parser.add_argument('--num_points', type=int, default=2048, help='Num of points to use') parser.add_argument('--model_path', type=str, default='', metavar='N', help='Path to load model') args = parser.parse_args() return args if __name__ == '__main__': args = get_parser() if args.eval == False: if args.task == 'reconstruct': reconstruction = Reconstruction(args) reconstruction.run() elif args.task == 'classify': classification = Classification(args) classification.run() elif args.task == 'segment': segmentation = Segmentation(args) segmentation.run() else: inference = Inference(args) feature_dir = inference.run() svm = SVM(feature_dir) svm.run()
str(prior["type"][idx]) + "_loc=" + str(int(prior["location"][idx])) + "_scl=" + str(int(prior["scale"][idx])) + ".h5") file_chains = dir_chains + name_chains file_csv = file_chains.replace("h5", "csv") if not os.path.isfile(file_chains): p1d = Inference(posterior=Posterior, prior=prior["type"], prior_loc=prior["location"], prior_scale=prior["scale"], n_walkers=n_walkers, zero_point=zero_point) p1d.load_data(file_data, id_name=id_name) p1d.run(n_iter, file_chains=file_chains, tol_convergence=tolerance) #----------------- Analysis --------------- a1d = Analysis( n_dim=dimension, file_name=file_chains, id_name=id_name, dir_plots=dir_plots, tol_convergence=tolerance, statistic=statistic, quantiles=[0.05, 0.95], # transformation=None, names="2", transformation="ICRS2GAL", ) a1d.plot_chains()
iris = load_iris() X, y = iris.data, iris.target X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.8, random_state=42) import xgboost as xgb xgb_model = xgb.XGBClassifier() xgb_model = xgb_model.fit(X_train, y_train) print("Test data accuracy of the xgb classifier is {:.2f}".format( xgb_model.score(X_test, y_test))) from onnxmltools.convert import convert_xgboost, convert_lightgbm from onnxconverter_common.data_types import FloatTensorType onnx_model = convert_xgboost(xgb_model, initial_types=[("input", FloatTensorType([1, 4]))]) with open("gbtree.onnx", "wb") as f: f.write(onnx_model.SerializeToString()) if __name__ == '__main__': from inference import Inference infer = Inference("gbtree.onnx") print(infer.run(X[:1]))
class NN(nn.Module): def __init__(self): super().__init__() self.fc1 = nn.Linear(4, 16) self.fc2 = nn.Linear(16, 3) def forward(self, x): x = F.relu(self.fc1(x)) x = self.fc2(x) # F.softmax return x net = NN() print(net) # Export: X.shape onnx.export(net, torch.randn(128, 4), './iris.onnx', verbose=True, input_names=['input_name'], output_names=['output_name']) if __name__ == '__main__': from inference import Inference infer = Inference() print(infer.run(X[:128])[:5])
import cv2 from inference import Inference import flask im1 = cv2.imread('bed (1).jpg') infer = Inference() #for i in range(1,9): output = infer.run(im1) cv2.imshow("output", output[0] / 255.0) cv2.waitKey(0) cv2.destroyAllWindows()
from utils import config GPU_LIST = config.INFERENCE_GPUS import os os.environ["CUDA_VISIBLE_DEVICES"] = ','.join('{0}'.format(n) for n in GPU_LIST) from inference import Inference if __name__ == '__main__': pg = Inference(data_dir='/path/to/data/', data_list='/path/to/list', class_num=2, result_dir='./result', use_level=1) pg.run()