Hey there people, i’m new to CUDA I have speed issues with code down below, when running this program my video feed has a noticeable delay and I assumed that “with vpi.Backend.CUDA:” would execute processing tasks faster than"with vpi.Backend.CPU" as it utilises the gpu on my jetson orin nano but there is no noticeable difference in the delay on my video feed when using vpi.Backend.CUDA vs vpi.Backend.CPU which is confusing me. Any help would be great as I’m still learning many things.
Thanks a bunch
regards
joe
def process_frame_vpi(frame, kernel_size=1):
#Create a VPI stream
stream = vpi.Stream()
with vpi.Backend.CUDA:
with stream:
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
r, g, b = cv2.split(frame_rgb)
# Create VPI images for each channel
r_vpi = vpi.asimage(r, vpi.Format.U8)
g_vpi = vpi.asimage(g, vpi.Format.U8)
b_vpi = vpi.asimage(b, vpi.Format.U8)
# Apply median blur using VPI on each channel
with stream:
r_blurred = r_vpi.median_filter((kernel_size, kernel_size), stream=stream)
g_blurred = g_vpi.median_filter((kernel_size, kernel_size), stream=stream)
b_blurred = b_vpi.median_filter((kernel_size, kernel_size), stream=stream)
# Sync the stream to ensure processing is complete
stream.sync()
# Retrieve the processed images
r_processed = r_blurred.cpu()
g_processed = g_blurred.cpu()
b_processed = b_blurred.cpu()
# Merge the processed channels back into an RGB image
with stream:
processed_frame = cv2.merge([r_processed, g_processed, b_processed])
# Convert the processed frame back to BGR for display
with stream:
processed_frame_bgr = cv2.cvtColor(processed_frame, cv2.COLOR_RGB2BGR)
stream.sync()
return processed_frame_bgr
def main():
# Open the camera
gst_pipeline =(
'nvarguscamerasrc ! ’
'video/x-raw(memory:NVMM), width=1920, height=1080, framerate=30/1 ! ’
'nvvidconv ! video/x-raw, format=BGRx ! videoconvert ! ’
‘video/x-raw, format=BGR ! appsink’
)
cap = cv2.VideoCapture(gst_pipeline, cv2.CAP_GSTREAMER)
Adjust the camera index if necessary
if not cap.isOpened():
print("Error: Could not open video stream.")
return
while True:
# Capture a frame from the video feed
ret, frame = cap.read()
if not ret:
print("Error: Could not read frame.")
break
# Process the frame using VPI
processed_frame = process_frame_vpi1(frame, 5)
# Display the original and processed frames
with vpi.Backend.CUDA:
cv2.imshow('Processed Frame', processed_frame)
cv2.imshow('Original Frame', frame)
# Break the loop on 'q' key press
if cv2.waitKey(1) & 0xFF == ord('q'):
break
if name == “main”:
main()
#planarcode
