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

Update: brain file to use gpu #371

Merged
merged 4 commits into from Aug 4, 2022
Merged

Update: brain file to use gpu #371

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0b4f6bc
Update: brain file to use gpu
nik1806 Jun 6, 2022
227f09f
Update: device defined by config file
nik1806 Jun 13, 2022
f8d1640
Additional condition using GPU param
nik1806 Jun 20, 2022
7a02f0c
Merge branch 'JdeRobot:noetic-devel' into issue-369
nik1806 Jul 4, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
6 changes: 3 additions & 3 deletions behavior_metrics/brains/f1/brain_f1_torch.py
View file
Open in desktop
Expand Up @@ -43,8 +43,8 @@ def __init__(self, sensors, actuators, model=None, handler=None, config=None):
self.handler = handler
self.cont = 0
self.inference_times = []
self.device = torch.device("cpu")
self.gpu_inference = torch.cuda.is_available()
self.gpu_inference = config['GPU']
self.device = torch.device('cuda' if (torch.cuda.is_available() and self.gpu_inference) else 'cpu')
self.first_image = None
self.transformations = transforms.Compose([
transforms.ToTensor()
Expand Down Expand Up @@ -110,7 +110,7 @@ def execute(self):
with torch.no_grad():
image = self.transformations(img).unsqueeze(0)
image = FLOAT(image).to(self.device)
prediction = self.net(image).numpy()
prediction = self.net(image).cpu().numpy()
sergiopaniego marked this conversation as resolved.
Show resolved Hide resolved
self.inference_times.append(time.time() - start_time)
sergiopaniego marked this conversation as resolved.
Show resolved Hide resolved
# prediction_v = prediction[0][0]*6.5
prediction_v = prediction[0][0]
Expand Down
1 change: 1 addition & 0 deletions behavior_metrics/configs/DL-torch.yml
View file
Open in desktop
Expand Up @@ -21,6 +21,7 @@ Behaviors:
Parameters:
Model: 'model_pilotnet_torch_extreme.ckpt'
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The model listed here in the official repo is from last year and the predictions are not normalized. Are you using a new version that is different from that one?
You should upload that version here two if so, please.

ImageCrop: True
GPU: True
Type: 'f1'
Experiment:
Name: "Experiment name"
Expand Down