Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

🐞 Fix tensor detach and gpu count issues in benchmarking script #100

Merged
merged 1 commit into from
Feb 15, 2022
Merged

🐞 Fix tensor detach and gpu count issues in benchmarking script #100

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions anomalib/utils/sweep/helpers/inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@
from typing import Dict, Iterable, List, Tuple, Union

import numpy as np
import torch
from omegaconf import DictConfig, ListConfig
from torch.utils.data import DataLoader

Expand Down Expand Up @@ -106,6 +107,7 @@ def get_torch_throughput(
Returns:
float: Inference throughput
"""
torch.set_grad_enabled(False)
model.eval()
inferencer = TorchInferencer(config, model)
torch_dataloader = MockImageLoader(config.dataset.image_size, len(test_dataset))
Expand All @@ -118,6 +120,7 @@ def get_torch_throughput(
inference_time = time.time() - start_time
throughput = len(test_dataset) / inference_time

torch.set_grad_enabled(True)
return throughput


Expand Down
5 changes: 3 additions & 2 deletions tools/benchmarking/benchmark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@


import logging
import math
import multiprocessing
import time
from concurrent.futures import ProcessPoolExecutor, as_completed
Expand Down Expand Up @@ -136,12 +137,12 @@ def distribute_over_gpus():
run_configs = list(get_run_config(sweep_config.grid_search))
jobs = []
for device_id, run_split in enumerate(
range(0, len(run_configs), len(run_configs) // torch.cuda.device_count())
range(0, len(run_configs), math.ceil(len(run_configs) / torch.cuda.device_count()))
):
jobs.append(
executor.submit(
compute_on_gpu,
run_configs[run_split : run_split + len(run_configs) // torch.cuda.device_count()],
run_configs[run_split : run_split + math.ceil(len(run_configs) / torch.cuda.device_count())],
device_id + 1,
sweep_config.seed,
sweep_config.writer,
Expand Down