diff options
| author | Private Island Networks Inc <opensource@privateisland.tech> | 2026-08-24 20:05:22 -0400 |
|---|---|---|
| committer | Private Island Networks Inc <opensource@privateisland.tech> | 2026-08-24 20:05:22 -0400 |
| commit | aaae2e60f196cbe0ee84f5d9076c4449a4ba0c28 (patch) | |
| tree | d61bd4f3bd878e38406020ab9687f3060cebcc63 /infer/http_infer_mlp.py | |
Diffstat (limited to 'infer/http_infer_mlp.py')
| -rw-r--r-- | infer/http_infer_mlp.py | 97 |
1 files changed, 97 insertions, 0 deletions
diff --git a/infer/http_infer_mlp.py b/infer/http_infer_mlp.py new file mode 100644 index 0000000..f7fa227 --- /dev/null +++ b/infer/http_infer_mlp.py @@ -0,0 +1,97 @@ +#
+# http_infer_mlp
+#
+import sys
+import numpy as np
+import datetime
+import argparse
+import tritonclient.http as httpclient
+from sklearn.datasets import make_moons
+from sklearn.preprocessing import StandardScaler
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser(description='Sends requests via KServe REST API using images in numpy format. '
+ 'It displays performance statistics and optionally the model accuracy')
+ parser.add_argument('--http_address', required=False, default='localhost', help='Specify url to http service. default:localhost')
+ parser.add_argument('--http_port', required=False, default=8000, help='Specify port to http service. default: 8000')
+ parser.add_argument('--input_name', required=False, default='input', help='Specify input tensor name. default: input')
+ parser.add_argument('--output_name', required=False, default='resnet_v1_50/predictions/Reshape_1',
+ help='Specify output name. default: resnet_v1_50/predictions/Reshape_1')
+ parser.add_argument('--iterations', default=1000,
+ help='Number of requests iterations',
+ dest='iterations', type=int)
+ parser.add_argument('--model_name', default='resnet', help='Define model name, must be same as is in service. default: resnet',
+ dest='model_name')
+ parser.add_argument('--pipeline_name', default='', help='Define pipeline name, must be same as is in service',
+ dest='pipeline_name')
+ parser.add_argument('--binary_data', default=False, action='store_true', help='Send input data in binary format', dest='binary_data')
+ parser.add_argument('--tls', default=False, action='store_true', help='use TLS communication with gRPC endpoint')
+ parser.add_argument('--server_cert', required=False, help='Path to server certificate', default=None)
+ parser.add_argument('--client_cert', required=False, help='Path to client certificate', default=None)
+ parser.add_argument('--client_key', required=False, help='Path to client key', default=None)
+
+ args = vars(parser.parse_args())
+ iterations = args.get('iterations')
+
+ # Create the data
+ X, y = make_moons(n_samples=iterations, noise=0.2, random_state=42)
+ scaler = StandardScaler()
+ X = scaler.fit_transform(X)
+
+ address = "{}:{}".format(args['http_address'], args['http_port'])
+ batch_size = 1
+
+ if args['tls']:
+ ssl_options = {
+ 'keyfile':args['client_key'],
+ 'cert_file':args['client_cert'],
+ 'ca_certs':args['server_cert']
+ }
+ else:
+ ssl_options = None
+
+ triton_client = httpclient.InferenceServerClient(
+ url=address,
+ ssl=args['tls'],
+ ssl_options=ssl_options,
+ verbose=False)
+
+ processing_times = np.zeros((0), int)
+
+ print('Start processing:')
+ print('\tModel name: {}'.format(args.get('pipeline_name') if bool(args.get('pipeline_name')) else args.get('model_name')))
+ print('\tIterations: {}'.format(iterations))
+
+ iteration = 0
+ is_pipeline_request = bool(args.get('pipeline_name'))
+ y_test = []
+ num_correct = 0
+
+ while iteration < iterations:
+ inputs = []
+ inputs.append(httpclient.InferInput(args['input_name'], [1,2], "FP32"))
+ point = np.array([X[iteration]],dtype=np.float32)
+ inputs[0].set_data_from_numpy(point)
+ start_time = datetime.datetime.now()
+ results = triton_client.infer(
+ model_name=args.get('pipeline_name') if is_pipeline_request else args.get('model_name'),
+ inputs=inputs)
+ end_time = datetime.datetime.now()
+ duration = (end_time - start_time).total_seconds() * 1000
+ processing_times = np.append(processing_times, np.array([int(duration)]))
+ output = results.as_numpy(args['output_name'])
+ y_test.append(float(output[0][0]))
+ if y[iteration] == round(float(output[0][0])):
+ num_correct += 1
+
+
+ # for object classification models show imagenet class
+ print('Iteration {}; Processing time: {:.2f} ms; speed {:.2f} fps'.format(iteration, round(np.average(duration), 2),
+ round(1000 * batch_size / np.average(duration), 2)
+ ))
+ iteration += 1
+
+
+
+ print('finished with {} out of {} correct'.format(num_correct, iterations))
+
+
|
