Skip to content

belief file csv output #483

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

Open
josephvanpeltkw wants to merge 6 commits into
base: master
Choose a base branch
from
Open

belief file csv output #483

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
fafc277
add new script to output the belief file csv
josephvanpeltkw Dec 20, 2024
0dd80f5
black formatting
josephvanpeltkw Dec 20, 2024
5012bd3
add gsp to the latency tracker
josephvanpeltkw Dec 26, 2024
3e99e35
black formatting changes
josephvanpeltkw Dec 26, 2024
55e21ff
add missing param to R18 yaml and add rgba support for bag extraction
josephvanpeltkw Apr 16, 2025
4ed06b7
add zed support back to docker
josephvanpeltkw Apr 16, 2025
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
42 changes: 21 additions & 21 deletions docker/workspace-build/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,31 +55,31 @@ RUN echo "source /etc/bash_completion" >> ~/.bashrc \

## Acquire and install NVIDIA CUDA 12.5
## * This is required for the ZED SDK installation.
#RUN --mount=type=cache,target=/root/nvidia,sharing=locked \
# wget https://developer.download.nvidia.com/compute/cuda/12.5.0/local_installers/cuda_12.5.0_555.42.02_linux.run \
# --no-verbose -c -O /root/nvidia/cuda_12.5.0_555.42.02_linux.run \
# && chmod +x /root/nvidia/cuda_12.5.0_555.42.02_linux.run \
# && /root/nvidia/cuda_12.5.0_555.42.02_linux.run --silent --toolkit
#ENV PATH=/usr/local/cuda-12.5/bin:${PATH}
#ENV LD_LIBRARY_PATH=/usr/local/cuda-12.5/lib64:${LD_LIBRARY_PATH}
#
RUN --mount=type=cache,target=/root/nvidia,sharing=locked \
wget https://developer.download.nvidia.com/compute/cuda/12.5.0/local_installers/cuda_12.5.0_555.42.02_linux.run \
--no-verbose -c -O /root/nvidia/cuda_12.5.0_555.42.02_linux.run \
&& chmod +x /root/nvidia/cuda_12.5.0_555.42.02_linux.run \
&& /root/nvidia/cuda_12.5.0_555.42.02_linux.run --silent --toolkit
ENV PATH=/usr/local/cuda-12.5/bin:${PATH}
ENV LD_LIBRARY_PATH=/usr/local/cuda-12.5/lib64:${LD_LIBRARY_PATH}

## Install ZED SDK and dependencies.
## We are skipping the python installation here as the pacakge version has been
## manually deduced and added to our poetry configuration to allow for its
## depedencies to be resolved along side everything else we use.
#RUN --mount=type=cache,target=/root/zed,sharing=locked \
# --mount=type=cache,target=/var/cache/apt,sharing=locked \
# --mount=type=cache,target=/var/lib/apt,sharing=locked \
# apt install zstd \
# && wget https://download.stereolabs.com/zedsdk/4.1/cu121/ubuntu20 \
# --no-verbose -c -O /root/zed/ZED_SDK_Ubuntu20_cuda12.1_v4.1.2.zstd.run \
# && chmod +x /root/zed/ZED_SDK_Ubuntu20_cuda12.1_v4.1.2.zstd.run \
# && /root/zed/ZED_SDK_Ubuntu20_cuda12.1_v4.1.2.zstd.run \
# --quiet \
# --target /root/zed/install \
# -- \
# --silent \
# --skip_python
RUN --mount=type=cache,target=/root/zed,sharing=locked \
--mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt,sharing=locked \
apt install zstd \
&& wget https://download.stereolabs.com/zedsdk/4.1/cu121/ubuntu20 \
--no-verbose -c -O /root/zed/ZED_SDK_Ubuntu20_cuda12.1_v4.1.2.zstd.run \
&& chmod +x /root/zed/ZED_SDK_Ubuntu20_cuda12.1_v4.1.2.zstd.run \
&& /root/zed/ZED_SDK_Ubuntu20_cuda12.1_v4.1.2.zstd.run \
--quiet \
--target /root/zed/install \
-- \
--silent \
--skip_python

# For the demo-ui
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
Expand Down
17 changes: 12 additions & 5 deletions ros/angel_utils/scripts/bag_extractor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,7 +130,7 @@ def __init__(self):
.string_value
)
self.pv_image_frame_id = (
self.declare_parameter("pv_image_frame_id", "PVFramesBGR")
self.declare_parameter("pv_image_frame_id", "/kitware/pv_image_detections_2d")#"PVFramesBGR")
Copy link
Member

@Purg Purg Apr 16, 2025

Choose a reason for hiding this comment

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

I would have expected this to just need to be "pv_image_detections_2d", and the namespace under which the bag play happens does appropriate namespace prepending to messages emitted?

.get_parameter_value()
.string_value
)
Expand All @@ -146,8 +146,11 @@ def __init__(self):
self.msg_type_to_handler_map = {}
if self.extract_audio:
self.msg_type_to_handler_map[HeadsetAudioData] = self.handle_audio_msg
if self.extract_images or self.extract_depth_images:
self.msg_type_to_handler_map[Image] = self.handle_image_msg
self.log.info(f"---------- images: {self.extract_images}")
#if self.extract_images or self.extract_depth_images:

self.msg_type_to_handler_map[Image] = self.handle_image_msg

if self.extract_eye_gaze_data:
self.msg_type_to_handler_map[EyeGazeData] = self.handle_eye_gaze_msg
if self.extract_head_pose_data or self.extract_depth_head_pose_data:
Expand Down Expand Up @@ -259,7 +262,7 @@ def parse_bag(self) -> None:
self.num_total_msgs += 1

if (self.num_total_msgs % 100) == 0:
self.log.info(f"Parsing message: {self.num_total_msgs}")
self.log.info(f"Parsing message: {self.num_total_msgs} type: {type(msg)}")

# Attempt to call the message handler for this message type
try:
Expand Down Expand Up @@ -561,7 +564,8 @@ def handle_image_msg(self, msg: Image) -> None:
Converts the PV images to RGB and saves them to disk.
Converts the depth images to 16-bit grayscale and saves them to disk.
"""
if msg.encoding in ["nv12", "rgb8", "bgr8"] and self.extract_images:
print(f"Image message received: {msg.encoding}")
if msg.encoding in ["nv12", "rgb8", "rgba8", "bgr8"]: # and self.extract_images:
self.num_image_msgs += 1

if msg.encoding == "nv12":
Expand All @@ -570,6 +574,9 @@ def handle_image_msg(self, msg: Image) -> None:
else:
rgb_image = bridge.imgmsg_to_cv2(msg, msg.encoding)

if "rgb" in msg.encoding:
rgb_image = cv2.cvtColor(rgb_image, cv2.COLOR_BGRA2RGBA)
Copy link
Member

@Purg Purg Apr 16, 2025

Choose a reason for hiding this comment

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

Is L575 not outputting an RGB image already when the msg.encoding is "rgb"? It looks like you're converting form "BGR" to "RGB" here, but I would have expected rgb_image to already be in RGB at this point (its just maybe missing the alpha channel?).


# Save image to disk
timestamp_str = (
f"{msg.header.stamp.sec:011d}_{msg.header.stamp.nanosec:09d}"
Expand Down
1 change: 1 addition & 0 deletions tmux/demos/medical/Kitware-R18.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,6 +119,7 @@ windows:
-p act_topic:=activity_topic
-p pose_repeat_rate:=7.5
-p window_leads_with_objects:=true
-p output_predictions_kwcoco:=${ANGEL_WORKSPACE_DIR}/stuff/activity_predictions.kwcoco
-p model_device:=0

- task_monitor:
Expand Down
Loading