Google Colab (Free) Crash due to not enough memory
#8
by
masoudkaviani
- opened
I had run this piece of code in Google Colab (Free) and the runtime crashed due to not enough memory! Any idea about that?
code:
import torch
from PIL import Image
import requests
from transformers import AutoProcessor, Blip2Model
device = "cuda" if torch.cuda.is_available() else "cpu"
model = Blip2Model.from_pretrained("Salesforce/blip2-opt-2.7b", torch_dtype=torch.float16)
model.to(device)
processor = AutoProcessor.from_pretrained("Salesforce/blip2-opt-2.7b")
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(images=image, return_tensors="pt").to(device, torch.float16)
image_outputs = model.get_image_features(**inputs)
do this(this loads it in 8 bit so it uses less memory)
# pip install accelerate bitsandbytes
import torch
import requests
from PIL import Image
from transformers import Blip2Processor, Blip2ForConditionalGeneration
processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b")
model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", load_in_8bit=True, device_map="auto")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
question = "how many dogs are in the picture?"
inputs = processor(raw_image, question, return_tensors="pt").to("cuda", torch.float16)
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))