exampleHash[exampleIndex] = i
exampleIndex += 1
# Compute and store the category means
categoryMeans.append(np.mean(localList, axis=0))
# Turn imFeatures into a 2D ndarray so that it can be used in K-means later on
imFeatures = np.array(imFeatures)
print "Read Caltech data in memory."
g1 = mixture.GMM(n_components=101,
thresh=1e-05,
covariance_type='diag')
print "About to fit data"
g1.fit(imFeatures)
pkl.dump(g1, open('proc_data/gmm_obj_diag_cov_sift.pkl', 'wb'))
print "Fitted data"
predLabels = g1.predict(imFeatures)
print "Predicted data"
predMeans = g1.means_
errRate, goodClusters, avgEntropy = evaluateClustering(
g1.means_, imFeatures, predLabels, categoryMeans, exampleHash, 101)
print "GMM model predicted labels with an error rate of %.4f%%, produced %d \"accurate\" clusters and %.4f average entropy." % (
errRate, goodClusters, avgEntropy)
print "That's all. Exiting..."
quit()
except Exception as exc:
print "An exception occurred:" + str(exc) + "."
quit()
# Run k-means 500 times (the default) on the data with aim to produce k = 101 clusters.
# The stopping criterion of each iteration is a difference in the computed distortion
# (mean squared error) less than e-05 (the default)
print "Running K-means..."
codebook, _distortion = kmeans(imFeatures, 101, 100)
assignments, _distortion = vq(imFeatures, codebook)
pkl.dump(codebook, open('proc_data/codebook_kmeans_gradients.pkl',
'wb'))
pkl.dump(assignments,
open('proc_data/labelAssignments_kmeans_gradients.pkl', 'wb'))
if (len(assignments) != imFeatures.shape[0]):
raise LogicalError, "Method %s: K-means should have computed %d assignments; instead, it computed %d." % (
stack()[0][3], imFeatures.shape[0], len(assignments))
print "Ran K-means"
errorRate, goodClusters, avgEntropy = evaluateClustering(
codebook, imFeatures, assignments, categoryMeans, exampleHash, 101)
print "K-means produced an error rate of %.4f%%, %d \"good\" clusters and %.4f average entropy." % (
errorRate, goodClusters, avgEntropy)
print "The amount of \'\"good\" clusters corresponds to %.4f%% of total clusters." % (
100 * goodClusters / float(101))
fp = open('output_data/errorRate_gradients_kmeans.txt', 'w')
fp.write(str(errorRate))
fp.close()
fp = open('output_data/accurateClusters_gradients_kmeans.txt', 'w')
fp.write(str(goodClusters))
fp.close()
fp = open('output_data/averageEntropy_gradients_kmeans.txt', 'w')
fp.write(str(avgEntropy))
fp.close()
matfile = loadmat('input_data/caltech101_SIFT/dense_bow/oneForAll_nr1_K1000/'+ cat + '/' + gr_im)
FV, _binedges = np.histogram(matfile['h'], range(1001))
imFeatures.append(FV)
localList.append(FV)
exampleHash[exampleIndex] = i
exampleIndex +=1
# Compute and store the category means
categoryMeans.append(np.mean(localList, axis = 0))
# Turn imFeatures into a 2D ndarray so that it can be used in K-means later on
imFeatures = np.array(imFeatures)
print "Read Caltech data in memory."
g1 = mixture.GMM(n_components=101,thresh = 1e-05, covariance_type='diag')
print "About to fit data"
g1.fit(imFeatures)
pkl.dump(g1, open('proc_data/gmm_obj_diag_cov_sift.pkl', 'wb'))
print "Fitted data"
predLabels= g1.predict(imFeatures)
print "Predicted data"
predMeans = g1.means_
errRate, goodClusters, avgEntropy = evaluateClustering(g1.means_, imFeatures, predLabels, categoryMeans, exampleHash, 101)
print "GMM model predicted labels with an error rate of %.4f%%, produced %d \"accurate\" clusters and %.4f average entropy." %(errRate, goodClusters, avgEntropy)
print "That's all. Exiting..."
quit()
except Exception as exc:
print "An exception occurred:" + str(exc) + "."
quit()
# (mean squared error) less than e-05 (the default)
print "Running K-means..."
codebook, _distortion = kmeans(imFeatures, 101, 100)
assignments, _distortion = vq(imFeatures, codebook)
pkl.dump(codebook, open("proc_data/codebook_kmeans_gradients.pkl", "wb"))
pkl.dump(assignments, open("proc_data/labelAssignments_kmeans_gradients.pkl", "wb"))
if len(assignments) != imFeatures.shape[0]:
raise LogicalError, "Method %s: K-means should have computed %d assignments; instead, it computed %d." % (
stack()[0][3],
imFeatures.shape[0],
len(assignments),
)
print "Ran K-means"
errorRate, goodClusters, avgEntropy = evaluateClustering(
codebook, imFeatures, assignments, categoryMeans, exampleHash, 101
)
print 'K-means produced an error rate of %.4f%%, %d "good" clusters and %.4f average entropy.' % (
errorRate,
goodClusters,
avgEntropy,
)
print 'The amount of \'"good" clusters corresponds to %.4f%% of total clusters.' % (
100 * goodClusters / float(101)
)
fp = open("output_data/errorRate_gradients_kmeans.txt", "w")
fp.write(str(errorRate))
fp.close()
fp = open("output_data/accurateClusters_gradients_kmeans.txt", "w")
