[
https://issues.apache.org/jira/browse/SYSTEMML-1583?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16000077#comment-16000077
]
Niketan Pansare commented on SYSTEMML-1583:
-------------------------------------------
To allow for transfer learning as well as prediction, Caffe2DML provides
optional 'weights' parameter in the constructor. This is consistent with
Caffe's usage.
{code}
# Prediction
predict_lenet = Caffe2DML(sqlCtx, solver='lenet_solver.proto',
weights='lenet_model', input_shape=(1, 28, 28))
predict_lenet.predict(X_test)
{code}
The key question remains what should be the format of 'lenet_model' ?
- The current version requires that 'lenet_model' is a directory that contains
weights/bias of the relevant layers in the format accepted by SystemML's read.
- In addition, we can extend Caffe2DML to accept .caffemodel file which calls
the converter function developed as part of this JIRA.
Until we stabilize the converter functions,
- Using .caffemodel will be a 2-step process: First, convert .caffemodel to
csv/binaryblock and store in HDFS/Local FS. Then, invoke Caffe2DML with the
path to the HDFS/Local FS directory.
- We should maintain a Model Zoo (https://github.com/niketanpansare/model_zoo/)
with weights in our format along with guided notebook. A good starting point
will be https://github.com/caffe2/caffe2/wiki/Model-Zoo
[~acs_s] [~reinwald] [[email protected]] [~freiss]
> Implement converter in Python to convert caffemodel in SystemML format
> ----------------------------------------------------------------------
>
> Key: SYSTEMML-1583
> URL: https://issues.apache.org/jira/browse/SYSTEMML-1583
> Project: SystemML
> Issue Type: Sub-task
> Reporter: Niketan Pansare
> Assignee: Arvind Surve
>
> Ideally, this converter shouldnot require the caffe to be installed. Please
> see
> http://stackoverflow.com/questions/37572948/extracting-weights-from-caffemodel-without-caffe-installed-in-python
> An example code to convert a caffe model to csv if caffe is installed:
> {code}
> import caffe
> import numpy as np
> #net =
> caffe.Net('/home/biuser/nike/barista/VGG_ILSVRC_19_layers_train_val.prototxt',
> caffe.TEST)
> net =
> caffe.Net('/home/biuser/VGG_trained_models/VGG_ILSVRC_19_layers_deploy.prototxt',
> '/home/biuser/VGG_trained_models/VGG_ILSVRC_19_layers.caffemodel',
> caffe.TEST)
> #surgery.transplant(net, base_net)
> for l in [ "conv1_1", "conv1_2", "conv2_1", "conv2_2", "conv3_1", "conv3_2",
> "conv3_3", "conv3_4", "conv4_1", "conv4_2", "conv4_3", "conv4_4", "conv5_1",
> "conv5_2", "conv5_3", "conv5_4", "fc6", "fc7", "fc8" ]:
> w = net.params[l][0].data
> w = w.reshape(w.shape[0], -1)
> b = net.params[l][1].data
> b = b.reshape(b.shape[0], -1)
> # You may have to reshape it for fc layers
> np.savetxt("VGG_trained_models/" + l + "_weight.csv", w,
> delimiter=",")
> np.savetxt("VGG_trained_models/" + l + "_bias.csv", b, delimiter=",")
> {code}
> Here is an example pyspark script to test this JIRA:
> {code}
> from systemml.mllearn import Caffe2DML
> from pyspark.sql import SQLContext
> import numpy as np
> import urllib, os, scipy.ndimage
> from PIL import Image
> import systemml as sml
> # ImageNet specific parameters
> img_shape = (3, 224, 224)
> # Downloads a jpg image, resizes it to 224 and return as numpy array in N X
> CHW format
> url =
> 'https://upload.wikimedia.org/wikipedia/commons/thumb/5/58/MountainLion.jpg/312px-MountainLion.jpg'
> outFile = 'test.jpg'
> urllib.urlretrieve(url, outFile)
> input_image = sml.convertImageToNumPyArr(Image.open(outFile),
> img_shape=img_shape)
> # Download the ResNet network
> import urllib
> urllib.urlretrieve('https://raw.githubusercontent.com/niketanpansare/model_zoo/master/caffe/vision/resnet/ilsvrc12/ResNet_50_network.proto',
> 'ResNet_50_network.proto')
> urllib.urlretrieve('https://raw.githubusercontent.com/niketanpansare/model_zoo/master/caffe/vision/resnet/ilsvrc12/ResNet_50_solver.proto',
> 'ResNet_50_solver.proto')
> home_dir = os.path.expanduser('~')
> # let's assume that this function is implemented as
> saveAsBinaryBlock(inputCaffeModel, outputDir)
> resnet_pretrained_weight_dir = os.path.join(home_dir, 'model_zoo', 'caffe',
> 'vision', 'resnet', 'ilsvrc12', 'ResNet_50_pretrained_weights')
> urllib.urlretrieve('https://deepdetect.com/models/resnet/ResNet-50-model.caffemodel',
> 'ResNet-50-model.caffemodel')
> #######################################################################
> # To be implemented as part of this JIRA
> sml.saveAsBinaryBlock('ResNet-50-model.caffemodel',
> resnet_pretrained_weight_dir)
> #######################################################################
> resnet = Caffe2DML(sqlCtx, solver='ResNet_50_solver.proto',
> weights=resnet_pretrained_weight_dir, input_shape=img_shape)
> resnet.predict(input_image)
> # This should return array(['cougar, puma, catamount, mountain lion, painter,
> panther, Felis '], dtype='|S64')
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
