Testing RTX 3090 for deep learning

RTX_3090_test_vs_AMD_5950x.py

# Modified example from: https://huggingface.co/facebook/detr-resnet-50

from transformers import DetrFeatureExtractor, DetrForObjectDetection
from PIL import Image
import requests
import torch

print("GPU is available:", torch.cuda.is_available()) 
#device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

feature_extractor = DetrFeatureExtractor.from_pretrained('facebook/detr-resnet-50')
model = DetrForObjectDetection.from_pretrained('facebook/detr-resnet-50')

inputs = feature_extractor(images=image, return_tensors="pt")

# On CPU (not batched)
with torch.no_grad():
    for i in range(50):
        outputs = model(**inputs)
        logits = outputs.logits
        bboxes = outputs.pred_boxes        
        
# On GPU (not batched)
inputs.to("cuda:0") 
model.to("cuda:0")

with torch.no_grad():
    for i in range(50):
        outputs = model(**inputs)
        logits = outputs.logits
        bboxes = outputs.pred_boxes
        
# On CPU (batched)
image_list = [image for i in range(32)]
inputs = feature_extractor(images=image_list, return_tensors="pt")
model = model.to("cpu")

with torch.no_grad():
    for i in range(2):
        outputs = model(**inputs)
        logits = outputs.logits
        bboxes = outputs.pred_boxes
        
# On GPU (batched)         
inputs.to("cuda:0") 
model.to("cuda:0")

with torch.no_grad():
    for i in range(2):
        outputs = model(**inputs)
        logits = outputs.logits
        bboxes = outputs.pred_boxes