Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.1
• TensorRT Version 8.2
• NVIDIA GPU Driver Version (valid for GPU only) 510.73.05, cuda: 11.6
I have trained a custom pytorch model on 17 classes:
colab link
I am using deepstream test app2 and I am using a detector and a classifier only, the classifier is not working fine, as I can see it the classifier_meta_data is always none
My SGIE:
[property]
gpu-id=0
net-scale-factor=0.0174292
offsets=123.675;116.28;103.53
onnx-file=model/resnet18.onnx
labelfile-path=model/labels.txt
batch-size=1
model-color-format=0
process-mode=2
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=2
is-classifier=1
num-detected-classes=17
interval=0
gie-unique-id=2
model-engine-file=pose_estimation.onnx_b1_gpu0_fp16.engine
network-type=100
workspace-size=3000
operate-on-gie-id=1 #use the classifier if the box comes the pgie id 1
operate-on-class-ids=0 #detect the classification for cars
maintain-aspect-ratio=1
classifier-async-mode=1
classifier-threshold=0.01
Python Script:
#!/usr/bin/env python3
################################################################################
# SPDX-FileCopyrightText: Copyright (c) 2019-2021 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
################################################################################
import sys
sys.path.append('../')
import platform
import configparser
import os
import gi
gi.require_version('Gst', '1.0')
from gi.repository import GLib, Gst
from common.is_aarch_64 import is_aarch64
from common.bus_call import bus_call
# location = os.getcwd() + "/src/ros2_deepstream/config_files/"
class_obj = 'Car;Bicycle;Person;Roadsign'.split(';')
# class_color = 'black;blue;brown;gold;green;grey;maroon;orange;red;silver;white;yellow'.split(';')
# class_make = 'acura;audi;bmw;chevrolet;chrysler;dodge;ford;gmc;honda;hyundai;infiniti;jeep;kia;lexus;mazda;mercedes;nissan;subaru;toyota;volkswagen'.split(';')
# class_type = 'coupe;largevehicle;sedan;suv;truck;van'.split(';')
class_type = 'Ambulance;Barge;Bicycle;Boat;Bus;Car;Cart;Caterpillar;Helicopter;Limousine;Motorcycle;Segway;Snowmobile;Tank;Taxi;Truck;Van'.split(';')
import pyds
PGIE_CLASS_ID_VEHICLE = 0
PGIE_CLASS_ID_BICYCLE = 1
PGIE_CLASS_ID_PERSON = 2
PGIE_CLASS_ID_ROADSIGN = 3
past_tracking_meta=[0]
def osd_sink_pad_buffer_probe(pad,info,u_data):
frame_number=0
#Intiallizing object counter with 0.
obj_counter = {
PGIE_CLASS_ID_VEHICLE:0,
PGIE_CLASS_ID_PERSON:0,
PGIE_CLASS_ID_BICYCLE:0,
PGIE_CLASS_ID_ROADSIGN:0
}
num_rects=0
gst_buffer = info.get_buffer()
if not gst_buffer:
print("Unable to get GstBuffer ")
return
# Retrieve batch metadata from the gst_buffer
# Note that pyds.gst_buffer_get_nvds_batch_meta() expects the
# C address of gst_buffer as input, which is obtained with hash(gst_buffer)
batch_meta = pyds.gst_buffer_get_nvds_batch_meta(hash(gst_buffer))
l_frame = batch_meta.frame_meta_list
while l_frame is not None:
try:
# Note that l_frame.data needs a cast to pyds.NvDsFrameMeta
# The casting is done by pyds.NvDsFrameMeta.cast()
# The casting also keeps ownership of the underlying memory
# in the C code, so the Python garbage collector will leave
# it alone.
frame_meta = pyds.NvDsFrameMeta.cast(l_frame.data)
except StopIteration:
break
frame_number=frame_meta.frame_num
num_rects = frame_meta.num_obj_meta
l_obj=frame_meta.obj_meta_list
while l_obj is not None:
try:
# Casting l_obj.data to pyds.NvDsObjectMeta
obj_meta=pyds.NvDsObjectMeta.cast(l_obj.data)
l_classifier = obj_meta.classifier_meta_list
# print(l_classifier)
# If object is a car (class ID 0), perform attribute classification
if obj_meta.class_id == 0 and l_classifier is not None:
# Creating and publishing message with output of classification inference
# msg2 = Classification2D()
while l_classifier is not None:
# result = ObjectHypothesis()
try:
classifier_meta = pyds.glist_get_nvds_classifier_meta(l_classifier.data)
except StopIteration:
print('Could not parse MetaData: ')
break
classifier_id = classifier_meta.unique_component_id
l_label = classifier_meta.label_info_list
label_info = pyds.glist_get_nvds_label_info(l_label.data)
classifier_class = label_info.result_class_id
# print("Classifier ID: ", classifier_id)
# print("Classifier Class: ", classifier_class)
# if classifier_id == 2: print('colour :', class_color[classifier_class])
if classifier_id == 2: print('Type -- :', class_color[classifier_class])
elif classifier_id == 3: print('maker:', class_make[classifier_class])
else: print('type:', class_type[classifier_class])
# if classifier_id == 2:
# result.id = class_color[classifier_class]
# elif classifier_id == 3:
# result.id = class_make[classifier_class]
# else:
# result.id = class_type[classifier_class]
# result.score = label_info.result_prob
# msg2.results.append(result)
l_classifier = l_classifier.next
# print('the result is ', result)
# self.publisher_classification.publish(msg2)
except StopIteration:
break
obj_counter[obj_meta.class_id] += 1
try:
l_obj=l_obj.next
except StopIteration:
break
# Acquiring a display meta object. The memory ownership remains in
# the C code so downstream plugins can still access it. Otherwise
# the garbage collector will claim it when this probe function exits.
display_meta=pyds.nvds_acquire_display_meta_from_pool(batch_meta)
display_meta.num_labels = 1
py_nvosd_text_params = display_meta.text_params[0]
# Setting display text to be shown on screen
# Note that the pyds module allocates a buffer for the string, and the
# memory will not be claimed by the garbage collector.
# Reading the display_text field here will return the C address of the
# allocated string. Use pyds.get_string() to get the string content.
py_nvosd_text_params.display_text = "Frame Number={} Number of Objects={} Vehicle_count={} Person_count={}".format(frame_number, num_rects, obj_counter[PGIE_CLASS_ID_VEHICLE], obj_counter[PGIE_CLASS_ID_PERSON])
# Now set the offsets where the string should appear
py_nvosd_text_params.x_offset = 10
py_nvosd_text_params.y_offset = 12
# Font , font-color and font-size
py_nvosd_text_params.font_params.font_name = "Serif"
py_nvosd_text_params.font_params.font_size = 10
# set(red, green, blue, alpha); set to White
py_nvosd_text_params.font_params.font_color.set(1.0, 1.0, 1.0, 1.0)
# Text background color
py_nvosd_text_params.set_bg_clr = 1
# set(red, green, blue, alpha); set to Black
py_nvosd_text_params.text_bg_clr.set(0.0, 0.0, 0.0, 1.0)
# Using pyds.get_string() to get display_text as string
print(pyds.get_string(py_nvosd_text_params.display_text))
pyds.nvds_add_display_meta_to_frame(frame_meta, display_meta)
try:
l_frame=l_frame.next
except StopIteration:
break
#past traking meta data
if(past_tracking_meta[0]==1):
l_user=batch_meta.batch_user_meta_list
while l_user is not None:
try:
# Note that l_user.data needs a cast to pyds.NvDsUserMeta
# The casting is done by pyds.NvDsUserMeta.cast()
# The casting also keeps ownership of the underlying memory
# in the C code, so the Python garbage collector will leave
# it alone
user_meta=pyds.NvDsUserMeta.cast(l_user.data)
except StopIteration:
break
if(user_meta and user_meta.base_meta.meta_type==pyds.NvDsMetaType.NVDS_TRACKER_PAST_FRAME_META):
try:
# Note that user_meta.user_meta_data needs a cast to pyds.NvDsPastFrameObjBatch
# The casting is done by pyds.NvDsPastFrameObjBatch.cast()
# The casting also keeps ownership of the underlying memory
# in the C code, so the Python garbage collector will leave
# it alone
pPastFrameObjBatch = pyds.NvDsPastFrameObjBatch.cast(user_meta.user_meta_data)
except StopIteration:
break
for trackobj in pyds.NvDsPastFrameObjBatch.list(pPastFrameObjBatch):
print("streamId=",trackobj.streamID)
print("surfaceStreamID=",trackobj.surfaceStreamID)
for pastframeobj in pyds.NvDsPastFrameObjStream.list(trackobj):
print("numobj=",pastframeobj.numObj)
print("uniqueId=",pastframeobj.uniqueId)
print("classId=",pastframeobj.classId)
print("objLabel=",pastframeobj.objLabel)
for objlist in pyds.NvDsPastFrameObjList.list(pastframeobj):
print('frameNum:', objlist.frameNum)
print('tBbox.left:', objlist.tBbox.left)
print('tBbox.width:', objlist.tBbox.width)
print('tBbox.top:', objlist.tBbox.top)
print('tBbox.right:', objlist.tBbox.height)
print('confidence:', objlist.confidence)
print('age:', objlist.age)
try:
l_user=l_user.next
except StopIteration:
break
return Gst.PadProbeReturn.OK
def main(args):
# Check input arguments
if(len(args)<2):
sys.stderr.write("usage: %s <h264_elementary_stream> [0/1]\n" % args[0])
sys.exit(1)
# Standard GStreamer initialization
if(len(args)==3):
past_tracking_meta[0]=int(args[2])
Gst.init(None)
# Create gstreamer elements
# Create Pipeline element that will form a connection of other elements
print("Creating Pipeline \n ")
pipeline = Gst.Pipeline()
if not pipeline:
sys.stderr.write(" Unable to create Pipeline \n")
# Source element for reading from the file
print("Creating Source \n ")
source = Gst.ElementFactory.make("filesrc", "file-source")
if not source:
sys.stderr.write(" Unable to create Source \n")
# Since the data format in the input file is elementary h264 stream,
# we need a h264parser
print("Creating H264Parser \n")
h264parser = Gst.ElementFactory.make("h264parse", "h264-parser")
if not h264parser:
sys.stderr.write(" Unable to create h264 parser \n")
# Use nvdec_h264 for hardware accelerated decode on GPU
print("Creating Decoder \n")
decoder = Gst.ElementFactory.make("nvv4l2decoder", "nvv4l2-decoder")
if not decoder:
sys.stderr.write(" Unable to create Nvv4l2 Decoder \n")
# Create nvstreammux instance to form batches from one or more sources.
streammux = Gst.ElementFactory.make("nvstreammux", "Stream-muxer")
if not streammux:
sys.stderr.write(" Unable to create NvStreamMux \n")
# Use nvinfer to run inferencing on decoder's output,
# behaviour of inferencing is set through config file
pgie = Gst.ElementFactory.make("nvinfer", "primary-inference")
if not pgie:
sys.stderr.write(" Unable to create pgie \n")
tracker = Gst.ElementFactory.make("nvtracker", "tracker")
if not tracker:
sys.stderr.write(" Unable to create tracker \n")
sgie1 = Gst.ElementFactory.make("nvinfer", "secondary1-nvinference-engine")
if not sgie1:
sys.stderr.write(" Unable to make sgie1 \n")
sgie2 = Gst.ElementFactory.make("nvinfer", "secondary2-nvinference-engine")
if not sgie2:
sys.stderr.write(" Unable to make sgie2 \n")
sgie3 = Gst.ElementFactory.make("nvinfer", "secondary3-nvinference-engine")
if not sgie3:
sys.stderr.write(" Unable to make sgie3 \n")
nvvidconv = Gst.ElementFactory.make("nvvideoconvert", "convertor")
if not nvvidconv:
sys.stderr.write(" Unable to create nvvidconv \n")
# Create OSD to draw on the converted RGBA buffer
nvosd = Gst.ElementFactory.make("nvdsosd", "onscreendisplay")
if not nvosd:
sys.stderr.write(" Unable to create nvosd \n")
# Finally render the osd output
if is_aarch64():
transform = Gst.ElementFactory.make("nvegltransform", "nvegl-transform")
print("Creating EGLSink \n")
sink = Gst.ElementFactory.make("fakesink", "fakesink")
if not sink:
sys.stderr.write(" Unable to create egl sink \n")
print("Playing file %s " %args[1])
source.set_property('location', args[1])
streammux.set_property('width', 1920)
streammux.set_property('height', 1080)
streammux.set_property('batch-size', 1)
streammux.set_property('batched-push-timeout', 4000000)
#Set properties of pgie and sgie
pgie.set_property('config-file-path', "dstest2_pgie_config.txt")
# sgie1.set_property('config-file-path', "dstest2_sgie1_config.txt")
# sgie2.set_property('config-file-path', "dstest2_sgie2_config.txt")
# sgie3.set_property('config-file-path', "dstest2_sgie3_config.txt")
sgie1.set_property('config-file-path', "customsgie.txt")
#Set properties of tracker
config = configparser.ConfigParser()
config.read('dstest2_tracker_config.txt')
config.sections()
for key in config['tracker']:
if key == 'tracker-width' :
tracker_width = config.getint('tracker', key)
tracker.set_property('tracker-width', tracker_width)
if key == 'tracker-height' :
tracker_height = config.getint('tracker', key)
tracker.set_property('tracker-height', tracker_height)
if key == 'gpu-id' :
tracker_gpu_id = config.getint('tracker', key)
tracker.set_property('gpu_id', tracker_gpu_id)
if key == 'll-lib-file' :
tracker_ll_lib_file = config.get('tracker', key)
tracker.set_property('ll-lib-file', tracker_ll_lib_file)
if key == 'll-config-file' :
tracker_ll_config_file = config.get('tracker', key)
tracker.set_property('ll-config-file', tracker_ll_config_file)
if key == 'enable-batch-process' :
tracker_enable_batch_process = config.getint('tracker', key)
tracker.set_property('enable_batch_process', tracker_enable_batch_process)
if key == 'enable-past-frame' :
tracker_enable_past_frame = config.getint('tracker', key)
tracker.set_property('enable_past_frame', tracker_enable_past_frame)
print("Adding elements to Pipeline \n")
pipeline.add(source)
pipeline.add(h264parser)
pipeline.add(decoder)
pipeline.add(streammux)
pipeline.add(pgie)
pipeline.add(tracker)
pipeline.add(sgie1)
# pipeline.add(sgie2)
# pipeline.add(sgie3)
pipeline.add(nvvidconv)
pipeline.add(nvosd)
pipeline.add(sink)
if is_aarch64():
pipeline.add(transform)
# we link the elements together
# file-source -> h264-parser -> nvh264-decoder ->
# nvinfer -> nvvidconv -> nvosd -> video-renderer
print("Linking elements in the Pipeline \n")
source.link(h264parser)
h264parser.link(decoder)
sinkpad = streammux.get_request_pad("sink_0")
if not sinkpad:
sys.stderr.write(" Unable to get the sink pad of streammux \n")
srcpad = decoder.get_static_pad("src")
if not srcpad:
sys.stderr.write(" Unable to get source pad of decoder \n")
srcpad.link(sinkpad)
streammux.link(pgie)
pgie.link(tracker)
tracker.link(sgie1)
# sgie1.link(sgie2)
# sgie2.link(sgie3)
# sgie3.link(nvvidconv)
sgie1.link(nvvidconv)
nvvidconv.link(nvosd)
if is_aarch64():
nvosd.link(transform)
transform.link(sink)
else:
nvosd.link(sink)
# create and event loop and feed gstreamer bus mesages to it
loop = GLib.MainLoop()
bus = pipeline.get_bus()
bus.add_signal_watch()
bus.connect ("message", bus_call, loop)
# Lets add probe to get informed of the meta data generated, we add probe to
# the sink pad of the osd element, since by that time, the buffer would have
# had got all the metadata.
osdsinkpad = nvosd.get_static_pad("sink")
if not osdsinkpad:
sys.stderr.write(" Unable to get sink pad of nvosd \n")
osdsinkpad.add_probe(Gst.PadProbeType.BUFFER, osd_sink_pad_buffer_probe, 0)
print("Starting pipeline \n")
# start play back and listed to events
pipeline.set_state(Gst.State.PLAYING)
try:
loop.run()
except:
pass
# cleanup
pipeline.set_state(Gst.State.NULL)
if __name__ == '__main__':
sys.exit(main(sys.argv))
The ONNX file I made:
resnet18.onnx (21.3 MB)
labels.txt:
Ambulance;Barge;Bicycle;Boat;Bus;Car;Cart;Caterpillar;Helicopter;Limousine;Motorcycle;Segway;Snowmobile;Tank;Taxi;Truck;Van
@yuweiw can you tell me where I am doing wrong and what parameter I have to update if necessary?