def loadSvmModel(modelParams, dataType, setID, repeat, size, X_train, y_train):
modelFn = modelParams['modelFn']
if modelFn is not None:
model = pickle.load(open(modelFn, "rb"))
else:
model = train_SVM(X_train, y_train)
fn = iconicImagesFileFormat().format("model{}_svm_{}_{}_{}.pkl".format(
dataType, setID, repeat, size))
pickle.dump(model, open(fn, "wb"))
print(" saved model to {}".format(fn))
print("\n\n-=- model loaded -=-\n\n")
return model
transform=None)
print('this is the annocount', annoCount)
l_feat,l_idx,y = extract_pyroidb_features(pyroidb, 'hog', clsToSet, calc_feat = False, \
spatial_size=(32, 32),hist_bins=32, \
orient=9, pix_per_cell=8, cell_per_block=2, \
hog_channel=0)
X_train, X_test, y_train, y_test, X_idx = split_data(train_size, test_size, \
l_feat,l_idx, y,\
clsToSet)
print(X_train.shape)
print(y_train.shape)
X_train, X_test = scale_data(X_train, X_test)
model = train_SVM(X_train, y_train)
print("accuracy on test data {}".format(model.score(X_test, y_test)))
path_to_save = osp.join(cfg.PATH_TO_NTD_OUTPUT,
'Mat1_' + setID + '_' + repeat + '_' + str(size))
cm_cropped = make_confusion_matrix(model, X_test, y_test, clsToSet,
path_to_save)
#raw image input
pyroidb = RoidbDataset(roidb, [0, 1, 2, 3, 4, 5, 6, 7],
loader=roidbSampleImage,
transform=None)
print('this is the annocount', annoCount)