Caffe Prediction

**If you find content helpful and want to quote this blog, please provide the link [ayst123] ( http://blog.csdn.net/ayst123/article/details/44223321 )

---

correct me if I am wrong

BGR or RGB?

Caffe uses opencv to convert image to datum. The channels will be disordered to BGR rather than RGB by OpenCV. It means all blobs in caffe are in the BGR format.
When doing test, we have to make image be in the BGR format.

The prediction code

import caffe###################################set modecaffe.set_mode_cpu()net = caffe.Net(caffe_root + 'models/bvlc_reference_caffenet/deploy.prototxt',caffe_root +'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel',caffe.TEST)# input preprocessing: 'data' is the name of the input blob == net.inputs[0]transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})transformer.set_transpose('data', (2,0,1))transformer.set_mean('data', np.load(caffe_root + 'python/caffe/imagenet/ilsvrc_2012_mean.npy').mean(1).mean(1)) # mean pixeltransformer.set_raw_scale('data', 255)  # the reference model operates on images in [0,255] range instead of [0,1]transformer.set_channel_swap('data', (2,1,0))  # the reference model has channels in BGR order instead of RGB###########################################predictnet.blobs['data'].reshape(1,3,227,227)net.blobs['data'].data[...] = transformer.preprocess('data', caffe.io.load_image(caffe_root + 'examples/images/cat.jpg'))out = net.forward()

Explanation

caffe.io.load_image converts image to numpy, which range is [0,1].

def load_image(filename, color=True):    """    Load an image converting from grayscale or alpha as needed.    Take    filename: string    color: flag for color format. True (default) loads as RGB while False        loads as intensity (if image is already grayscale).    Give    image: an image with type np.float32 in range [0, 1]        of size (H x W x 3) in RGB or        of size (H x W x 1) in grayscale.    """    img = skimage.img_as_float(skimage.io.imread(filename)).astype(np.float32)    if img.ndim == 2:        img = img[:, :, np.newaxis]        if color:            img = np.tile(img, (1, 1, 3))    elif img.shape[2] == 4:        img = img[:, :, :3]    return img

transformer. preprocess

net.blobs['data'].data[...] = transformer.preprocess('data', caffe.io.load_image(caffe_root + 'examples/images/cat.jpg'))

do
- convert to single
- resize to input dimensions (preserving number of channels)
- transpose dimensions to K x H x W
- reorder channels (for instance color to BGR)
- scale raw input (e.g. from [0, 1] to [0, 255] for ImageNet models)
- subtract mean
- scale feature

If loading image directly, the python will make its range be [0,1]. That is why we need to set scale raw

forward

out = net.forward()

It will output all output blob. If we want to add additional blob as output, it is better to use

out = net.forward( [‘blob_name’] )

**If you find content helpful and want to quote this blog, please provide the link [ayst123] ( http://blog.csdn.net/ayst123/article/details/44223321 )