How can I create an animated plot from incoming serial port data - pyserial

I want to live plot incoming data from a serial port without writing and reading data from a file. I understand that it's necessary to run a thread where the serial data is coming in on the fly. While the thread is running the animation.FuncAnimation should grab the serial data and render the plot each time.
That's where I can't figure out how to code the handover to get the animation to work.
import serial
import threading
import matplotlib.pyplot as plt
import matplotlib.animation as animation
import itertools
def thread_data_gen():
i = 0
counter = itertools.count()
ser = serial.Serial('/dev/tty.SLAB_USBtoUART', 1000000, timeout=1) # Open port and read data.
ser.reset_input_buffer() # Flush input buffer, discarding all its contents.
while True:
ser_bytes = ser.readline() # Read serial data line by line
# Incoming lines in Format -> b'$ 32079 32079 32079 32079 32079 32079 32079 32079;\r\n'
# Each value represents a data channel which can measure torque, temperatur,...
# Right now all values are set to torque which is why they have the same values.
# 8 data channels available
decoded_bytes = ser_bytes.decode('utf-8')
decoded_bytes = decoded_bytes.lstrip('$').rstrip().split()
# Re-format to ['32274', '32274', '32274', '32274', '32274', '32274', '32274', '32274;']
if i == 0:
i += 1
continue
# Skip first read-out because the first transmitted line is empty. Don't know the reason.
t = next(counter) # Create values for x-axis
y = decoded_bytes[0] # Read channel 1 values for y-axis
yield t, y # Was thinking about a generator type of return but that's not working
def run(data): # Handing over yield data from thread_data_gen()
t, y = data # TypeError:"cannot unpack non-iterable int object" I don't know how to fix this.
# I have to convert the while loop in the running thread to something where I get iterable int data.
# That's where I don't see the solution
xdata.append(t) # Adding data to list for x-values
ydata.append(y) # Adding data to list for y-values
line.set_data(xdata, ydata) # Creating data for hand-over to plt
return line,
if __name__ == '__main__':
dgen = threading.Thread(target=thread_data_gen)
dgen.start()
fig, ax = plt.subplots()
line, = ax.plot([], [], lw=2)
ax.grid()
xdata, ydata = [], []
ani = animation.FuncAnimation(fig, run, interval=100)
plt.show()
Update
I just solved my own problem with:
# A sensor upgraded coupling in a power transmission system provides data per bluetooth.
# Data: Torque, force, temperature and acceleration (x-y-z-axis).
# A hardware gateway receives the data with an antenna.
# The purpose of this code is to read and plot out serial data from that hardware gateway
# which is linked via USB-C to the laptop. A USB-C to UART software bride,
# makes the data as serial port on MacOS or Windows available.
import time
import serial
import matplotlib.pyplot as plt
import matplotlib.animation as animation
import itertools
def data_gen():
i = 0
counter = itertools.count() # Create counter
ser = serial.Serial('/dev/tty.SLAB_USBtoUART', 1000000, timeout=1) # Open port and read data.
ser.reset_input_buffer() # Flush input buffer, discarding all its contents.
while True:
# Read serial data line by line.
# Incoming lines in Format -> b'$ 32079 32079 32079 32079 32079 32079 32079 32079;\r\n'
# Each value represents a data channel which can measure torque, temperatur, ...
# Right now all values are set to torque which is why they have the same values.
# 8 data channels are available
ser_bytes = ser.readline()
decoded_bytes = ser_bytes.decode('utf-8')
# Re-format to list ['32274', '32274', '32274', '32274', '32274', '32274', '32274', '32274;']
decoded_bytes = decoded_bytes.lstrip('$').rstrip().split()
# Skip first read-out because the first transmitted line is empty. Don't know the reason.
if i == 0:
i += 1
continue
t = next(counter) # Create values for x-axis
y = decoded_bytes[0] # Read channel 1 values for y-axis
yield t, float(y) # Yield back x and y values for plot
def run(data):
x, y = data
y_cal = round(y * 0.00166, 1) #
xdata.append(x) # Adding data to list for x-values
ydata.append(y_cal) # Adding data to list for y-values
line.set_data(xdata, ydata) # Creating a data set for hand-over to plot
return line,
if __name__ == '__main__':
fig, ax = plt.subplots() # Setup figure and axis
line, = ax.plot([], [], lw=2) # Setup line
ax.set_ylim(40, 80) # Set limitation in y
ax.set_xlim(0, 1000) # Set limitation in x
ax.grid() # Create grid
xdata, ydata = [], [] # Create empty lists
# Frames: Receives the generated data from the serial connection
# Run: Provides the line data
ani = animation.FuncAnimation(fig, run, frames=data_gen, blit=True, interval=10)
plt.show()

Related

Raspberry Pi 4 Aborts SSH Connection When TensorFlow Lite Has Initialized After Running Python 3 Script

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

How to convert Holoviews graph to Bokeh 'model' in order to utilize more Bokeh features such as bokeh.models.GraphRenderer and node_renderer?

I'm trying to create a directed graph using networkx and bokeh, however, I also want to show the arrows for each out-edge. I found that the Holoviews library has the ability to add a 'directed=true' parameter to its graph constructor. However, I also want to utilize Bokeh's design features such as adjusting node color/size based on previously set node-attributes. The latter only works if I use Bokeh's from_networkx() to get a bokeh.models.renderers.GraphRender object, and then use its attributes node_renderer and edge_renderer.
The issue is when using Holoviews' renderer to specify Bokeh as the backend, it returns a bokeh.plotting.figure.Figure instead of the GraphRenderer. Ultimately, I want to be know how to be able to control the node size/color based on some attributes possible through Bokeh, and simultaneously use Holoviews to display the arrowheads on each edge.
import networkx as nx
import holoviews as hv
from holoviews import opts
hv.extension('bokeh')
from bokeh.io import show, output_file
# ... some code for I/O ...
G = nx.DiGraph(edgeList) # Directed networkx graph
# Set Node/Edge attributes to display upon hover
numConnections = {k:v for k,v in G.out_degree()}
nx.set_node_attributes(G, numConnections, name='numConnections')
# Returns Holoviews graph
hvGraph = hv.Graph.from_networkx(G, nx.spring_layout).opts(tools=['hover'], directed=True, arrowhead_length=0.01)
# Renders Holoviews graph into bokeh.plotting.figure.Figure
hvRendered = hv.render(hvGraph, 'bokeh')
output_file("out.html")
show(hvRendered)
# # The below code runs as expected using Bokeh only, and not Holoviews
# # to produce the directed graph (without arrowed edges):
# from bokeh.models import Plot, Range1d, MultiLine, Circle
# from bokeh.models import LinearColorMapper, ColorBar, BasicTicker
# import bokeh.models as bm
# from bokeh.models.graphs import from_networkx
# from bokeh.models.graphs import NodesAndLinkedEdges, EdgesAndLinkedNodes
# # Returns GraphRenderer from bokeh.models.renderers.DateRenderer
# graphRenderer = from_networkx(G, nx.spring_layout)
# mapper = LinearColorMapper(palette="Viridis256", low=76, high=0)
# # Node size/color when unselected / selected / hover
# graphRenderer.node_renderer.glyph = Circle(
# size='node_size',
# fill_color= {'field': "numConnections", "transform": mapper},
# fill_alpha=.8
# )
# graphRenderer.node_renderer.selection_glyph = Circle(
# size=25,
# fill_color=Inferno6[4]
# )
# graphRenderer.node_renderer.hover_glyph = Circle(
# size=20,
# fill_color=Inferno6[3]
# )
# # Edge size/color when unselected / selected / hover
# graphRenderer.edge_renderer.glyph = MultiLine(
# line_color="#CCCCCC",
# line_alpha=0.8,
# line_width=3
# )
# graphRenderer.edge_renderer.selection_glyph = MultiLine(
# line_color=Inferno6[4],
# line_width=4
# )
# graphRenderer.edge_renderer.hover_glyph = MultiLine(
# line_color=Inferno6[3],
# line_width=4
# )
# graphRenderer.node_renderer.data_source.data['numConnections'] = [v for k,v in
nx.get_node_attributes(G,'numConnections').items()]
# graphRenderer.selection_policy = NodesAndLinkedEdges()
# graphRenderer.inspection_policy = NodesAndLinkedEdges()
# bar = ColorBar(color_mapper=mapper, location=(0,0), title='#connections')
# # Create Bokeh Plot
# plot = Plot(
# plot_width=20,
# plot_height=20,
# x_range=Range1d(-1.1,1.1),
# y_range=Range1d(-1.1,1.1)
# )
# plot.add_tools(
# bm.HoverTool(tooltips=[("#connections", "#numConnections")]),
# bm.TapTool(),
# bm.BoxSelectTool()
# )
# plot.renderers.append(graphRenderer)
# output_file("bokeh.html")
# show(plot)
After rendering the Holoview graph into a Bokeh Figure (not a models.GraphRenderer), if I try to call the attribute node_renderer using the rendered Bokeh Figure object, it obviously throws an exception.
Traceback (most recent call last): File "holoview.py", line 106, in hvRenderedGraph.node_renderer.selection_glyph = Circle() AttributeError: 'BokehRenderer' object has no attribute 'node_renderer'
You can get the GraphRender object by following code:
from bokeh.models import GraphRenderer
gr = hvRendered.select_one(GraphRenderer)
then use gr.node_renderer and gr.edge_renderer to adjust the style.

Callbackfunction modelcheckpoint causes error in keras

I seem to get this error when I am using the callback function modelcheckpoint..
I read from a github issue that the solution would be make use of model.get_weight, but I am implicitly only storing that since i am only storing the one with best weight.
Keras only seem to save weights using h5, which make me question is there any other way to do store them using the eras API, if so how? If not, how do i store it?
Made an example to recreate the problem:
#!/usr/bin/python
import glob, os
import sys
from os import listdir
from os.path import isfile, join
import numpy as np
import warnings
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from keras.utils import np_utils
from keras import metrics
import keras
from keras import backend as K
from keras.models import Sequential
from keras.optimizers import SGD, Adam
from keras.layers.core import Dense, Activation, Lambda, Reshape,Flatten
from keras.layers import Conv1D,Conv2D,MaxPooling2D, MaxPooling1D, Reshape
#from keras.utils.visualize_util import plot
from keras.models import Model
from keras.layers import Input, Dense
from keras.layers.merge import Concatenate, Add
import h5py
import random
import tensorflow as tf
import math
from keras.callbacks import CSVLogger
from keras.callbacks import ModelCheckpoint
if len(sys.argv) < 5:
print "Missing Arguments!"
print "python keras_convolutional_feature_extraction.py <workspace> <totale_frames> <fbank-dim> <window-height> <batch_size>"
print "Example:"
print "python keras_convolutional_feature_extraction.py deltas 15 40 5 100"
sys.exit()
total_frames = int(sys.argv[2])
total_frames_with_deltas = total_frames*3
dim = int(sys.argv[3])
window_height = int(sys.argv[4])
inserted_batch_size = int(sys.argv[5])
stride = 1
splits = ((dim - window_height)+1)/stride
#input_train_data = "/media/carl/E2302E68302E443F/"+str(sys.argv[1])+"/fbank/org_train_total_frames_"+str(total_frames)+"_dim_"+str(dim)+"_winheig_"+str(window_height)+"_batch_"+str(inserted_batch_size)+"_fws_input"
#output_train_data ="/media/carl/E2302E68302E443F/"+str(sys.argv[1])+"/fbank/org_train_total_frames_"+str(total_frames)+"_dim_"+str(dim)+"_winheig_"+str(window_height)+"_batch_"+str(inserted_batch_size)+"_fws_output"
#input_test_data = "/media/carl/E2302E68302E443F/"+str(sys.argv[1])+"/fbank/org_test_total_frames_"+str(total_frames)+"_dim_"+str(dim)+"_winheig_"+str(window_height)+"_batch_"+str(1)+"_fws_input"
#output_test_data = "/media/carl/E2302E68302E443F/"+str(sys.argv[1])+"/fbank/org_test_total_frames_"+str(total_frames)+"_dim_"+str(dim)+"_winheig_"+str(window_height)+"_batch_"+str(1)+"_fws_output"
#train_files =[f for f in listdir(input_train_data) if isfile(join(input_train_data, f))]
#test_files =[f for f in listdir(input_test_data) if isfile(join(input_test_data, f))]
#print len(train_files)
np.random.seed(100)
print "hallo"
def train_generator():
while True:
# input = random.choice(train_files)
# h5f = h5py.File(input_train_data+'/'+input, 'r')
# train_input = h5f['train_input'][:]
# train_output = h5f['train_output'][:]
# h5f.close()
train_input = np.random.randint(100,size=((inserted_batch_size,splits*total_frames_with_deltas,window_height,3)))
train_list_list = []
train_input = train_input.reshape((inserted_batch_size,splits*total_frames_with_deltas,window_height,3))
train_input_list = np.split(train_input,splits*total_frames_with_deltas,axis=1)
for i in range(len(train_input_list)):
train_input_list[i] = train_input_list[i].reshape(inserted_batch_size,window_height,3)
#for i in range(len(train_input_list)):
# train_input_list[i] = train_input_list[i].reshape(inserted_batch_size,33,window_height,1,3)
train_output = np.random.randint(5, size = (1,total_frames,5))
middle = int(math.ceil(total_frames/2))
train_output = train_output[:,middle:middle+1,:].reshape((inserted_batch_size,1,5))
#print train_output.shape
#print len(train_input_list)
#print train_input_list[0].shape
yield (train_input_list, train_output)
print "hallo"
def test_generator():
while True:
# input = random.choice(test_files)
# h5f = h5py.File(input_test_data+'/'+input, 'r')
# test_input = h5f['test_input'][:]
# test_output = h5f['test_output'][:]
# h5f.close()
test_input = np.random.randint(100,size=((inserted_batch_size,splits*total_frames_with_deltas,window_height,3)))
test_input = test_input.reshape((inserted_batch_size,splits*total_frames_with_deltas,window_height,3))
test_input_list = np.split(test_input,splits*total_frames_with_deltas,axis=1)
#test_input_list = np.split(test_input,45,axis=3)
for i in range(len(test_input_list)):
test_input_list[i] = test_input_list[i].reshape(inserted_batch_size,window_height,3)
#for i in range(len(test_input_list)):
# test_input_list[i] = test_input_list[i].reshape(inserted_batch_size,33,window_height,1,3)
test_output = np.random.randint(5, size = (1,total_frames,5))
middle = int(math.ceil(total_frames/2))
test_output = test_output[:,middle:middle+1,:].reshape((inserted_batch_size,1,5))
yield (test_input_list, test_output)
print "hallo"
def fws():
#print "Inside"
# Params:
# batch , lr, decay , momentum, epochs
#
#Input shape: (batch_size,40,45,3)
#output shape: (1,15,50)
# number of unit in conv_feature_map = splitd
next(train_generator())
model_output = []
list_of_input = [Input(shape=(8,3)) for i in range(splits*total_frames_with_deltas)]
output = []
#Conv
skip = total_frames_with_deltas
for steps in range(total_frames_with_deltas):
conv = Conv1D(filters = 100, kernel_size = 8)
column = 0
for _ in range(splits):
#print "column " + str(column) + "steps: " + str(steps)
output.append(conv(list_of_input[(column*skip)+steps]))
column = column + 1
#print len(output)
#print splits*total_frames_with_deltas
conv = []
for section in range(splits):
column = 0
skip = splits
temp = []
for _ in range(total_frames_with_deltas):
temp.append(output[((column*skip)+section)])
column = column + 1
conv.append(Add()(temp))
#print len(conv)
output_conc = Concatenate()(conv)
#print output_conc.get_shape
output_conv = Reshape((splits, -1))(output_conc)
#print output_conv.get_shape
#Pool
pooled = MaxPooling1D(pool_size = 6, strides = 2)(output_conv)
reshape = Reshape((1,-1))(pooled)
#Fc
dense1 = Dense(units = 1024, activation = 'relu', name = "dense_1")(reshape)
#dense2 = Dense(units = 1024, activation = 'relu', name = "dense_2")(dense1)
dense3 = Dense(units = 1024, activation = 'relu', name = "dense_3")(dense1)
final = Dense(units = 5, activation = 'relu', name = "final")(dense3)
model = Model(inputs = list_of_input , outputs = final)
sgd = SGD(lr=0.1, decay=1e-1, momentum=0.9, nesterov=True)
model.compile(loss="categorical_crossentropy", optimizer=sgd , metrics = ['accuracy'])
print "compiled"
model_yaml = model.to_yaml()
with open("model.yaml", "w") as yaml_file:
yaml_file.write(model_yaml)
print "Model saved!"
log= CSVLogger('/home/carl/kaldi-trunk/dnn/experimental/yesno_cnn_50_training_total_frames_'+str(total_frames)+"_dim_"+str(dim)+"_window_height_"+str(window_height)+".csv")
filepath='yesno_cnn_50_training_total_frames_'+str(total_frames)+"_dim_"+str(dim)+"_window_height_"+str(window_height)+"weights-improvement-{epoch:02d}-{val_acc:.2f}.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_weights_only=True, mode='max')
print "log"
#plot_model(model, to_file='model.png')
print "Fit"
hist_current = model.fit_generator(train_generator(),
steps_per_epoch=444,#len(train_files),
epochs = 10000,
verbose = 1,
validation_data = test_generator(),
validation_steps=44,#len(test_files),
pickle_safe = True,
workers = 4,
callbacks = [log,checkpoint])
fws()
Execute the script by: python name_of_script.py yens 50 40 8 1
which give me a full traceback:
full traceback
Error:
carl#ca-ThinkPad-T420s:~/Dropbox$ python mini.py yesno 50 40 8 1
Using TensorFlow backend.
Couldn't import dot_parser, loading of dot files will not be possible.
hallo
hallo
hallo
compiled
Model saved!
log
Fit
/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py:2252: UserWarning: Expected no kwargs, you passed 1
kwargs passed to function are ignored with Tensorflow backend
warnings.warn('\n'.join(msg))
Epoch 1/10000
2017-05-26 13:01:45.851125: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-05-26 13:01:45.851345: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-05-26 13:01:45.851392: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
443/444 [============================>.] - ETA: 4s - loss: 100.1266 - acc: 0.3138Epoch 00000: saving model to yesno_cnn_50_training_total_frames_50_dim_40_window_height_8weights-improvement-00-0.48.hdf5
Traceback (most recent call last):
File "mini.py", line 205, in <module>
File "mini.py", line 203, in fws
File "/usr/local/lib/python2.7/dist-packages/keras/legacy/interfaces.py", line 88, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1933, in fit_generator
callbacks.on_epoch_end(epoch, epoch_logs)
File "/usr/local/lib/python2.7/dist-packages/keras/callbacks.py", line 77, in on_epoch_end
callback.on_epoch_end(epoch, logs)
File "/usr/local/lib/python2.7/dist-packages/keras/callbacks.py", line 411, in on_epoch_end
self.model.save_weights(filepath, overwrite=True)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 2503, in save_weights
save_weights_to_hdf5_group(f, self.layers)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 2746, in save_weights_to_hdf5_group
f.attrs['layer_names'] = [layer.name.encode('utf8') for layer in layers]
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper (/tmp/pip-4rPeHA-build/h5py/_objects.c:2684)
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper (/tmp/pip-4rPeHA-build/h5py/_objects.c:2642)
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/attrs.py", line 93, in __setitem__
self.create(name, data=value, dtype=base.guess_dtype(value))
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/attrs.py", line 183, in create
attr = h5a.create(self._id, self._e(tempname), htype, space)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper (/tmp/pip-4rPeHA-build/h5py/_objects.c:2684)
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper (/tmp/pip-4rPeHA-build/h5py/_objects.c:2642)
File "h5py/h5a.pyx", line 47, in h5py.h5a.create (/tmp/pip-4rPeHA-build/h5py/h5a.c:1904)
RuntimeError: Unable to create attribute (Object header message is too large)
If you look at the amount of data Keras is trying to save under layer_names attribute (inside the output HDF5 file being create), you will find that it takes more than 64kB.
np.asarray([layer.name.encode('utf8') for layer in model.layers]).nbytes
>> 77100
I quote from https://support.hdfgroup.org/HDF5/faq/limits.html:
Is there an object header limit and how does that affect HDF5 ?
There is a limit (in HDF5-1.8) of the object header, which is 64 KB.
The datatype for a dataset is stored in the object header, so there is
therefore a limit on the size of the datatype that you can have. (See
HDFFV-1089)
The code above was (almost entirely) copied from the traceback:
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 2746, in save_weights_to_hdf5_group
f.attrs['layer_names'] = [layer.name.encode('utf8') for layer in layers]
I am using numpy asarray method to get the figure fast but h5py gets similar figure (I guess), see https://github.com/h5py/h5py/blob/master/h5py/_hl/attrs.py#L102 if you want to find exact figure.
Anyway, either you will need to implement your own methods for saving/loading of the weights (or use existing workarounds), or you need to give a really short name to ALL the layers inside your model :), something like this:
list_of_input = [Input(shape=(8,3), name=('i%x' % i)) for i in range(splits*total_frames_with_deltas)]
conv = Conv1D(filters = 100, kernel_size = 8, name='cv%x' % steps)
conv.append(Add(name='add%x' % section)(temp))
output_conc = Concatenate(name='ct')(conv)
output_conv = Reshape((splits, -1), name='rs1')(output_conc)
pooled = MaxPooling1D(pool_size = 6, strides = 2, name='pl')(output_conv)
reshape = Reshape((1,-1), name='rs2')(pooled)
dense1 = Dense(units = 1024, activation = 'relu', name = "d1")(reshape)
dense2 = Dense(units
= 1024, activation = 'relu', name = "d2")(dense1)
dense3 = Dense(units = 1024, activation = 'relu', name = "d3")(dense1)
final = Dense(units = 5, activation = 'relu', name = "fl")(dense3)
You mustn't forget to name all the layers because the (numpy) string array into which the layer names are converted is using the size of the longest string for each individual string in it when it is saved!
After renaming the layers as proposed above (which takes almost 26kB) the model is saved successfully. Hope this elaborate answer helps someone.
Update: I have just made a PR to Keras which should fix the issue without implementing any custom loading/saving methods, see 7508
A simple solution, albeit possibly not the most elegant, could be to run a while loop with epochs = 1.
Get the weights at the end of every epoch together with the accuracy and the loss
Save the weights to file 1 with model.get_weight
if accuracy is greater than at the previous epoch (i.e. loop), store the weights to a different file (file 2)
Run the loop again loading the weights from file 1
Break the loops setting a manual early stopping so that it breaks if the loss does not improve for a certain number of loops
You can use get_weights() together with numpy.save.
It's not the best solution, because it will save several files, but it actually works.
The problem is that you won't have the "optimizer" saved with the current states. But you can perhaps work around that by using smaller learning rates after loading.
Custom callback using numpy.save:
def myCallback(epoch,logs):
global storedLoss
#do your comparisons here using the "logs" var.
print(logs)
if (logs['loss'] < storedLoss):
storedLoss = logs['loss']
for i in range(len(model.layers)):
WandB = model.layers[i].get_weights()
if len (WandB) > 0: #necessary because some layers have no weights
np.save("W" + "-" + str(i), WandB[0],False)
np.save("B" + "-" + str(i), WandB[1],False)
#remember that get and set weights use a list: [weights,biases]
#it may happen (not sure) that there is no bias, and thus you may have to check it (len(WandB)==1).
The logs var brings a dictionary with named metrics, such as "loss", and "accuracy", if you used it.
You can store the losses within the callback in a global var, and compare if each loss is better or worse than the last.
When fitting, use the lambda callback:
from keras.callbacks import LambdaCallback
model.fit(...,callbacks=[LambdaCallback(on_epoch_end=myCallback)])
In the example above, I used the LambdaCallback, which has more possibilities than just on_epoch_end.
For loading, do a similar loop:
#you have to create the model first and then set the layers
def loadModel(model):
for i in range(len(model.layers)):
WandBForCheck = model.layers[i].get_weights()
if len (WandBForCheck) > 0: #necessary because some layers have no weights
W = np.load(Wfile + str(i))
B = np.load(Bfile + str(i))
model.layers[i].set_weights([W,B])
See follow-up at https://github.com/fchollet/keras/issues/6766 and https://github.com/farizrahman4u/keras-contrib/pull/90.
I saw the YAML and the root cause is probably that you have so many Inputs. A few Inputs with many dimensions is preferred to many Inputs, especially if you can use scanning and batch operations to do everything efficiently.
Now, ignoring that entirely, here is how you can save and load your model if it has too much stuff to save as JSON efficiently:
You can pass save_weights_only=True. That won't save optimizer weights, so isn't a great solution.
Just put together a PR for saving model weights and optimizer weights but not configuration. When you want to load, first instantiate and compile the model as you did when you were going to train it, then use load_all_weights to load the model and optimizer weights into that model. I'll try to merge it soon so you can use it from the master branch.
You could use it something like this:
from keras.callbacks import LambdaCallback
from keras_contrib.utils.save_load_utils import save_all_weights, load_all_weights
# do some stuff to create and compile model
# use `save_all_weights` as a callback to checkpoint your model and optimizer weights
model.fit(..., callbacks=[LambdaCallback(on_epoch_end=lambda epoch, logs: save_all_weights(model, "checkpoint-{:05d}.h5".format(epoch))])
# use `load_all_weights` to load model and optimizer weights into an existing model
# if not compiled (no `model.optimizer`), this will just load model weights
load_all_weights(model, 'checkpoint-1337.h5')
So I don't endorse the model, but if you want to get it to save and load anyways this should probably work for you.
As a side note, if you want to save weights in a different format, something like this would work.
pickle.dump([K.get_value(w) for w in model.weights], open( "save.p", "wb" ) )
Cheers
Your model architecture must be too large to be saved.
USE get_weights AND set_weights TO SAVE AND LOAD MODEL, RESPECTIVELY.
Do not use callback model checkpoint. just once the training ends, save its weights with pickle.
Have a look at this link: Unable to save DataFrame to HDF5 ("object header message is too large")

Keras: What is the correct data format for recurrent networks?

I am trying to build a recurrent network which classifies sequences (multidimensional data streams). I must be missing something, since while running my code:
from keras.models import Sequential
from keras.layers import LSTM, Dropout, Activation
import numpy as np
ils = 10 # input layer size
ilt = 11 # input layer time steps
hls = 12 # hidden layer size
nhl = 2 # number of hidden layers
ols = 1 # output layer size
p = 0.2 # dropout probability
f_a = 'relu' # activation function
opt = 'rmsprop' # optimizing function
#
# Building the model
#
model = Sequential()
# The input layer
model.add(LSTM(hls, input_shape=(ilt, ils), return_sequences=True))
model.add(Activation(f_a))
model.add(Dropout(p))
# Hidden layers
for i in range(nhl - 1):
model.add(LSTM(hls, return_sequences=True))
model.add(Activation(f_a))
model.add(Dropout(p))
# Output layer
model.add(LSTM(ols, return_sequences=False))
model.add(Activation('softmax'))
model.compile(optimizer=opt, loss='binary_crossentropy')
#
# Making test data and fitting the model
#
m_train, n_class = 1000, 2
data = np.array(np.random.random((m_train, ilt, ils)))
labels = np.random.randint(n_class, size=(m_train, 1))
model.fit(data, labels, nb_epoch=10, batch_size=32)
I get output (truncated):
Using Theano backend.
line 611, in __call__
node = self.make_node(*inputs, **kwargs)
File "/home/koala/.local/lib/python2.7/site-packages/theano/scan_module/scan_op.py", line 430, in make_node
new_inputs.append(format(outer_seq, as_var=inner_seq))
File "/home/koala/.local/lib/python2.7/site-packages/theano/scan_module/scan_op.py", line 422, in format
rval = tmp.filter_variable(rval)
File "/home/koala/.local/lib/python2.7/site-packages/theano/tensor/type.py", line 233, in filter_variable
self=self))
TypeError: Cannot convert Type TensorType(float32, 3D) (of Variable Subtensor{:int64:}.0) into Type TensorType(float32, (False, False, True)). You can try to manually convert Subtensor{:int64:}.0 into a TensorType(float32, (False, False, True)).
Is this a problem with the data format at all.
For me the problem was fixed when I went and tried it on my real dataset. The difference being that in the real dataset I have more than 1 label. So an example of dataset on which this code works is:
(...)
ols = 2 # Output layer size
(...)
m_train, n_class = 1000, ols
data = np.array(np.random.random((m_train, ilt, ils)))
labels = np.random.randint(n_class, size=(m_train, 1))
# Make labels onehot
onehot_labels = np.zeros(shape=(labels.shape[0], ols))
onehot_labels[np.arange(labels.shape[0]), labels.astype(np.int)] = 1

XGBoost: xgb.importance feature map

I am getting the below error when I am trying to use the following code.
******Code******
importance = bst.get_fscore(fmap='xgb.fmap')
importance = sorted(importance.items(), key=operator.itemgetter(1))
******Error******
File "scripts/xgboost_bnp.py", line 225, in <module>
importance = bst.get_fscore(fmap='xgb.fmap')
File "/usr/lib/python2.7/site-packages/xgboost/core.py", line 754, in get_fscore
trees = self.get_dump(fmap)
File "/usr/lib/python2.7/site-packages/xgboost/core.py", line 740, in get_dump
ctypes.byref(sarr)))
File "/usr/lib/python2.7/site-packages/xgboost/core.py", line 92, in _check_call
raise XGBoostError(_LIB.XGBGetLastError())
xgboost.core.XGBoostError: can not open file "xgb.fmap"
The error is raised because you are calling get_fscore with an optional parameter fmap stating that feature importance of each feature should be fetched from a feature map file called xgb.fmap, which does not exist in your file system.
Here is a function returning sorted feature names and their importances:
import xgboost as xgb
import pandas as pd
def get_xgb_feat_importances(clf):
if isinstance(clf, xgb.XGBModel):
# clf has been created by calling
# xgb.XGBClassifier.fit() or xgb.XGBRegressor().fit()
fscore = clf.booster().get_fscore()
else:
# clf has been created by calling xgb.train.
# Thus, clf is an instance of xgb.Booster.
fscore = clf.get_fscore()
feat_importances = []
for ft, score in fscore.iteritems():
feat_importances.append({'Feature': ft, 'Importance': score})
feat_importances = pd.DataFrame(feat_importances)
feat_importances = feat_importances.sort_values(
by='Importance', ascending=False).reset_index(drop=True)
# Divide the importances by the sum of all importances
# to get relative importances. By using relative importances
# the sum of all importances will equal to 1, i.e.,
# np.sum(feat_importances['importance']) == 1
feat_importances['Importance'] /= feat_importances['Importance'].sum()
# Print the most important features and their importances
print feat_importances.head()
return feat_importances