I get the following error when I try to open a .ncu-rep file that I generated from the command:
#!/bin/bash
batch_sizes=(64)
input_script="inference_scripts/yolo_infer.py"
output_dir="results/ncu-reps/9-April/yolo"
echo "$input_script"
script_name=$(basename "$input_script" .py)
for batch_size in "${batch_sizes[@]}"; do
sudo ncu --target-processes all --set roofline -f -o "$output_dir/${script_name}_bs_${batch_size}_epoch_20" bash exp_script.sh "$input_script" "$batch_size"
echo "Profiling for batch size $batch_size successful!"
done
echo "PROFILING SUCCESSFUL!"
where yolo_infer.py program is as follows:
import numpy as np
from ultralytics import YOLO
import argparse
import torch
from warnings import filterwarnings
import logging
import os
filterwarnings('ignore')
parser = argparse.ArgumentParser()
parser.add_argument('--epochs', default=20, type=int)
parser.add_argument('--batch_size', default=32, type=int)
args = parser.parse_args()
epochs = args.epochs
batch_size = args.batch_size
# Set up logging
log_filename = f'yolo_epochs_{epochs}_batchsize_{batch_size}.log'
logging.basicConfig(filename=log_filename, level=logging.INFO, format='%(asctime)s - %(message)s')
# Load the YOLOv8 model (pre-trained on COCO dataset)
model = YOLO('yolov8n.pt') # Use 'yolov8n.pt' for a small model; adjust as needed.
model.to('cuda')
# Function to generate random images
def generate_random_images(bs=16, width=640, height=640):
images = np.array([np.random.randint(0, 256, (height, width, 3), dtype=np.uint8)
for _ in range(bs)])
return torch.tensor(images).permute(0, 3, 1, 2).float().cuda()
# Perform inference using YOLOv8
def perform_inference(model, images):
results = []
for idx, img in enumerate(images):
# YOLOv8 requires images in BGR format (OpenCV)
result = model.predict(img, conf=0.25, verbose=False) # Set confidence threshold as needed
results.append(result)
return results
# Perform inference
for i in range(epochs):
random_images = generate_random_images(bs=batch_size)
print(random_images.shape)
inference_results = perform_inference(model, random_images)
logging.info(f'Epoch {i+1}/{epochs} completed')
# print(inference_results)
I am able to get the results for batch size 1. But for batch size 2 my .ncu-rep file is surprisingly of 15GB and does not open in Nvidia Nsight Compute software.
