I'm following the tutorial on using your own template images to do object 3D pose tracking, but I'm trying to get it working on Ubuntu 20.04 with a live webcam stream.
I was able to successfully make my index .pb file with extracted KNIFT features from my custom images.
It seems the next thing to do is load the provided template matching graph (in mediapipe/graphs/template_matching/template_matching_desktop.pbtxt) (replacing the index_proto_filename of the BoxDetectorCalculator with my own index file), and run it on a video input stream to track my custom object.
I was hoping that would be easiest to do in python, but am running into dependency problems.
(I installed mediapipe python with pip3 install mediapipe)
First, I couldn't find how to directly load a .pbtxt file as a graph in the mediapipe python API, but that's ok. I just load the text it contains and use that.
template_matching_graph_filepath=os.path.abspath("~/mediapipe/mediapipe/graphs/template_matching/template_matching_desktop.pbtxt")
graph = mp.CalculatorGraph(graph_config=open(template_matching_graph_filepath).read())
But I get missing calculator targets.
No registered object with name: OpenCvVideoDecoderCalculator; Unable to find Calculator "OpenCvVideoDecoderCalculator"
or
[libprotobuf ERROR external/com_google_protobuf/src/google/protobuf/text_format.cc:309] Error parsing text-format mediapipe.CalculatorGraphConfig: 54:70: Could not find type "type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions" stored in google.protobuf.Any.
It seems similar to this troubleshooting case but, since I'm not trying to compile an application, I'm not sure how to link in the missing calculators.
How to I make the mediapipe python API aware of these graphs?
UPDATE:
I made decent progress by adding the graphs that the template_matching depends on to the cc_library deps of the mediapipe/python/BUILD file
cc_library(
name = "builtin_calculators",
deps = [
"//mediapipe/calculators/image:feature_detector_calculator",
"//mediapipe/calculators/image:image_properties_calculator",
"//mediapipe/calculators/video:opencv_video_decoder_calculator",
"//mediapipe/calculators/video:opencv_video_encoder_calculator",
"//mediapipe/calculators/video:box_detector_calculator",
"//mediapipe/calculators/tflite:tflite_inference_calculator",
"//mediapipe/calculators/tflite:tflite_tensors_to_floats_calculator",
"//mediapipe/calculators/util:timed_box_list_id_to_label_calculator",
"//mediapipe/calculators/util:timed_box_list_to_render_data_calculator",
"//mediapipe/calculators/util:landmarks_to_render_data_calculator",
"//mediapipe/calculators/util:annotation_overlay_calculator",
...
I also modified solution_base.py so it knows about BoxDetector's options.
from mediapipe.calculators.video import box_detector_calculator_pb2
...
CALCULATOR_TO_OPTIONS = {
'BoxDetectorCalculator':
box_detector_calculator_pb2
.BoxDetectorCalculatorOptions,
Then I rebuilt and installed mediapipe python from source with:
~/mediapipe$ python3 setup.py install --link-opencv
Then I was able to make my own class derived from SolutionBase
from mediapipe.python.solution_base import SolutionBase
class ObjectTracker(SolutionBase):
"""Process a video stream and output a video with edges of templates highlighted."""
def __init__(self,
object_knift_index_file_path):
super().__init__(binary_graph_path=object_pose_estimation_binary_file_path,
calculator_params={"BoxDetector.index_proto_filename": object_knift_index_file_path},
)
def process(self, image: np.ndarray) -> NamedTuple:
return super().process(input_data={'input_video':image})
ot = ObjectTracker(object_knift_index_file_path="/path/to/my/object_knift_index.pb")
Finally, I process a video frame from a cv2.VideoCapture
cv_video = cv2.VideoCapture(0)
result, frame = cv_video.read()
input_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
res = ot.process(image=input_frame)
So close! But I run into this error which I just don't know what to do with.
/usr/local/lib/python3.8/dist-packages/mediapipe/python/solution_base.py in process(self, input_data)
326 if data.shape[2] != RGB_CHANNELS:
327 raise ValueError('Input image must contain three channel rgb data.')
--> 328 self._graph.add_packet_to_input_stream(
329 stream=stream_name,
330 packet=self._make_packet(input_stream_type,
RuntimeError: Graph has errors:
Calculator::Open() for node "BoxDetector" failed: ; Error while reading file: /usr/local/lib/python3.8/dist-packages/
Looks like CalculatorNode::OpenNode() is trying to open the python API install path as a file. Maybe it has to do with the default_context. I have no idea where to go from here. :(
I can't seem to find any documentation on how to use this model.
I am trying to use it to print out the objects that appear in a video
any help would be greatly appreciated
I am just starting out so go easy on me
I am trying to use it to print out the objects that appear in a video
I interpret that your problem is to print out the name of the found objects.
I don't know how you implemented where you got Fast RCNN trained on OpenImages v4. Therefore, I will give you the way with the model from Tensorflow Hub. Google Colab. AI Hub
After some digging around and a LOT of trial and error I came up with this
#!/home/ahmed/anaconda3/envs/TensorFlow/bin/python3.8
import tensorflow as tf
import tensorflow_hub as hub
import time,imageio,sys,pickle
# sys.argv[1] is used for taking the video path from the terminal
video = sys.argv[1]
#passing the video file to ImageIO to be read later in form of frames
video = imageio.get_reader(video)
dictionary = {}
#download and extract the model( faster_rcnn/openimages_v4/inception_resnet_v2 or
# openimages_v4/ssd/mobilenet_v2) in the same folder
module_handle = "*Path to the model folder*"
detector = hub.load(module_handle).signatures['default']
#looping over every frame in the video
for index, frames in enumerate(video):
# converting the images ( video frames ) to tf.float32 which is the only acceptable input format
image = tf.image.convert_image_dtype(frames, tf.float32)[tf.newaxis]
# passing the converted image to the model
detector_output = detector(image)
class_names = detector_output["detection_class_entities"]
scores = detector_output["detection_scores"]
# in case there are multiple objects in the frame
for i in range(len(scores)):
if scores[i] > 0.3:
#converting form bytes to string
object = class_names[i].numpy().decode("ascii")
#adding the objects that appear in the frames in a dictionary and their frame numbers
if object not in dictionary:
dictionary[object] = [index]
else:
dictionary[object].append(index)
print(dictionary)
Background
I have been playing around with Deep Dream and Inceptionism, using the Caffe framework to visualize layers of GoogLeNet, an architecture built for the Imagenet project, a large visual database designed for use in visual object recognition.
You can find Imagenet here: Imagenet 1000 Classes.
To probe into the architecture and generate 'dreams', I am using three notebooks:
https://github.com/google/deepdream/blob/master/dream.ipynb
https://github.com/kylemcdonald/deepdream/blob/master/dream.ipynb
https://github.com/auduno/deepdraw/blob/master/deepdraw.ipynb
The basic idea here is to extract some features from each channel in a specified layer from the model or a 'guide' image.
Then we input an image we wish to modify into the model and extract the features in the same layer specified (for each octave),
enhancing the best matching features, i.e., the largest dot product of the two feature vectors.
So far I've managed to modify input images and control dreams using the following approaches:
(a) applying layers as 'end' objectives for the input image optimization. (see Feature Visualization)
(b) using a second image to guide de optimization objective on the input image.
(c) visualize Googlenet model classes generated from noise.
However, the effect I want to achieve sits in-between these techniques, of which I haven't found any documentation, paper, or code.
Desired result (not part of the question to be answered)
To have one single class or unit belonging to a given 'end' layer (a) guide the optimization objective (b) and have this class visualized (c) on the input image:
An example where class = 'face' and input_image = 'clouds.jpg':
please note: the image above was generated using a model for face recognition, which was not trained on the Imagenet dataset. For demonstration purposes only.
Working code
Approach (a)
from cStringIO import StringIO
import numpy as np
import scipy.ndimage as nd
import PIL.Image
from IPython.display import clear_output, Image, display
from google.protobuf import text_format
import matplotlib as plt
import caffe
model_name = 'GoogLeNet'
model_path = 'models/dream/bvlc_googlenet/' # substitute your path here
net_fn = model_path + 'deploy.prototxt'
param_fn = model_path + 'bvlc_googlenet.caffemodel'
model = caffe.io.caffe_pb2.NetParameter()
text_format.Merge(open(net_fn).read(), model)
model.force_backward = True
open('models/dream/bvlc_googlenet/tmp.prototxt', 'w').write(str(model))
net = caffe.Classifier('models/dream/bvlc_googlenet/tmp.prototxt', param_fn,
mean = np.float32([104.0, 116.0, 122.0]), # ImageNet mean, training set dependent
channel_swap = (2,1,0)) # the reference model has channels in BGR order instead of RGB
def showarray(a, fmt='jpeg'):
a = np.uint8(np.clip(a, 0, 255))
f = StringIO()
PIL.Image.fromarray(a).save(f, fmt)
display(Image(data=f.getvalue()))
# a couple of utility functions for converting to and from Caffe's input image layout
def preprocess(net, img):
return np.float32(np.rollaxis(img, 2)[::-1]) - net.transformer.mean['data']
def deprocess(net, img):
return np.dstack((img + net.transformer.mean['data'])[::-1])
def objective_L2(dst):
dst.diff[:] = dst.data
def make_step(net, step_size=1.5, end='inception_4c/output',
jitter=32, clip=True, objective=objective_L2):
'''Basic gradient ascent step.'''
src = net.blobs['data'] # input image is stored in Net's 'data' blob
dst = net.blobs[end]
ox, oy = np.random.randint(-jitter, jitter+1, 2)
src.data[0] = np.roll(np.roll(src.data[0], ox, -1), oy, -2) # apply jitter shift
net.forward(end=end)
objective(dst) # specify the optimization objective
net.backward(start=end)
g = src.diff[0]
# apply normalized ascent step to the input image
src.data[:] += step_size/np.abs(g).mean() * g
src.data[0] = np.roll(np.roll(src.data[0], -ox, -1), -oy, -2) # unshift image
if clip:
bias = net.transformer.mean['data']
src.data[:] = np.clip(src.data, -bias, 255-bias)
def deepdream(net, base_img, iter_n=20, octave_n=4, octave_scale=1.4,
end='inception_4c/output', clip=True, **step_params):
# prepare base images for all octaves
octaves = [preprocess(net, base_img)]
for i in xrange(octave_n-1):
octaves.append(nd.zoom(octaves[-1], (1, 1.0/octave_scale,1.0/octave_scale), order=1))
src = net.blobs['data']
detail = np.zeros_like(octaves[-1]) # allocate image for network-produced details
for octave, octave_base in enumerate(octaves[::-1]):
h, w = octave_base.shape[-2:]
if octave > 0:
# upscale details from the previous octave
h1, w1 = detail.shape[-2:]
detail = nd.zoom(detail, (1, 1.0*h/h1,1.0*w/w1), order=1)
src.reshape(1,3,h,w) # resize the network's input image size
src.data[0] = octave_base+detail
for i in xrange(iter_n):
make_step(net, end=end, clip=clip, **step_params)
# visualization
vis = deprocess(net, src.data[0])
if not clip: # adjust image contrast if clipping is disabled
vis = vis*(255.0/np.percentile(vis, 99.98))
showarray(vis)
print octave, i, end, vis.shape
clear_output(wait=True)
# extract details produced on the current octave
detail = src.data[0]-octave_base
# returning the resulting image
return deprocess(net, src.data[0])
I run the code above with:
end = 'inception_4c/output'
img = np.float32(PIL.Image.open('clouds.jpg'))
_=deepdream(net, img)
Approach (b)
"""
Use one single image to guide
the optimization process.
This affects the style of generated images
without using a different training set.
"""
def dream_control_by_image(optimization_objective, end):
# this image will shape input img
guide = np.float32(PIL.Image.open(optimization_objective))
showarray(guide)
h, w = guide.shape[:2]
src, dst = net.blobs['data'], net.blobs[end]
src.reshape(1,3,h,w)
src.data[0] = preprocess(net, guide)
net.forward(end=end)
guide_features = dst.data[0].copy()
def objective_guide(dst):
x = dst.data[0].copy()
y = guide_features
ch = x.shape[0]
x = x.reshape(ch,-1)
y = y.reshape(ch,-1)
A = x.T.dot(y) # compute the matrix of dot-products with guide features
dst.diff[0].reshape(ch,-1)[:] = y[:,A.argmax(1)] # select ones that match best
_=deepdream(net, img, end=end, objective=objective_guide)
and I run the code above with:
end = 'inception_4c/output'
# image to be modified
img = np.float32(PIL.Image.open('img/clouds.jpg'))
guide_image = 'img/guide.jpg'
dream_control_by_image(guide_image, end)
Question
Now the failed approach how I tried to access individual classes, hot encoding the matrix of classes and focusing on one (so far to no avail):
def objective_class(dst, class=50):
# according to imagenet classes
#50: 'American alligator, Alligator mississipiensis',
one_hot = np.zeros_like(dst.data)
one_hot.flat[class] = 1.
dst.diff[:] = one_hot.flat[class]
To make this clear: the question is not about the dream code, which is the interesting background and which is already working code, but it is about this last paragraph's question only: Could someone please guide me on how to get images of a chosen class (take class #50: 'American alligator, Alligator mississipiensis') from ImageNet (so that I can use them as input - together with the cloud image - to create a dream image)?
The question is how to get images of the chosen class #50: 'American alligator, Alligator mississipiensis' from ImageNet.
Go to image-net.org.
Go to "Download".
Follow the instructions for "Download Image URLs":
How to download the URLs of a synset from your Brower?
1. Type a query in the Search box and click "Search" button
The alligator is not shown. ImageNet is under maintenance. Only ILSVRC synsets are included in the search results. No problem, we are fine with the similar animal "alligator lizard", since this search is about getting to the right branch of the WordNet treemap. I do not know whether you will get the direct ImageNet images here even if there were no maintenance.
2. Open a synset papge
Scrolling down:
Scrolling down:
Searching for the American alligator, which happens to be a saurian diapsid reptile as well, as a near neighbour:
3. You will find the "Download URLs" button under the left-bottom corner of the image browsing window.
You will get all of the URLs with the chosen class. A text file pops up in the browser:
http://image-net.org/api/text/imagenet.synset.geturls?wnid=n01698640
We see here that it is just about knowing the right WordNet id that needs to be put at the end of the URL.
Manual image download
The text file looks as follows:
http://farm1.static.flickr.com/136/326907154_d975d0c944.jpg
http://weeksbay.org/photo_gallery/reptiles/American20Alligator.jpg
...
till image number 1261.
As an example, the first URL links to:
And the second is a dead link:
The third link is dead, but the fourth is working.
The images of these URLs are publicly available, but many links are dead, and the pictures are of lower resolution.
Automated image download
From the ImageNet guide again:
How to download by HTTP protocol? To download a synset by HTTP
request, you need to obtain the "WordNet ID" (wnid) of a synset first.
When you use the explorer to browse a synset, you can find the WordNet
ID below the image window.(Click Here and search "Synset WordNet ID"
to find out the wnid of "Dog, domestic dog, Canis familiaris" synset).
To learn more about the "WordNet ID", please refer to
Mapping between ImageNet and WordNet
Given the wnid of a synset, the URLs of its images can be obtained at
http://www.image-net.org/api/text/imagenet.synset.geturls?wnid=[wnid]
You can also get the hyponym synsets given wnid, please refer to API
documentation to learn more.
So what is in that API documentation?
There is everything needed to get all of the WordNet IDs (so called "synset IDs") and their words for all synsets, that is, it has any class name and its WordNet ID at hand, for free.
Obtain the words of a synset
Given the wnid of a synset, the words of
the synset can be obtained at
http://www.image-net.org/api/text/wordnet.synset.getwords?wnid=[wnid]
You can also Click Here to
download the mapping between WordNet ID and words for all synsets,
Click Here to download the
mapping between WordNet ID and glosses for all synsets.
If you know the WordNet ids of choice and their class names, you can use the nltk.corpus.wordnet of "nltk" (natural language toolkit), see the WordNet interface.
In our case, we just need the images of class #50: 'American alligator, Alligator mississipiensis', we already know what we need, thus we can leave the nltk.corpus.wordnet aside (see tutorials or Stack Exchange questions for more). We can automate the download of all alligator images by looping through the URLs that are still alive. We could also widen this to the full WordNet with a loop over all WordNet IDs, of course, though this would take far too much time for the whole treemap - and is also not recommended since the images will stop being there if 1000s of people download them daily.
I am afraid I will not take the time to write this Python code that accepts the ImageNet class number "#50" as the argument, though that should be possible as well, using mapping tables from WordNet to ImageNet. Class name and WordNet ID should be enough.
For a single WordNet ID, the code could be as follows:
import urllib.request
import csv
wnid = "n01698640"
url = "http://image-net.org/api/text/imagenet.synset.geturls?wnid=" + str(wnid)
# From https://stackoverflow.com/a/45358832/6064933
req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0'})
with open(wnid + ".csv", "wb") as f:
with urllib.request.urlopen(req) as r:
f.write(r.read())
with open(wnid + ".csv", "r") as f:
counter = 1
for line in f.readlines():
print(line.strip("\n"))
failed = []
try:
with urllib.request.urlopen(line) as r2:
with open(f'''{wnid}_{counter:05}.jpg''', "wb") as f2:
f2.write(r2.read())
except:
failed.append(f'''{counter:05}, {line}'''.strip("\n"))
counter += 1
if counter == 10:
break
with open(wnid + "_failed.csv", "w", newline="") as f3:
writer = csv.writer(f3)
writer.writerow(failed)
Result:
If you need the images even behind the dead links and in original quality, and if your project is non-commercial, you can sign in, see "How do I get a copy of the images?" at the Download FAQ.
In the URL above, you see the wnid=n01698640 at the end of the URL which is the WordNet id that is mapped to ImageNet.
Or in the "Images of the Synset" tab, just click on "Wordnet IDs".
To get to:
or right-click -- save as:
You can use the WordNet id to get the original images.
If you are commercial, I would say contact the ImageNet team.
Add-on
Taking up the idea of a comment: If you do not want many images, but just the "one single class image" that represents the class as much as possible, have a look at Visualizing GoogLeNet Classes and try to use this method with the images of ImageNet instead. Which is using the deepdream code as well.
Visualizing GoogLeNet Classes
July 2015
Ever wondered what a deep neural network thinks a Dalmatian should
look like? Well, wonder no more.
Recently Google published a post describing how they managed to use
deep neural networks to generate class visualizations and modify
images through the so called “inceptionism” method. They later
published the code to modify images via the inceptionism method
yourself, however, they didn’t publish code to generate the class
visualizations they show in the same post.
While I never figured out exactly how Google generated their class
visualizations, after butchering the deepdream code and this ipython
notebook from Kyle McDonald, I managed to coach GoogLeNet into drawing
these:
... [with many other example images to follow]
The following simple python code is for detecting and tracking the object based on color by using webcam.
My question is how can use the same code but by using Kinect v2 (NOT webcam).
I am using Ubuntu 16.04, linux
Any one can help with this, and tell me how to use Kinect v2 as webcam in linux ???
import cv2
import numpy as np
cap = cv2.VideoCapture(0)
while(1):
# Take each frame
_, frame = cap.read()
# Convert BGR to HSV
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
# define range of blue color in HSV
lower_blue = np.array([110,50,50])
upper_blue = np.array([130,255,255])
# Threshold the HSV image to get only blue colors
mask = cv2.inRange(hsv, lower_blue, upper_blue)
# Bitwise-AND mask and original image
res = cv2.bitwise_and(frame,frame, mask= mask)
cv2.imshow('Original',frame)
cv2.imshow('mask',mask)
cv2.imshow('Detect-Blue',res)
k = cv2.waitKey(5) & 0xFF
if k == 27:
break
cv2.destroyAllWindows()
If you are still looking for a solution here is one. For Linux, there is an open source library called, "libfreenect2" which I have been using to grab images from Kinect2. Once you are done with the installation part then you could play with the program "Protonect.cpp" as per you needs. In the same program you could added your code after the "while" loop at line#349. It will do the job. And of course, you have to add the OpenCV header files as you are using cv2 functionalities.
By the way, I have installed the library on my laptop with Ubuntu 16.04 and Nvidia Jetson TK1 and both are working fine. In my work, I used it only to save the images and create 3D models out of it. Not doing any kind of tracking, though.
I'm discovering VTK and want to use it to plot a 3D numpy array. So far, I've managed to convert a numpy array to a vtk.Volume and displaying it but from there I am having a hard time getting something pretty.
I get a very blocky rendering like this :
and I would like a smooth rendering, so I guess either this volume but smoothed, or the surface extracted from this volume smoothed.
I've tested a bunch of vtk mappers for this volume, like SmartVolumeMapper, and played around with the Shader and the Interpolation, but did not get great results.
Here is my code (in Python) :
import vtk
import numpy as np
npa= #some 3D numpy array
[h,w,z]=npa.shape
#importing the numpy array (comes from http://www.vtk.org/Wiki/VTK/Examples/Python/vtkWithNumpy)
dataImporter = vtk.vtkImageImport()
data_string = npa.tostring()
dataImporter.CopyImportVoidPointer(data_string, len(data_string))
dataImporter.SetDataScalarTypeToUnsignedChar()
dataImporter.SetNumberOfScalarComponents(1)
dataImporter.SetDataExtent(0,z-1, 0, w-1, 0,h-1)
dataImporter.SetWholeExtent(0,z-1, 0,w-1, 0,h-1)
#Defining a transparency function
alphaChannelFunc = vtk.vtkPiecewiseFunction()
alphaChannelFunc.AddPoint(0, 0.0)
alphaChannelFunc.AddPoint(255, 1)
# Defining a color function
colorFunc = vtk.vtkColorTransferFunction()
colorFunc.AddRGBPoint(255, 1.0, 1.0, 1.0)
colorFunc.AddRGBPoint(128, 0.0, 0, 1.0)
#Creating the volume
volumeProperty = vtk.vtkVolumeProperty()
volumeProperty.SetColor(colorFunc)
volumeProperty.SetScalarOpacity(alphaChannelFunc)
volumeProperty.ShadeOn()
volumeProperty.SetInterpolationTypeToLinear()
#Creating the mapper
compositeFunction = vtk.vtkVolumeRayCastCompositeFunction()
volumeMapper = vtk.vtkVolumeRayCastMapper()
volumeMapper.SetVolumeRayCastFunction(compositeFunction)
volumeMapper.SetInputConnection(dataImporter.GetOutputPort())
#Creating the volume actor
volume = vtk.vtkVolume()
volume.SetMapper(volumeMapper)
volume.SetProperty(volumeProperty)
#Creating the renderer
renderer = vtk.vtkRenderer()
renderWin = vtk.vtkRenderWindow()
renderWin.AddRenderer(renderer)
renderInteractor = vtk.vtkRenderWindowInteractor()
renderInteractor.SetRenderWindow(renderWin)
#Adding the actor
renderer.AddVolume(volume)
renderer.SetBackground(0, 0, 0)
renderWin.SetSize(400, 400)
#Launching the renderer
renderInteractor.Initialize()
renderWin.Render()
renderInteractor.Start()
I get the impression that a Volume actor is not the way to go to get something pretty, maybe I should go for a PolyData or something ? I went through the Marching Cubes example (in C++) which seems to take a volume and extract a surface out of it, but I can't get it to work for the moment (no errors but output is a completely white buggy window which won't close).
I could dive more into it to try and get it to work but first I would like to get input from you guys, since I'm a beginner in VTK and maybe I'm handling this all wrong.
I'm using Python 2.7.12 and vtk 5.10.1 on Ubuntu 14.