)
except:
print "ERROR, file already exists: " + validation_files[
index
] + " -> " + TRAININGSET_DIR + "/" + os.path.basename(validation_files[index])
training_files = algo.get_imgfiles(TRAININGSET_DIR)
validation_files = algo.get_imgfiles(VALIDATIONSET_DIR)
dataset_split = 1
# extract features
print ""
print "---------------------"
print "## extracting SIFT features"
algo.__clear_dir(TMP_DIR_TRAINING)
featureCount = algo.extract_features(training_files, TMP_DIR_TRAINING)
performance["sift_feature_count"] = featureCount
# generate codebook
print "---------------------"
print "## generating bag-of-words codebook"
currentCodebook = SIFT_CODEBOOK_FILE + str(len(performances))
clusterCount = hyperparameters["codebook_size"](featureCount)
hyperparameters["codebook_size"] = clusterCount
performance["codebook_size"] = clusterCount
algo.gen_codebook(
TMP_DIR_TRAINING,
clusterCount,
currentCodebook,
batch_size=algo.BATCH_SIZE if algo.BATCH_SIZE >= clusterCount else clusterCount,
)
print "---------------------"
print "## loading the images and extracting the sift features"
# list files
all_files = get_imgfiles(DATASETPATH)
all_labels = {}
all_weights = {}
for i in all_files:
certainty = float(i.replace("\\","/").rpartition("/")[2].partition("_")[0])
label = 1 if certainty > 0 else 0
all_labels[i] = label
all_weights[i] = certainty if label == 1 else 1-certainty
# extract features
featureCount = algo.extract_features(all_files, TMP_DIR)
# generate codebook
clusterCount = int(sqrt(featureCount))
algo.gen_codebook(TMP_DIR, clusterCount, SIFT_CODEBOOK,
batch_size = algo.BATCH_SIZE if algo.BATCH_SIZE >= clusterCount else clusterCount)
# generate histograms
algo.compute_histograms(TMP_DIR, SIFT_CODEBOOK, TMP_DIR)
# train svm
algo.train_svm(TMP_DIR, all_labels, SVM_MODEL_FILE, all_weights = all_weights)
print "calculating predictions"
predictions = algo.predict(SVM_MODEL_FILE, SIFT_CODEBOOK, DATASETPATH2, TMP_DIR)