv layer? (I mean, how…
Nima
  • 433
  • 2
  • 8
-2
votes
2 answers

caffe SqueezeNet: where is the fully connected FC layer in prototxt

I am working on caffe SqueezeNet prototxt link. I am just wondering where is the FC layer? (I only see type: data, conv, relu, pooling, concat, SoftmaxWithLoss and accuracy)
Nima
  • 433
  • 2
  • 8
-2
votes
1 answer

Edit prototxt file from python

I would like to edit a prototxt file using python. I simply need to change the source from one directory to another. Is there a simple way to go about this, to not have to redefine the net and rewrite the entire file? For example, in my prototxt…
jerpint
  • 399
  • 2
  • 16
-2
votes
2 answers

Send two argument using map and lambda functions and return two values

I would like to send two arguments within a function and receive two values as well I want to modify this code so that I code be able to send two arguments and receive two as well list_value = [ 1, 2,0,-1,-9,2,3,5,4,6,7,8,9,0,1,50] hnd = map(lambda…
S.AMEEN
  • 1,461
  • 4
  • 16
  • 23
1 2 3
…
34
35