Related
I want to use object detection using tensorflow lite in order to detect a clear face or a covered face where the statement "door opens" is printed when a clear face is detected. I could run this code smoothly previously but later after rebooting raspberry pi 4, although the tensorflow lite runtime is initialized, the raspberry pi 4 disconnects with the ssh completely. The following is the code:
######## Webcam Object Detection Using Tensorflow-trained Classifier #########
#
# Author: Evan Juras
# Date: 10/27/19
# Description:
# This program uses a TensorFlow Lite model to perform object detection on a live webcam
# feed. It draws boxes and scores around the objects of interest in each frame from the
# webcam. To improve FPS, the webcam object runs in a separate thread from the main program.
# This script will work with either a Picamera or regular USB webcam.
#
# This code is based off the TensorFlow Lite image classification example at:
# https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/examples/python/label_image.py
#
# I added my own method of drawing boxes and labels using OpenCV.
# Import packages
import os
import argparse
import cv2
import numpy as np
import sys
import time
from threading import Thread
import importlib.util
import simpleaudio as sa
# Define VideoStream class to handle streaming of video from webcam in separate processing thread
# Source - Adrian Rosebrock, PyImageSearch: https://www.pyimagesearch.com/2015/12/28/increasing-raspberry-pi-fps-with-python-and-opencv/
class VideoStream:
"""Camera object that controls video streaming from the Picamera"""
def __init__(self,resolution=(640,480),framerate=30):
# Initialize the PiCamera and the camera image stream
self.stream = cv2.VideoCapture(0)
ret = self.stream.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*'MJPG'))
ret = self.stream.set(3,resolution[0])
ret = self.stream.set(4,resolution[1])
# Read first frame from the stream
(self.grabbed, self.frame) = self.stream.read()
# Variable to control when the camera is stopped
self.stopped = False
def start(self):
# Start the thread that reads frames from the video stream
Thread(target=self.update,args=()).start()
return self
def update(self):
# Keep looping indefinitely until the thread is stopped
while True:
# If the camera is stopped, stop the thread
if self.stopped:
# Close camera resources
self.stream.release()
return
# Otherwise, grab the next frame from the stream
(self.grabbed, self.frame) = self.stream.read()
def read(self):
# Return the most recent frame
return self.frame
def stop(self):
# Indicate that the camera and thread should be stopped
self.stopped = True
# Define and parse input arguments
parser = argparse.ArgumentParser()
parser.add_argument('--modeldir', help='Folder the .tflite file is located in',
required=True)
parser.add_argument('--graph', help='Name of the .tflite file, if different than detect.tflite',
default='masktracker.tflite')
parser.add_argument('--labels', help='Name of the labelmap file, if different than labelmap.txt',
default='facelabelmap.txt')
parser.add_argument('--threshold', help='Minimum confidence threshold for displaying detected objects',
default=0.5)
parser.add_argument('--resolution', help='Desired webcam resolution in WxH. If the webcam does not support the resolution entered, errors may occur.',
default='640x480')
parser.add_argument('--edgetpu', help='Use Coral Edge TPU Accelerator to speed up detection',
action='store_true')
args = parser.parse_args()
MODEL_NAME = args.modeldir
GRAPH_NAME = args.graph
LABELMAP_NAME = args.labels
min_conf_threshold = float(args.threshold)
resW, resH = args.resolution.split('x')
imW, imH = int(resW), int(resH)
use_TPU = args.edgetpu
# Import TensorFlow libraries
# If tflite_runtime is installed, import interpreter from tflite_runtime, else import from regular tensorflow
# If using Coral Edge TPU, import the load_delegate library
pkg = importlib.util.find_spec('tflite_runtime')
if pkg:
from tflite_runtime.interpreter import Interpreter
if use_TPU:
from tflite_runtime.interpreter import load_delegate
else:
from tensorflow.lite.python.interpreter import Interpreter
if use_TPU:
from tensorflow.lite.python.interpreter import load_delegate
# If using Edge TPU, assign filename for Edge TPU model
if use_TPU:
# If user has specified the name of the .tflite file, use that name, otherwise use default 'edgetpu.tflite'
if (GRAPH_NAME == 'masktracker.tflite'):
GRAPH_NAME = 'edgetpu.tflite'
# Get path to current working directory
CWD_PATH = os.getcwd()
# Path to .tflite file, which contains the model that is used for object detection
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,GRAPH_NAME)
# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,MODEL_NAME,LABELMAP_NAME)
# Load the label map
with open(PATH_TO_LABELS, 'r') as f:
labels = [line.strip() for line in f.readlines()]
# Have to do a weird fix for label map if using the COCO "starter model" from
# https://www.tensorflow.org/lite/models/object_detection/overview
# First label is '???', which has to be removed.
if labels[0] == '???':
del(labels[0])
# Load the Tensorflow Lite model.
# If using Edge TPU, use special load_delegate argument
if use_TPU:
interpreter = Interpreter(model_path=PATH_TO_CKPT,
experimental_delegates=[load_delegate('libedgetpu.so.1.0')])
print(PATH_TO_CKPT)
else:
interpreter = Interpreter(model_path=PATH_TO_CKPT)
interpreter.allocate_tensors()
# Get model details
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
height = input_details[0]['shape'][1]
width = input_details[0]['shape'][2]
floating_model = (input_details[0]['dtype'] == np.float32)
input_mean = 127.5
input_std = 127.5
# Initialize frame rate calculation
frame_rate_calc = 1
freq = cv2.getTickFrequency()
global image_capture
image_capture = 0
# Initialize video stream
videostream = VideoStream(resolution=(imW,imH),framerate=30).start()
time.sleep(1)
#for frame1 in camera.capture_continuous(rawCapture, format="bgr",use_video_port=True):
while True:
# Start timer (for calculating frame rate)
t1 = cv2.getTickCount()
# Grab frame from video stream
frame1 = videostream.read()
# Acquire frame and resize to expected shape [1xHxWx3]
frame = frame1.copy()
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
frame_resized = cv2.resize(frame_rgb, (width, height))
input_data = np.expand_dims(frame_resized, axis=0)
# Normalize pixel values if using a floating model (i.e. if model is non-quantized)
if floating_model:
input_data = (np.float32(input_data) - input_mean) / input_std
# Perform the actual detection by running the model with the image as input
interpreter.set_tensor(input_details[0]['index'],input_data)
interpreter.invoke()
# Retrieve detection results
boxes = interpreter.get_tensor(output_details[0]['index'])[0] # Bounding box coordinates of detected objects
classes = interpreter.get_tensor(output_details[1]['index'])[0] # Class index of detected objects
scores = interpreter.get_tensor(output_details[2]['index'])[0] # Confidence of detected objects
#num = interpreter.get_tensor(output_details[3]['index'])[0] # Total number of detected objects (inaccurate and not needed)
# Loop over all detections and draw detection box if confidence is above minimum threshold
for i in range(len(scores)):
if ((scores[i] > min_conf_threshold) and (scores[i] <= 1.0)):
# Get bounding box coordinates and draw box
# Interpreter can return coordinates that are outside of image dimensions, need to force them to be within image using max() and min()
ymin = int(max(1,(boxes[i][0] * imH)))
xmin = int(max(1,(boxes[i][1] * imW)))
ymax = int(min(imH,(boxes[i][2] * imH)))
xmax = int(min(imW,(boxes[i][3] * imW)))
# Draw label
object_name = labels[int(classes[i])] # Look up object name from "labels" array using class index
if (object_name=="face unclear" ):
color = (0, 255, 0)
cv2.rectangle(frame, (xmin,ymin), (xmax,ymax),color, 2)
print("Face Covered: Door Not Opened")
if(image_capture == 0):
path = r'/home/pi/Desktop/tflite_1/photographs'
date_string = time.strftime("%Y-%m-%d_%H%M%S")
#print(date_string)
cv2.imwrite(os.path.join(path, (date_string + ".jpg")),frame)
#cv2.imshow("Photograph",frame)
#mp3File = input(alert_audio.mp3)
print("Photo Taken")
#w_object = sa.WaveObject.from_wave_file('alert_audio.wav')
#p_object = w_object.play()
#p_object.wait_done()
image_capture = 1
else:
color = (0, 0, 255)
cv2.rectangle(frame, (xmin,ymin), (xmax,ymax),color, 2)
print("Face Clear: Door Opened")
image_capture = 0
#cv2.rectangle(frame, (xmin,ymin), (xmax,ymax),color, 2)
#image = np.asarray(ImageGrab.grab())
label = '%s: %d%%' % (object_name, int(scores[i]*100)) # Example: 'person: 72%'
labelSize, baseLine = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2) # Get font size
label_ymin = max(ymin, labelSize[1] + 10) # Make sure not to draw label too close to top of window
cv2.rectangle(frame, (xmin, label_ymin-labelSize[1]-10), (xmin+labelSize[0], label_ymin+baseLine-10), (255, 255, 255), cv2.FILLED) # Draw white box to put label text in
cv2.putText(frame, label, (xmin, label_ymin-7), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 0), 2) # Draw label text
if ((scores[0] < min_conf_threshold)):
cv2.putText(frame,"No Face Detected",(260,260),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, color=(255,0,0))
print("No Face Detected")
image_capture = 0
# Draw framerate in corner of frame
cv2.putText(frame,'FPS: {0:.2f}'.format(frame_rate_calc),(30,50),cv2.FONT_HERSHEY_SIMPLEX,1,(255,255,0),2,cv2.LINE_AA)
# All the results have been drawn on the frame, so it's time to display it.
cv2.imshow('Object detector', frame)
# Calculate framerate
t2 = cv2.getTickCount()
time1 = (t2-t1)/freq
frame_rate_calc= 1/time1
# Press 'q' to quit
if cv2.waitKey(1) == ord('q'):
break
# Clean up
cv2.destroyAllWindows()
videostream.stop()
Any help is appreciated.
Regards,
MD
I am running MicroPython on a Raspberry Pi Pico. I can set the position of the servo by changing the duty cycles:
from machine import Pin, PWM
servo = PWM(Pin(0))
servo.freq(50)
servo.duty_u16(1350) # sets position to 0 degrees
I may have missed something, but I have read through the docs and couldn't find any way to read the current position of the servo. Is there any way to do this?
Most servos do not provide any sort of position information. You know what the position is because you set it. You can write code that will keep track of this value for you. For example, something like:
from machine import Pin, PWM
class Servo:
min_duty = 40
max_duty = 1115
def __init__(self, pin):
servo = PWM(Pin(pin))
servo.freq(50)
self.servo = servo
self.setpos(90)
def setpos(self, pos):
'''Scale the angular position to a value between self.min_duty
and self.max_duty.'''
if pos < 0 or pos > 180:
raise ValueError(pos)
self.pos = pos
duty = int((pos/180) * (self.max_duty - self.min_duty) + self.min_duty)
self.servo.duty(duty)
You would use the Servo class like this:
>>> s = Servo(18)
>>> s.pos
90
>>> s.setpos(180)
>>> s.pos
180
>>> s.setpos(0)
>>> s.pos
0
>>>
In your question, you have:
servo.duty_u16(1350)
I'm suspicious of this value: at 50Hz, the duty cycle is typically between 40 and 115 (+/1 some small amount at either end), corresponding to ≈ 1ms (duty=40) to 2ms (duty=115).
so I am trying to run my object detection program and I keep getting the following error message:
AssertionError: Torch not compiled with CUDA enabled.
I don't understand why this happens, as I have a 2017 MacBook Pro with an AMD GPU, so I have no CUDA enabled GPU.
I added this statement in my code to make sure the device is set to 'cpu', however, it looks as if the program keeps trying to run it through a GPU even though it does not exist.
if torch.cuda.is_available():
device = torch.device('cuda')
else:
device = torch.device('cpu')
This is the place where the error happens (4th line):
for epoch in range(num_epochs):
# train for one epoch, printing every 10 iterations
print("Hey")
train_one_epoch(model, optimizer, data_loader, device, epoch, print_freq=10)
print("Hey")
# update the learning rate
lr_scheduler.step()
# evaluate on the test dataset
evaluate(model, data_loader_test, device=device)
It would be really great, if anyone could help me with this issue!
Thanks everyone in advance!
PS: I already tried updating the Pytorch version, but still same problem.
Error output:
import os
import pandas as pd
import torch
import torch.utils.data
import torchvision
from PIL import Image
import utils
from engine import train_one_epoch, evaluate
import transforms as T
from torchvision.models.detection.faster_rcnn import FastRCNNPredictor
def parse_one_annot(path_to_data_file, filename):
data = pd.read_csv(path_to_data_file)
boxes_array = data[data["filename"] == filename][["xmin", "ymin", "xmax", "ymax"]].values
return boxes_array
class RaccoonDataset(torch.utils.data.Dataset):
def __init__(self, root, data_file, transforms=None):
self.root = root
self.transforms = transforms
self.imgs = sorted(os.listdir(os.path.join(root, "images")))
self.path_to_data_file = data_file
def __getitem__(self, idx):
# load images and bounding boxes
img_path = os.path.join(self.root, "images", self.imgs[idx])
img = Image.open(img_path).convert("RGB")
box_list = parse_one_annot(self.path_to_data_file,
self.imgs[idx])
boxes = torch.as_tensor(box_list, dtype=torch.float32)
num_objs = len(box_list)
# there is only one class
labels = torch.ones((num_objs,), dtype=torch.int64)
image_id = torch.tensor([idx])
area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])
# suppose all instances are not crowd
iscrowd = torch.zeros((num_objs,), dtype=torch.int64)
target = {}
target["boxes"] = boxes
target["labels"] = labels
target["image_id"] = image_id
target["area"] = area
target["iscrowd"] = iscrowd
if self.transforms is not None:
img, target = self.transforms(img, target)
return img, target
def __len__(self):
return len(self.imgs)
dataset = RaccoonDataset(root="./raccoon_dataset", data_file="./raccoon_dataset/data/raccoon_labels.csv")
dataset.__getitem__(0)
def get_model(num_classes):
model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
in_features = model.roi_heads.box_predictor.cls_score.in_features
# replace the pre-trained head with a new on
model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)
return model
def get_transform(train):
transforms = []
# converts the image, a PIL image, into a PyTorch Tensor
transforms.append(T.ToTensor())
if train:
# during training, randomly flip the training images
# and ground-truth for data augmentation
transforms.append(T.RandomHorizontalFlip(0.5))
return T.Compose(transforms)
def main():
dataset = RaccoonDataset(root="./raccoon_dataset",
data_file="raccoon_dataset/data/raccoon_labels.csv",
transforms=get_transform(train=True))
dataset_test = RaccoonDataset(root="./raccoon_dataset",
data_file="raccoon_dataset/data/raccoon_labels.csv",
transforms=get_transform(train=False))
torch.manual_seed(1)
indices = torch.randperm(len(dataset)).tolist()
dataset = torch.utils.data.Subset(dataset, indices[:-40])
dataset_test = torch.utils.data.Subset(dataset_test, indices[-40:])
# define training and validation data loaders
data_loader = torch.utils.data.DataLoader(dataset, batch_size=2, shuffle=True, num_workers=4,
collate_fn=utils.collate_fn)
data_loader_test = torch.utils.data.DataLoader(dataset_test, batch_size=1, shuffle=False, num_workers=4,
collate_fn=utils.collate_fn)
print("We have: {} examples, {} are training and {} testing".format(len(indices), len(dataset), len(dataset_test)))
if torch.cuda.is_available():
device = torch.device('cuda')
else:
device = torch.device('cpu')
num_classes = 2
model = get_model(num_classes)
# construct an optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params, lr=0.005, momentum=0.9, weight_decay=0.0005)
# and a learning rate scheduler which decreases the learning rate by
# 10x every 3 epochs
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=3, gamma=0.1)
# let's train it for 10 epochs
num_epochs = 10
for epoch in range(num_epochs):
# train for one epoch, printing every 10 iterations
train_one_epoch(model, optimizer, data_loader, device, epoch, print_freq=10)
# update the learning rate
lr_scheduler.step()
# evaluate on the test dataset
evaluate(model, data_loader_test, device=device)
os.mkdir("pytorch object detection/raccoon/")
torch.save(model.state_dict(), "pytorch object detection/raccoon/model")
if __name__ == '__main__':
main()
Turns out I had to reinstall torch and torch vision to make everything work
I am trying to build a neural network model with one hidden layer (1024 nodes). The hidden layer is nothing but a relu unit. I am also processing the input data in batches of 128.
The inputs are images of size 28 * 28. In the following code I get the error in line
_, c = sess.run([optimizer, loss], feed_dict={x: batch_x, y: batch_y})
Error: TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("Placeholder_64:0", shape=(128, 784), dtype=float32) is not an element of this graph.
Here is the code I have written
#Initialize
batch_size = 128
layer1_input = 28 * 28
hidden_layer1 = 1024
num_labels = 10
num_steps = 3001
#Create neural network model
def create_model(inp, w, b):
layer1 = tf.add(tf.matmul(inp, w['w1']), b['b1'])
layer1 = tf.nn.relu(layer1)
layer2 = tf.matmul(layer1, w['w2']) + b['b2']
return layer2
#Initialize variables
x = tf.placeholder(tf.float32, shape=(batch_size, layer1_input))
y = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
w = {
'w1': tf.Variable(tf.random_normal([layer1_input, hidden_layer1])),
'w2': tf.Variable(tf.random_normal([hidden_layer1, num_labels]))
}
b = {
'b1': tf.Variable(tf.zeros([hidden_layer1])),
'b2': tf.Variable(tf.zeros([num_labels]))
}
init = tf.initialize_all_variables()
train_prediction = tf.nn.softmax(model)
tf_valid_dataset = tf.constant(valid_dataset)
tf_test_dataset = tf.constant(test_dataset)
model = create_model(x, w, b)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(model, y))
optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
#Process
with tf.Session(graph=graph1) as sess:
tf.initialize_all_variables().run()
total_batch = int(train_dataset.shape[0] / batch_size)
for epoch in range(num_steps):
loss = 0
for i in range(total_batch):
batch_x, batch_y = train_dataset[epoch * batch_size:(epoch+1) * batch_size, :], train_labels[epoch * batch_size:(epoch+1) * batch_size,:]
_, c = sess.run([optimizer, loss], feed_dict={x: batch_x, y: batch_y})
loss = loss + c
loss = loss / total_batch
if epoch % 500 == 0:
print ("Epoch :", epoch, ". cost = {:.9f}".format(avg_cost))
print("Minibatch accuracy: %.1f%%" % accuracy(predictions, batch_labels))
valid_prediction = tf.run(tf_valid_dataset, {x: tf_valid_dataset})
print("Validation accuracy: %.1f%%" % accuracy(valid_prediction.eval(), valid_labels))
test_prediction = tf.run(tf_test_dataset, {x: tf_test_dataset})
print("TEST accuracy: %.1f%%" % accuracy(test_prediction.eval(), test_labels))
This worked for me
from keras import backend as K
and after predicting my data i inserted this part of code
then i had again loaded the model.
K.clear_session()
i faced this problem in production server,
but in my pc it was running fine
...........
from keras import backend as K
#Before prediction
K.clear_session()
#After prediction
K.clear_session()
Variable x is not in the same graph as model, try to define all of these in the same graph scope. For example,
# define a graph
graph1 = tf.Graph()
with graph1.as_default():
# placeholder
x = tf.placeholder(...)
y = tf.placeholder(...)
# create model
model = create(x, w, b)
with tf.Session(graph=graph1) as sess:
# initialize all the variables
sess.run(init)
# then feed_dict
# ......
If you use django server, just runserver with --nothreading
for example:
python manage.py runserver --nothreading
I had the same issue with flask. adding --without-threads flag to flask run or threaded=False to app.run() fixed it
In my case, I was using loop while calling in CNN multiple times, I fixed my problem by doing the following:
# Declare this as global:
global graph
graph = tf.get_default_graph()
# Then just before you call in your model, use this
with graph.as_default():
# call you models here
Note: In my case too, the app ran fine for the first time and then gave the error above. Using the above fix solved the problem.
Hope that helps.
The error message TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("...", dtype=dtype) is not an element of this graph can also arise in case you run a session outside of the scope of its with statement. Consider:
with tf.Session() as sess:
sess.run(logits, feed_dict=feed_dict)
sess.run(logits, feed_dict=feed_dict)
If logits and feed_dict are defined properly, the first sess.run command will execute normally, but the second will raise the mentioned error.
You can also experience this while working on notebooks hosted on online learning platforms like Coursera. So, implementing following code could help get over with the issue.
Implement this at the topmost block of Notebook file:
from keras import backend as K
K.clear_session()
Similar to #javan-peymanfard and #hmadali-shafiee, I ran into this issue when loading the model in an API. I was using FastAPI with uvicorn. To fix the issue I just set the API function definitions to async similar to this:
#app.post('/endpoint_name')
async def endpoint_function():
# Do stuff here, including possibly (re)loading the model
I have tried the following code from myHDL manual on EDAPlayground.com, but it didn't print anything out for me. Can anyone show me why ? and how to solve this ?
My configuration on the site is outlined here.
Testbench+Design : Python only
Methodology : MyHDL 0.8
from random import randrange
from myhdl import *
ACTIVE_LOW, INACTIVE_HIGH = 0, 1
def Inc(count, enable, clock, reset, n):
""" Incrementer with enable.
count -- output
enable -- control input, increment when 1
clock -- clock input
reset -- asynchronous reset input
n -- counter max value
"""
#always_seq(clock.posedge, reset=reset)
def incLogic():
if enable:
count.next = (count + 1) % n
return incLogic
def testbench():
count, enable, clock = [Signal(intbv(0)) for i in range(3)]
# Configure your reset signal here (active type, async/sync)
reset = ResetSignal(0,active=ACTIVE_LOW,async=True)
## DUT to be instantiated
inc_1 = Inc(count, enable, clock, reset, n=4)
HALF_PERIOD = delay(10)
## forever loop : clock generator
#always(HALF_PERIOD)
def clockGen():
clock.next = not clock
## Stimulus generator
#instance
def stimulus():
reset.next = ACTIVE_LOW
yield clock.negedge
reset.next = INACTIVE_HIGH
for i in range(12):
enable.next = min(1, randrange(3))
yield clock.negedge
raise StopSimulation
#instance
def monitor():
print "enable count"
yield reset.posedge
while 1:
yield clock.posedge
yield delay(1)
print " %s %s" % (enable, count)
return clockGen, stimulus, inc_1, monitor
tb = testbench()
def main():
Simulation(tb).run()
You need to call the main() function at the end.
E.g., add a line
main()
at the end, or better, use Python's idiom of
if __name__=="__main__":
main()