我是 torch 的新手,所以如果之前有人问过这个问题,请原谅我。我正在使用 OpenAI 的 Point-E,我正在尝试在模型运行后减少 VRAM 的使用。运行此代码块后如何重置 VRAM:
import torch
from tqdm.auto import tqdm
from point_e.diffusion.configs import DIFFUSION_CONFIGS, diffusion_from_config
from point_e.diffusion.sampler import PointCloudSampler
from point_e.models.download import load_checkpoint
from point_e.models.configs import MODEL_CONFIGS, model_from_config
from point_e.util.plotting import plot_point_cloud
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print('creating base model...')
base_name = 'base40M-textvec'
base_model = model_from_config(MODEL_CONFIGS[base_name], device)
base_model.eval()
base_diffusion = diffusion_from_config(DIFFUSION_CONFIGS[base_name])
print('creating upsample model...')
upsampler_model = model_from_config(MODEL_CONFIGS['upsample'], device)
upsampler_model.eval()
upsampler_diffusion = diffusion_from_config(DIFFUSION_CONFIGS['upsample'])
print('downloading base checkpoint...')
base_model.load_state_dict(load_checkpoint(base_name, device))
print('downloading upsampler checkpoint...')
upsampler_model.load_state_dict(load_checkpoint('upsample', device))
sampler = PointCloudSampler(
device=device,
models=[base_model, upsampler_model],
diffusions=[base_diffusion, upsampler_diffusion],
num_points=[1024, 4096 - 1024],
aux_channels=['R', 'G', 'B'],
guidance_scale=[3.0, 0.0],
model_kwargs_key_filter=('texts', ''), # Do not condition the upsampler at all
)
# Set a prompt to condition on.
prompt = 'a red motorcycle'
# Produce a sample from the model.
samples = None
for x in tqdm(sampler.sample_batch_progressive(batch_size=1, model_kwargs=dict(texts=[prompt]))):
samples = x
pc = sampler.output_to_point_clouds(samples)[0]
fig = plot_point_cloud(pc, grid_size=3, fixed_bounds=((-0.75, -0.75, -0.75),(0.75, 0.75, 0.75)))
我试过这个,但是两个打印返回相同的值:
print(torch.cuda.memory_allocated(device))
device = None
gc.collect()
with torch.no_grad():
torch.cuda.empty_cache()
print(torch.cuda.memory_allocated(device))