Questions tagged [pycaffe]

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

18
votes
3answers
6k views

What is a `“Python”` layer in caffe?

Caffe has a layer type "Python". For instance, this layer type can be used as a loss layer.On other occasions it is used as an input layer.What is this layer type?How can this layer be used?
10
votes
2answers
7k views

caffe data layer example step by step

I want to find a caffe python data layer example to learn.I know that Fast-RCNN has a python data layer, but it's rather complicated since Iam not familiar with object detection.So my question is, ...
8
votes
2answers
8k views

How to create caffe.deploy from train.prototxt

This is my train.prototxt. And this is my deploy.prototxt.When I want to load my deploy file I get this error:File "http://stackoverflow.com/python/caffe/classifier.py", line 29, in __init__ in_=self.inputs[0] ...
13
votes
2answers
4k views

Multiple category classification in Caffe

I thought we might be able to compile a Caffeinated description of some methods of performing multiple category classification.By multi category classification I mean: The input data containing ...
4
votes
2answers
4k views

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 ...
1
vote
1answer
542 views

Accuracy reported by caffe and pycaffe are different

Below is the train.Prototxt file that is used to train a pretrained model.name: "TempWLDNET"layer {name: "data"type: "ImageData"top: "data"top: "label"...
44
votes
2answers
24k views

Cheat sheet for caffe / pycaffe?

Does anyone know whether there is a cheat sheet for all important pycaffe commands?I was so far using caffe only via Matlab interface and terminal + bash scripts.I wanted to shift towards using ...
18
votes
2answers
9k views

Building custom Caffe layer in python

After parsing many links regarding building Caffe layers in Python i still have difficulties in understanding few concepts. Can please someone clarify them? Blobs and weights python structure for ...
14
votes
2answers
30k views

NameError: name 'get_ipython' is not defined

I am working on Caffe framework and using PyCaffe interface. I am using a Python script obtained from converting the IPython Notebook 00-classification.ipynb for testing the classification by a ...
9
votes
2answers
3k views

Caffe: how to get the phase of a Python layer?

I created a "Python" layer "myLayer" in caffe, and use it in the net train_val.prototxt I insert the layer like this:layer {name: "my_py_layer"type: "Python"bottom: "in"top: "out"...
7
votes
2answers
1k views

deep learning - a number of naive questions about caffe

I am trying to understand the basics of caffe, in particular to use with python.My understanding is that the model definition (say a given neural net architecture) must be included in the '.prototxt'...
41
votes
1answer
13k views

Faster RCNN for TensorFlow

Has anyone implement the FRCNN for TensorFlow version?I found some related repos as following:Implement roi pool layerImplement fast RCNN based on py-faster-rcnn repobut for 1: assume the roi ...
3
votes
3answers
2k views

Backward pass in Caffe Python Layer is not called/working?

I am unsuccessfully trying to implement a simple loss layer in Python using Caffe. As reference, I found several layers implemented in Python, including here, here and here.Starting with the ...
2
votes
1answer
1k views

How to classify images using Spark and Caffe

I am using Caffe to do image classification, can I am using MAC OS X, Pyhton.Right now I know how to classify a list of images using Caffe with Spark python, but if I want to make it faster, I want ...
2
votes
2answers
2k views

I “import caffe” from ipython, but I got “RuntimeWarning”. How to resolve it?

I have read the article "Ubuntu Installation --Guide for Ubuntu 14.04 with a 64 bit processor." from Github website (https://github.com/tiangolo/caffe/blob/ubuntu-tutorial-b/docs/install_apt2.md).And ...
1
vote
1answer
232 views

How to modify batch normalization layers (DeconvNet) to be able to run with caffe?

I wanted to run the Deconvnet on my data, however it seemd it has been written for another version of caffe. Does anyone know how to change batch_params?The one that is in Deconvnetlayers { bottom:...
-2
votes
1answer
51 views

Caffe CNN: diversity of filters within a conv layer [closed]

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 ...
5
votes
1answer
3k views

How reconstruct the caffe net by using pycaffe

What I want is, After loading a net, I will decompose some certain layers and save the new net. For exampleOrignial net: data -> conv1 -> conv2 -> fc1 -> fc2 -> softmax;New net:data -> ...
3
votes
4answers
5k views

Exception: “dot” not found in path in python on mac

I want to use caffe.draw to draw the caffe net by anaconda python on mac. But I got the error like this:File "python/draw_net.py", line 45, in <module>main()File "python/draw_net.py", ...
2
votes
4answers
6k views

Extracting weights from .caffemodel without caffe installed in Python

Is there a relatively simple way to extract weights in Python from one of the many pretrained models in Caffe Zoo WITHOUT CAFFE (nor pyCaffe)? i.e. parsing .caffemodel to hdf5/numpy or whatever format ...
8
votes
1answer
5k views

Caffe Iteration loss versus Train Net loss

I'm using caffe to train a CNN with a Euclidean loss layer at the bottom, and my solver.prototxt file configured to display every 100 iterations. I see something like this,Iteration 4400, loss=0...
4
votes
1answer
3k views

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 ...
7
votes
2answers
1k views

Multiple pretrained networks in Caffe

Is there a simple way (e.g. without modifying caffe code) to load wights from multiple pretrained networks into one network? The network contains some layers with same dimensions and names as both ...
3
votes
1answer
1k views

Net surgery: How to reshape a convolution layer of a caffemodel file in caffe?

I'm trying to reshape the size of a convolution layer of a caffemodel (This is a follow-up question to this question). Although there is a tutorial on how to do net surgery, it only shows how to copy ...
3
votes
1answer
687 views

batch size does not work for caffe with deploy.prototxt

I'm trying to make my classification process a bit faster. I thought of increasing the first input_dim in my deploy.prototxt but that does not seem to work. It's even a little bit slower than ...
2
votes
1answer
403 views

Caffe accuracy bigger than 100%

I'm building one but, and when I use the custom train function provided on lenet example with a batch size bigger than 110 my accuracy gets bigger than 1 (100%).If I use batch size 32, I get 30 ...
1
vote
1answer
402 views

How to apply a pre-trained model of 3 channel images on single channel images?

I tried to used a pre-trained model that already was trained on three-channel color images, however, I am getting an error because of shape difference. Could someone let me know how can I tackle this ...
1
vote
1answer
555 views

net surgery on a custom caffe model

I'm trying to modify the weights of a caffemodel which is part of a caffe-branch called Deep Lab. Although there is a tutorial on how to do net surgery, when I try to do the same with my custom ...
6
votes
1answer
4k views

RMSprop, Adam, AdaDelta test accuracy does not improve using Caffe

I am finetuning using Caffe on an image dataset on a Tesla K40. Using a batch size=47, solver_type=SGD, base_lr=0.001, lr_policy="step", momentum=0.9, gamma=0.1, the training loss decreases and test ...
5
votes
1answer
2k views

Caffe HDF5 pixel-wise classification

I am trying to implement a pixel-wise binary classification for images using caffe. For each image having dimension 3x256x256, I have a 256x256 label array in which each entry is marked as either 0 ...

153050per page
angop.ao, elkhabar.com, noa.al, afghanpaper.com, bbc.com, time.com, cdc.gov, nih.gov, xnxx.com, github.com,