intel · mohsinmx · Jan 3, 2023 · Jan 3, 2023 · Jan 3, 2023
diff --git a/c_sharp/OpenVINO_EP/yolov3_object_detection/Program.cs b/c_sharp/OpenVINO_EP/yolov3_object_detection/Program.cs
@@ -108,7 +108,7 @@ static void Main(string[] args)
             // Session Options
             SessionOptions options = new SessionOptions();
             options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
-            options.AppendExecutionProvider_OpenVINO(@"MYRIAD_FP16");
+            options.AppendExecutionProvider_OpenVINO(@"CPU_FP32");
             options.AppendExecutionProvider_CPU(1);
 
             // Run inference

diff --git a/c_sharp/OpenVINO_EP/yolov3_object_detection/README.md b/c_sharp/OpenVINO_EP/yolov3_object_detection/README.md
@@ -2,7 +2,7 @@
 
 1. The object detection sample uses YOLOv3 Deep Learning ONNX Model from the ONNX Model Zoo.
 
-2. The sample involves presenting an image to the ONNX Runtime (RT), which uses the OpenVINO Execution Provider for ONNX RT to run inference on Intel<sup>®</sup> NCS2 stick (MYRIADX device). The sample uses ImageSharp for image processing and ONNX Runtime OpenVINO EP for inference.
+2. The sample involves presenting an image to the ONNX Runtime (RT), which uses the OpenVINO Execution Provider for ONNX RT to run inference on Intel<sup>®</sup> CPU. The sample uses ImageSharp for image processing and ONNX Runtime OpenVINO EP for inference.
 
 The source code for this sample is available [here](https://github.com/microsoft/onnxruntime-inference-examples/tree/main/c_sharp/OpenVINO_EP/yolov3_object_detection).
 

diff --git a/python/OpenVINO_EP/tiny_yolo_v2_object_detection/requirements.txt b/python/OpenVINO_EP/tiny_yolo_v2_object_detection/requirements.txt
@@ -1,9 +1,9 @@
 certifi==2022.5.18.1
 flatbuffers==2.0
-numpy==1.22.4
-onnx==1.11.0
+numpy==1.23.5
+onnx==1.13.0
 opencv-python==4.5.5.64
 Pillow==9.3.0
-protobuf==4.21.6
-scipy==1.7.3
+protobuf==3.20.2
+scipy==1.9.0
 typing-extensions==4.2.0
diff --git a/python/OpenVINO_EP/tiny_yolo_v2_object_detection/tiny_yolov2_obj_detection_sample.py b/python/OpenVINO_EP/tiny_yolo_v2_object_detection/tiny_yolov2_obj_detection_sample.py
@@ -133,7 +133,8 @@ def postprocess_output(out, frame, x_scale, y_scale, i):
 
 def show_bbox(device, frame, inference_time):
   cv2.putText(frame,device,(10,20),cv2.FONT_HERSHEY_COMPLEX,0.5,(255,255,255),1)
-  cv2.putText(frame,'FPS: {}'.format(1.0/inference_time),(10,40),cv2.FONT_HERSHEY_COMPLEX,0.5,(255,255,255),1)
+  if (inference_time!=0):
+    cv2.putText(frame,'FPS: {}'.format(1.0/inference_time),(10,40),cv2.FONT_HERSHEY_COMPLEX,0.5,(255,255,255),1)
   frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
   cv2.imshow('frame',frame)
 
@@ -150,16 +151,16 @@ def main():
     print("Device type selected is 'cpu' which is the default CPU Execution Provider (MLAS)")
     #Specify the path to the ONNX model on your machine and register the CPU EP
     sess = rt.InferenceSession(args.model, so, providers=['CPUExecutionProvider'])
-  elif (args.device == 'CPU_FP32' or args.device == 'GPU_FP32' or args.device == 'GPU_FP16' or args.device == 'MYRIAD_FP16' or args.device == 'VADM_FP16'):
+  elif (args.device == 'CPU_FP32' or args.device == 'CPU_FP16' or args.device == 'GPU_FP32' or args.device == 'GPU_FP16' or args.device == 'MYRIAD_FP16' or args.device == 'VADM_FP16'):
     #Specify the path to the ONNX model on your machine and register the OpenVINO EP
     sess = rt.InferenceSession(args.model, so, providers=['OpenVINOExecutionProvider'], provider_options=[{'device_type' : args.device}])
     print("Device type selected is: " + args.device + " using the OpenVINO Execution Provider")
     '''
     other 'device_type' options are: (Any hardware target can be assigned if you have the access to it)
-    'CPU_FP32', 'GPU_FP32', 'GPU_FP16', 'MYRIAD_FP16', 'VAD-M_FP16'
+    'CPU_FP32', 'CPU_FP16', 'GPU_FP32', 'GPU_FP16', 'MYRIAD_FP16', 'VAD-M_FP16'
     '''
   else:
-    raise Exception("Device type selected is not [cpu, CPU_FP32, GPU_FP32, GPU_FP16, MYRIAD_FP16, VADM_FP16]")
+    raise Exception("Device type selected is not [cpu, CPU_FP32, CPU_FP16, GPU_FP32, GPU_FP16, MYRIAD_FP16, VADM_FP16]")
 
   # Get the input name of the model
   input_name = sess.get_inputs()[0].name

diff --git a/python/OpenVINO_EP/yolov4_object_detection/requirements.txt b/python/OpenVINO_EP/yolov4_object_detection/requirements.txt
@@ -1,9 +1,9 @@
 certifi==2022.5.18.1
 flatbuffers==2.0
-numpy==1.22.4
-onnx==1.11.0
+numpy==1.23.5
+onnx==1.13.0
 opencv-python==4.5.5.64
 Pillow==9.3.0
-protobuf==4.21.6
-scipy==1.7.3
+protobuf==3.20.2
+scipy==1.9.0
 typing-extensions==4.2.0
diff --git a/python/OpenVINO_EP/yolov4_object_detection/yolov4.py b/python/OpenVINO_EP/yolov4_object_detection/yolov4.py
@@ -327,7 +327,8 @@ def main():
         image = draw_bbox(original_image, bboxes)
 
         cv2.putText(image,device,(10,20),cv2.FONT_HERSHEY_COMPLEX,0.5,(255,255,255),1)
-        cv2.putText(image,'FPS: {}'.format(1.0/inference_time),(10,40),cv2.FONT_HERSHEY_COMPLEX,0.5,(255,255,255),1)
+        if (inference_time!=0):
+            cv2.putText(image,'FPS: {}'.format(1.0/inference_time),(10,40),cv2.FONT_HERSHEY_COMPLEX,0.5,(255,255,255),1)
 
         # Write the frame with the detection boxes
         if (args.image):