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()
I have trained a network model and saved its weights and architecture via checkpoint = ModelCheckpoint(filepath='weights.hdf5') callback. During training, I am using multiple GPUs by calling the funtion below:
def make_parallel(model, gpu_count):
def get_slice(data, idx, parts):
shape = tf.shape(data)
size = tf.concat([ shape[:1] // parts, shape[1:] ],axis=0)
stride = tf.concat([ shape[:1] // parts, shape[1:]*0 ],axis=0)
start = stride * idx
return tf.slice(data, start, size)
outputs_all = []
for i in range(len(model.outputs)):
outputs_all.append([])
#Place a copy of the model on each GPU, each getting a slice of the batch
for i in range(gpu_count):
with tf.device('/gpu:%d' % i):
with tf.name_scope('tower_%d' % i) as scope:
inputs = []
#Slice each input into a piece for processing on this GPU
for x in model.inputs:
input_shape = tuple(x.get_shape().as_list())[1:]
slice_n = Lambda(get_slice, output_shape=input_shape, arguments={'idx':i,'parts':gpu_count})(x)
inputs.append(slice_n)
outputs = model(inputs)
if not isinstance(outputs, list):
outputs = [outputs]
#Save all the outputs for merging back together later
for l in range(len(outputs)):
outputs_all[l].append(outputs[l])
# merge outputs on CPU
with tf.device('/cpu:0'):
merged = []
for outputs in outputs_all:
merged.append(merge(outputs, mode='concat', concat_axis=0))
return Model(input=model.inputs, output=merged)
With the testing code:
from keras.models import Model, load_model
import numpy as np
import tensorflow as tf
model = load_model('cpm_log/deneme.hdf5')
x_test = np.random.randint(0, 255, (1, 368, 368, 3))
output = model.predict(x = x_test, batch_size=1)
print output[4].shape
I got the error below:
Traceback (most recent call last):
File "cpm_test.py", line 5, in <module>
model = load_model('cpm_log/Jun5_1000/deneme.hdf5')
File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 240, in load_model
model = model_from_config(model_config, custom_objects=custom_objects)
File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 301, in model_from_config
return layer_module.deserialize(config, custom_objects=custom_objects)
File "/usr/local/lib/python2.7/dist-packages/keras/layers/__init__.py", line 46, in deserialize
printable_module_name='layer')
File "/usr/local/lib/python2.7/dist-packages/keras/utils/generic_utils.py", line 140, in deserialize_keras_object
list(custom_objects.items())))
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 2378, in from_config
process_layer(layer_data)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 2373, in process_layer
layer(input_tensors[0], **kwargs)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 578, in __call__
output = self.call(inputs, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/keras/layers/core.py", line 659, in call
return self.function(inputs, **arguments)
File "/home/muhammed/DEV_LIBS/developments/mocap/pose_estimation/training/cpm/multi_gpu.py", line 12, in get_slice
def get_slice(data, idx, parts):
NameError: global name 'tf' is not defined
By inspecting the error output, I decide that the problem is with the parallelization code. However, I can't resolve the issue.
You may need to use custom_objects to enable loading of the model.
import tensorflow as tf
model = load_model('model.h5', custom_objects={'tf': tf,})
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")
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
I am trying to find the indices 2d max pooling in lasagne
network = batch_norm(Conv2DLayer(
network, num_filters=filter_size, filter_size=(kernel, kernel),pad=pad,
nonlinearity=lasagne.nonlinearities.rectify,
W=lasagne.init.GlorotUniform(),name="conv"), name="BN")
pool_in = lasagne.layers.get_output(network)
network = MaxPool2DLayer(network, pool_size=(pool_size, pool_size),stride=2,name="pool")
pool_out = lasagne.layers.get_output(network)
ind1 = T.grad(T.sum(pool_out), wrt=pool_in)
When I try to build the model it raises a error
DisconnectedInputError: grad method was asked to compute the gradient with respect to a variable that is not part of the computational graph of the cost, or is used only by a non-differentiable operator: Elemwise{mul,no_inplace}.0
Backtrace when the node is created:
File "//anaconda/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2871, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "//anaconda/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2975, in run_ast_nodes
if self.run_code(code, result):
File "//anaconda/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 3035, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-28-0b136cc660e2>", line 1, in <module>
network = build_model()
File "<ipython-input-27-20acc3fe0d98>", line 8, in build_model
pool_in = lasagne.layers.get_output(network)
File "//anaconda/lib/python2.7/site-packages/lasagne/layers/helper.py", line 191, in get_output
all_outputs[layer] = layer.get_output_for(layer_inputs, **kwargs)
File "//anaconda/lib/python2.7/site-packages/lasagne/layers/special.py", line 52, in get_output_for
return self.nonlinearity(input)
File "//anaconda/lib/python2.7/site-packages/lasagne/nonlinearities.py", line 157, in rectify
return theano.tensor.nnet.relu(x)
What is the right way of coding functions on lasagne layers intermediate outputs.
I had a similar problem a while ago, check out my solution for 2d and 3d max pooling indices:
Theano max_pool_3d
(Its based on the same Google-groups post, i guess)