Related
Doing a final project for my school and need help because I'm not sure how to execute it.
I'm investigating how image distortion will affect ANN's learning ability. Have no background in coding whatsoever so any help will be hugely appreciated! Can't use TensorFlow as part of requirements.
This is what my prof used for network classification which is standard from the textbook we're using.
# neural network class definition
class neuralNetwork:
# initialise the neural network
def __init__(self, inputnodes, hiddennodes, outputnodes, learningrate):
# set number of nodes in each input, hidden, output layer
self.inodes = inputnodes
self.hnodes = hiddennodes
self.onodes = outputnodes
self.wih = numpy.random.normal(0.0, pow(self.inodes, -0.5), (self.hnodes, self.inodes))
self.who = numpy.random.normal(0.0, pow(self.hnodes, -0.5), (self.onodes, self.hnodes))
self.lr = learningrate
self.activation_function = lambda x: scipy.special.expit(x)
pass
# train the neural network
def train(self, inputs_list, targets_list):
inputs = numpy.array(inputs_list, ndmin=2).T
targets = numpy.array(targets_list, ndmin=2).T
hidden_inputs = numpy.dot(self.wih, inputs)
hidden_outputs = self.activation_function(hidden_inputs)
final_inputs = numpy.dot(self.who, hidden_outputs)
final_outputs = self.activation_function(final_inputs)
output_errors = targets - final_outputs
hidden_errors = numpy.dot(self.who.T, output_errors)
self.who += self.lr * numpy.dot((output_errors * final_outputs * (1.0 - final_outputs)), numpy.transpose(hidden_outputs))
self.wih += self.lr * numpy.dot((hidden_errors * hidden_outputs * (1.0 - hidden_outputs)), numpy.transpose(inputs))
pass
# query the neural network
def query(self, inputs_list):
inputs = numpy.array(inputs_list, ndmin=2).T
hidden_inputs = numpy.dot(self.wih, inputs)
hidden_outputs = self.activation_function(hidden_inputs)
final_inputs = numpy.dot(self.who, hidden_outputs)
final_outputs = self.activation_function(final_inputs)
return final_outputs
# number of input, hidden and output nodes
input_nodes = 784
hidden_nodes = 200
output_nodes = 10
learning_rate = 0.1
# create instance of neural network
n = neuralNetwork(input_nodes,hidden_nodes,output_nodes, learning_rate)
# load the mnist training data CSV file into a list
training_data_file = open("mnist_train.csv", 'r')
training_data_list = training_data_file.readlines()
training_data_file.close()
# train the neural network
epochs = 5
for e in range(epochs):
for record in training_data_list:
all_values = record.split(',')
inputs = (numpy.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
targets = numpy.zeros(output_nodes) + 0.01
targets[int(all_values[0])] = 0.99
n.train(inputs, targets)
pass
pass
# load the mnist test data CSV file into a list
test_data_file = open("mnist_test.csv", 'r')
test_data_list = test_data_file.readlines()
test_data_file.close()
# test the neural network
# scorecard for how well the network performs, initially empty
scorecard = []
for record in test_data_list:
all_values = record.split(',')
correct_label = int(all_values[0])
inputs = (numpy.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
outputs = n.query(inputs)
label = numpy.argmax(outputs)
if (label == correct_label):
scorecard.append(1)
else:
scorecard.append(0)
pass
pass
# calculate the performance score, the fraction of correct answers
scorecard_array = numpy.asarray(scorecard)
print ("performance = ", scorecard_array.sum() / scorecard_array.size)
So I came up with a sharpening kernel and basically what I want to accomplish is to apply this kernel to the network so that the images in the training dataset is now 'sharpened'. (Also am using the convolution method given by my prof) Where am I supposed to add this to the class above??
sharpen_kernel = np.array([[0, -1, 0],
[-1, 5, -1],
[0, -1, 0]])
# convolve your image with the kernel
matplotlib.rcParams['figure.figsize'] = 20,20
conv_image = numpy.ones((28,28))
print("shape of image_array",numpy.shape(image_array))
step = 3
i=0
while i < 25:
i+=1
j = 0
while j < 25 :
sub_image = image_array[i:(i+step),j:(j+step):] # array[starty : endy , start x : end x : step]
sub_image = numpy.reshape(sub_image,(1,(step ** 2)))
kernel = numpy.reshape(sharpen_kernel, ((step ** 2),1))
conv_scalar = numpy.dot(sub_image,kernel)
conv_image[i,j] = conv_scalar
j+=1
pass
pass
Basically want to measure the relationship of the performance of ANN and quality of image (e.g. blur, sharpening). Help!
Python version: 3.8
Pytorch version: 1.9.0+cpu
Platform: Anaconda Spyder5.0
To reproduce this problem, just copy every code below to a single file.
The ILSVRC2012_val_00000293.jpg file used in this code is shown below, you also need to download it and then change its destination in the code.
Some background of this problem:
I am now working on a project that aims to develop a hardware accelerator to complete the inference process of the MobileNet V2 network. I used pretrained quantized Pytorch model to simulate the outcome, and the result comes out very well.
In order to use hardware to complete this task, I wish to know every inputs and outputs as well as intermidiate variables during runing this piece of pytorch code. I used a package named torchextractor to fetch the outcomes of first layer, which in this case, is a 3*3 convolution layer.
import numpy as np
import torchvision
import torch
from torchvision import transforms, datasets
from PIL import Image
from torchvision import transforms
import torchextractor as tx
import math
#########################################################################################
##### Processing of input image
#########################################################################################
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
test_transform = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize,])
preprocess = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
#image file destination
filename = "D:\Project_UM\MobileNet_VC709\MobileNet_pytorch\ILSVRC2012_val_00000293.jpg"
input_image = Image.open(filename)
input_tensor = preprocess(input_image)
input_batch = input_tensor.unsqueeze(0)
#########################################################################################
#########################################################################################
#########################################################################################
#----First verify that the torchextractor class should not influent the inference outcome
# ofmp of layer1 before putting into torchextractor
a,b,c = quantize_tensor(input_batch)# to quantize the input tensor and return an int8 tensor, scale and zero point
input_qa = torch.quantize_per_tensor(torch.tensor(input_batch.clone().detach()), b, c, torch.quint8)# Using quantize_per_tensor method of torch
# Load a quantized mobilenet_v2 model
model_quantized = torchvision.models.quantization.mobilenet_v2(pretrained=True, quantize=True)
model_quantized.eval()
with torch.no_grad():
output = model_quantized.features[0][0](input_qa)# Ofmp of layer1, datatype : quantized_tensor
# print("FM of layer1 before tx_extractor:\n",output.int_repr())# Ofmp of layer1, datatype : int8 tensor
output1_clone = output.int_repr().detach().numpy()# Clone ofmp of layer1, datatype : ndarray
#########################################################################################
#########################################################################################
#########################################################################################
# ofmp of layer1 after adding torchextractor
model_quantized_ex = tx.Extractor(model_quantized, ["features.0.0"])#Capture of the module inside first layer
model_output, features = model_quantized_ex(input_batch)# Forward propagation
# feature_shapes = {name: f.shape for name, f in features.items()}
# print(features['features.0.0']) # Ofmp of layer1, datatype : quantized_tensor
out1_clone = features['features.0.0'].int_repr().numpy() # Clone ofmp of layer1, datatype : ndarray
if(out1_clone.all() == output1_clone.all()):
print('Model with torchextractor attached output the same value as the original model')
else:
print('Torchextractor method influence the outcome')
Here I define a numpy quantization scheme based on the quantization scheme proposed by
Quantization and Training of Neural Networks for Efficient
Integer-Arithmetic-Only Inference
# Convert a normal regular tensor to a quantized tensor with scale and zero_point
def quantize_tensor(x, num_bits=8):# to quantize the input tensor and return an int8 tensor, scale and zero point
qmin = 0.
qmax = 2.**num_bits - 1.
min_val, max_val = x.min(), x.max()
scale = (max_val - min_val) / (qmax - qmin)
initial_zero_point = qmin - min_val / scale
zero_point = 0
if initial_zero_point < qmin:
zero_point = qmin
elif initial_zero_point > qmax:
zero_point = qmax
else:
zero_point = initial_zero_point
# print(zero_point)
zero_point = int(zero_point)
q_x = zero_point + x / scale
q_x.clamp_(qmin, qmax).round_()
q_x = q_x.round().byte()
return q_x, scale, zero_point
#%%
# #############################################################################################
# --------- Simulate the inference process of layer0: conv33 using numpy
# #############################################################################################
# get the input_batch quantized buffer data
input_scale = b.item()
input_zero = c
input_quantized = a[0].detach().numpy()
# get the layer0 output scale and zero_point
output_scale = model_quantized.features[0][0].state_dict()['scale'].item()
output_zero = model_quantized.features[0][0].state_dict()['zero_point'].item()
# get the quantized weight with scale and zero_point
weight_scale = model_quantized.features[0][0].state_dict()["weight"].q_scale()
weight_zero = model_quantized.features[0][0].state_dict()["weight"].q_zero_point()
weight_quantized = model_quantized.features[0][0].state_dict()["weight"].int_repr().numpy()
# print(weight_quantized)
# print(weight_quantized.shape)
# bias_quantized,bias_scale,bias_zero= quantize_tensor(model_quantized.features[0][0].state_dict()["bias"])# to quantize the input tensor and return an int8 tensor, scale and zero point
# print(bias_quantized.shape)
bias = model_quantized.features[0][0].state_dict()["bias"].detach().numpy()
# print(input_quantized)
print(type(input_scale))
print(type(output_scale))
print(type(weight_scale))
Then I write a quantized 2D convolution using numpy, hope to figure out every details in pytorch data flow during the inference.
#%% numpy simulated layer0 convolution function define
def conv_cal(input_quantized, weight_quantized, kernel_size, stride, out_i, out_j, out_k):
weight = weight_quantized[out_i]
input = np.zeros((input_quantized.shape[0], kernel_size, kernel_size))
for i in range(weight.shape[0]):
for j in range(weight.shape[1]):
for k in range(weight.shape[2]):
input[i][j][k] = input_quantized[i][stride*out_j+j][stride*out_k+k]
# print(np.dot(weight,input))
# print(input,"\n")
# print(weight)
return np.multiply(weight,input).sum()
def QuantizedConv2D(input_scale, input_zero, input_quantized, output_scale, output_zero, weight_scale, weight_zero, weight_quantized, bias, kernel_size, stride, padding, ofm_size):
output = np.zeros((weight_quantized.shape[0],ofm_size,ofm_size))
input_quantized_padding = np.full((input_quantized.shape[0],input_quantized.shape[1]+2*padding,input_quantized.shape[2]+2*padding),0)
zero_temp = np.full(input_quantized.shape,input_zero)
input_quantized = input_quantized - zero_temp
for i in range(input_quantized.shape[0]):
for j in range(padding,padding + input_quantized.shape[1]):
for k in range(padding,padding + input_quantized.shape[2]):
input_quantized_padding[i][j][k] = input_quantized[i][j-padding][k-padding]
zero_temp = np.full(weight_quantized.shape, weight_zero)
weight_quantized = weight_quantized - zero_temp
for i in range(output.shape[0]):
for j in range(output.shape[1]):
for k in range(output.shape[2]):
# output[i][j][k] = (weight_scale*input_scale)*conv_cal(input_quantized_padding, weight_quantized, kernel_size, stride, i, j, k) + bias[i] #floating_output
output[i][j][k] = weight_scale*input_scale/output_scale*conv_cal(input_quantized_padding, weight_quantized, kernel_size, stride, i, j, k) + bias[i]/output_scale + output_zero
output[i][j][k] = round(output[i][j][k])
# int_output
return output
Here I input the same image, weight, and bias together with their zero_point and scale, then compare this "numpy simulated" result to the PyTorch calculated one.
quantized_model_out1_int8 = np.squeeze(features['features.0.0'].int_repr().numpy())
print(quantized_model_out1_int8.shape)
print(quantized_model_out1_int8)
out1_np = QuantizedConv2D(input_scale, input_zero, input_quantized, output_scale, output_zero, weight_scale, weight_zero, weight_quantized, bias, 3, 2, 1, 112)
np.save("out1_np.npy",out1_np)
for i in range(quantized_model_out1_int8.shape[0]):
for j in range(quantized_model_out1_int8.shape[1]):
for k in range(quantized_model_out1_int8.shape[2]):
if(out1_np[i][j][k] < 0):
out1_np[i][j][k] = 0
print(out1_np)
flag = np.zeros(quantized_model_out1_int8.shape)
for i in range(quantized_model_out1_int8.shape[0]):
for j in range(quantized_model_out1_int8.shape[1]):
for k in range(quantized_model_out1_int8.shape[2]):
if(quantized_model_out1_int8[i][j][k] == out1_np[i][j][k]):
flag[i][j][k] = 1
out1_np[i][j][k] = 0
quantized_model_out1_int8[i][j][k] = 0
# Compare the simulated result to extractor fetched result, gain the total hit rate
print(flag.sum()/(112*112*32)*100,'%')
If the "numpy simulated" results are the same as the extracted one, call it a hit. Print the total hit rate, it shows that numpy gets 92% of the values right. Now the problem is, I have no idea why the rest 8% of values come out wrong.
Comparison of two outcomes:
The picture below shows the different values between Numpy one and PyTorch one, the sample channel is index[1]. The left upper corner is Numpy one, and the upright corner is PyTorch one, I have set all values that are the same between them to 0, as you can see, most of the values just have a difference of 1(This can be view as the error brought by the precision loss of fixed point arithmetics), but some have large differences, e.g. the value[1][4], 121 vs. 76 (I don't know why)
Focus on one strange value:
This code is used to replay the calculation process of the value[1][4], originally I was expecting a trial and error process could lead me to solve this problem, to get my wanted number of 76, but no matter how I tried, it didn't output 76. If you want to try this, I paste this code for your convenience.
#%% A test code to check the calculation process
weight_quantized_sample = weight_quantized[2]
M_t = input_scale * weight_scale / output_scale
ifmap_t = np.int32(input_quantized[:,1:4,7:10])
weight_t = np.int32(weight_quantized_sample)
bias_t = bias[2]
bias_q = bias_t/output_scale
res_t = 0
for ch in range(3):
ifmap_offset = ifmap_t[ch]-np.int32(input_zero)
weight_offset = weight_t[ch]-np.int32(weight_zero)
res_ch = np.multiply(ifmap_offset, weight_offset)
res_ch = res_ch.sum()
res_t = res_t + res_ch
res_mul = M_t*res_t
# for n in range(1, 30):
# res_mul = multiply(n, M_t, res_t)
res_t = round(res_mul + output_zero + bias_q)
print(res_t)
Could you help me out of this, have been stuck here for a long time.
I implemented my own version of quantized convolution and got from 99.999% to 100% hitrate (and mismatch of a single value is by 1 that I can consider to be a rounding issue). The link on the paper in the question helped a lot.
But I found that your formulas are the same as mine. So I don't know what was your issue. As I understand quantization in pytorch is hardware dependent.
Here is my code:
def my_Conv2dRelu_b2(input_q, conv_layer, output_shape):
'''
Args:
input_q: quantized tensor
conv_layer: quantized tensor
output_shape: the pre-computed shape of the result
Returns:
'''
output = np.zeros(output_shape)
# extract needed float numbers from quantized operations
weights_scale = conv_layer.weight().q_per_channel_scales()
input_scale = input_q.q_scale()
weights_zp = conv_layer.weight().q_per_channel_zero_points()
input_zp = input_q.q_zero_point()
# extract needed convolution parameters
padding = conv_layer.padding
stride = conv_layer.stride
# extract float numbers for results
output_zp = conv_layer.zero_point
output_scale = conv_layer.scale
conv_weights_int = conv_layer.weight().int_repr()
input_int = input_q.int_repr()
biases = conv_layer.bias().numpy()
for k in range(input_q.shape[0]):
for i in range(conv_weights_int.shape[0]):
output[k][i] = manual_convolution_quant(
input_int[k].numpy(),
conv_weights_int[i].numpy(),
biases[i],
padding=padding,
stride=stride,
image_zp=input_zp, image_scale=input_scale,
kernel_zp=weights_zp[i].item(), kernel_scale=weights_scale[i].item(),
result_zp=output_zp, result_scale=output_scale
)
return output
def manual_convolution_quant(image, kernel, b, padding, stride, image_zp, image_scale, kernel_zp, kernel_scale,
result_zp, result_scale):
H = image.shape[1]
W = image.shape[2]
new_H = H // stride[0]
new_W = W // stride[1]
results = np.zeros([new_H, new_W])
M = image_scale * kernel_scale / result_scale
bias = b / result_scale
paddedIm = np.pad(
image,
[(0, 0), (padding[0], padding[0]), (padding[1], padding[1])],
mode="constant",
constant_values=image_zp,
)
s = kernel.shape[1]
for i in range(new_H):
for j in range(new_W):
patch = paddedIm[
:, i * stride[0]: i * stride[0] + s, j * stride[1]: j * stride[1] + s
]
res = M * ((kernel - kernel_zp) * (patch - image_zp)).sum() + result_zp + bias
if res < 0:
res = 0
results[i, j] = round(res)
return results
Code to compare pytorch and my own version.
def calc_hit_rate(array1, array2):
good = (array1 == array2).astype(np.int).sum()
all = array1.size
return good / all
# during inference
y2 = model.conv1(y1)
y2_int = torch.int_repr(y2)
y2_int_manual = my_Conv2dRelu_b2(y1, model.conv1, y2.shape)
print(f'y2 hit rate= {calc_hit_rate(y2.int_repr().numpy(), y2_int_manual)}') #hit_rate=1.0
I am looking at the KalmanFilter from pykalman shown in examples:
pykalman documentation
Example 1
Example 2
and I am wondering
observation_covariance=100,
vs
observation_covariance=1,
the documentation states
observation_covariance R: e(t)^2 ~ Gaussian (0, R)
How should the value be set here correctly?
Additionally, is it possible to apply the Kalman filter without intercept in the above module?
The observation covariance shows how much error you assume to be in your input data. Kalman filter works fine on normally distributed data. Under this assumption you can use the 3-Sigma rule to calculate the covariance (in this case the variance) of your observation based on the maximum error in the observation.
The values in your question can be interpreted as follows:
Example 1
observation_covariance = 100
sigma = sqrt(observation_covariance) = 10
max_error = 3*sigma = 30
Example 2
observation_covariance = 1
sigma = sqrt(observation_covariance) = 1
max_error = 3*sigma = 3
So you need to choose the value based on your observation data. The more accurate the observation, the smaller the observation covariance.
Another point: you can tune your filter by manipulating the covariance, but I think it's not a good idea. The higher the observation covariance value the weaker impact a new observation has on the filter state.
Sorry, I did not understand the second part of your question (about the Kalman Filter without intercept). Could you please explain what you mean?
You are trying to use a regression model and both intercept and slope belong to it.
---------------------------
UPDATE
I prepared some code and plots to answer your questions in details. I used EWC and EWA historical data to stay close to the original article.
First of all here is the code (pretty the same one as in the examples above but with a different notation)
from pykalman import KalmanFilter
import numpy as np
import matplotlib.pyplot as plt
# reading data (quick and dirty)
Datum=[]
EWA=[]
EWC=[]
for line in open('data/dataset.csv'):
f1, f2, f3 = line.split(';')
Datum.append(f1)
EWA.append(float(f2))
EWC.append(float(f3))
n = len(Datum)
# Filter Configuration
# both slope and intercept have to be estimated
# transition_matrix
F = np.eye(2) # identity matrix because x_(k+1) = x_(k) + noise
# observation_matrix
# H_k = [EWA_k 1]
H = np.vstack([np.matrix(EWA), np.ones((1, n))]).T[:, np.newaxis]
# transition_covariance
Q = [[1e-4, 0],
[ 0, 1e-4]]
# observation_covariance
R = 1 # max error = 3
# initial_state_mean
X0 = [0,
0]
# initial_state_covariance
P0 = [[ 1, 0],
[ 0, 1]]
# Kalman-Filter initialization
kf = KalmanFilter(n_dim_obs=1, n_dim_state=2,
transition_matrices = F,
observation_matrices = H,
transition_covariance = Q,
observation_covariance = R,
initial_state_mean = X0,
initial_state_covariance = P0)
# Filtering
state_means, state_covs = kf.filter(EWC)
# Restore EWC based on EWA and estimated parameters
EWC_restored = np.multiply(EWA, state_means[:, 0]) + state_means[:, 1]
# Plots
plt.figure(1)
ax1 = plt.subplot(211)
plt.plot(state_means[:, 0], label="Slope")
plt.grid()
plt.legend(loc="upper left")
ax2 = plt.subplot(212)
plt.plot(state_means[:, 1], label="Intercept")
plt.grid()
plt.legend(loc="upper left")
# check the result
plt.figure(2)
plt.plot(EWC, label="EWC original")
plt.plot(EWC_restored, label="EWC restored")
plt.grid()
plt.legend(loc="upper left")
plt.show()
I could not retrieve data using pandas, so I downloaded them and read from the file.
Here you can see the estimated slope and intercept:
To test the estimated data I restored the EWC value from the EWA using the estimated parameters:
About the observation covariance value
By varying the observation covariance value you tell the Filter how accurate the input data is (normally you just describe your confidence in the observation using some datasheets or your knowledge about the system).
Here are estimated parameters and the restored EWC values using different observation covariance values:
You can see the filter follows the original function better with a bigger confidence in observation (smaller R). If the confidence is low (bigger R) the filter leaves the initial estimate (slope = 0, intercept = 0) very slowly and the restored function is far away from the original one.
About the frozen intercept
If you want to freeze the intercept for some reason, you need to change the whole model and all filter parameters.
In the normal case we had:
x = [slope; intercept] #estimation state
H = [EWA 1] #observation matrix
z = [EWC] #observation
Now we have:
x = [slope] #estimation state
H = [EWA] #observation matrix
z = [EWC-const_intercept] #observation
Results:
Here is the code:
from pykalman import KalmanFilter
import numpy as np
import matplotlib.pyplot as plt
# only slope has to be estimated (it will be manipulated by the constant intercept) - mathematically incorrect!
const_intercept = 10
# reading data (quick and dirty)
Datum=[]
EWA=[]
EWC=[]
for line in open('data/dataset.csv'):
f1, f2, f3 = line.split(';')
Datum.append(f1)
EWA.append(float(f2))
EWC.append(float(f3))
n = len(Datum)
# Filter Configuration
# transition_matrix
F = 1 # identity matrix because x_(k+1) = x_(k) + noise
# observation_matrix
# H_k = [EWA_k]
H = np.matrix(EWA).T[:, np.newaxis]
# transition_covariance
Q = 1e-4
# observation_covariance
R = 1 # max error = 3
# initial_state_mean
X0 = 0
# initial_state_covariance
P0 = 1
# Kalman-Filter initialization
kf = KalmanFilter(n_dim_obs=1, n_dim_state=1,
transition_matrices = F,
observation_matrices = H,
transition_covariance = Q,
observation_covariance = R,
initial_state_mean = X0,
initial_state_covariance = P0)
# Creating the observation based on EWC and the constant intercept
z = EWC[:] # copy the list (not just assign the reference!)
z[:] = [x - const_intercept for x in z]
# Filtering
state_means, state_covs = kf.filter(z) # the estimation for the EWC data minus constant intercept
# Restore EWC based on EWA and estimated parameters
EWC_restored = np.multiply(EWA, state_means[:, 0]) + const_intercept
# Plots
plt.figure(1)
ax1 = plt.subplot(211)
plt.plot(state_means[:, 0], label="Slope")
plt.grid()
plt.legend(loc="upper left")
ax2 = plt.subplot(212)
plt.plot(const_intercept*np.ones((n, 1)), label="Intercept")
plt.grid()
plt.legend(loc="upper left")
# check the result
plt.figure(2)
plt.plot(EWC, label="EWC original")
plt.plot(EWC_restored, label="EWC restored")
plt.grid()
plt.legend(loc="upper left")
plt.show()
I know this question has been asked in various forms, but I can't really find any answer I can understand and use. So forgive me if this is a basic question, 'cause I'm a newbie to these tools(theano/keras)
Problem to Solve
Monitor variables in Neural Networks
(e.g. input/forget/output gate values in LSTM)
What I'm currently getting
no matter in which stage I'm getting those values, I'm getting something like :
Elemwise{mul,no_inplace}.0
Elemwise{mul,no_inplace}.0
[for{cpu,scan_fn}.2, Subtensor{int64::}.0, Subtensor{int64::}.0]
[for{cpu,scan_fn}.2, Subtensor{int64::}.0, Subtensor{int64::}.0]
Subtensor{int64}.0
Subtensor{int64}.0
Is there any way I can't monitor(e.g. print to stdout, write to a file, etc) them?
Possible Solution
Seems like callbacks in Keras can do the job, but it doesn't work either for me. I'm getting same thing as above
My Guess
Seems like I'm making very simple mistakes.
Thank you very much in advance, everyone.
ADDED
Specifically, I'm trying to monitor input/forget/output gating values in LSTM.
I found that LSTM.step() is for computing those values:
def step(self, x, states):
h_tm1 = states[0] # hidden state of the previous time step
c_tm1 = states[1] # cell state from the previous time step
B_U = states[2] # dropout matrices for recurrent units?
B_W = states[3] # dropout matrices for input units?
if self.consume_less == 'cpu': # just cut x into 4 pieces in columns
x_i = x[:, :self.output_dim]
x_f = x[:, self.output_dim: 2 * self.output_dim]
x_c = x[:, 2 * self.output_dim: 3 * self.output_dim]
x_o = x[:, 3 * self.output_dim:]
else:
x_i = K.dot(x * B_W[0], self.W_i) + self.b_i
x_f = K.dot(x * B_W[1], self.W_f) + self.b_f
x_c = K.dot(x * B_W[2], self.W_c) + self.b_c
x_o = K.dot(x * B_W[3], self.W_o) + self.b_o
i = self.inner_activation(x_i + K.dot(h_tm1 * B_U[0], self.U_i))
f = self.inner_activation(x_f + K.dot(h_tm1 * B_U[1], self.U_f))
c = f * c_tm1 + i * self.activation(x_c + K.dot(h_tm1 * B_U[2], self.U_c))
o = self.inner_activation(x_o + K.dot(h_tm1 * B_U[3], self.U_o))
with open("test_visualization.txt", "a") as myfile:
myfile.write(str(i)+"\n")
h = o * self.activation(c)
return h, [h, c]
And as it's in the code above, I tried to write the value of i into a file, but it only gave me values like :
Elemwise{mul,no_inplace}.0
[for{cpu,scan_fn}.2, Subtensor{int64::}.0, Subtensor{int64::}.0]
Subtensor{int64}.0
So I tried i.eval() or i.get_value(), but both failed to give me values.
.eval() gave me this:
theano.gof.fg.MissingInputError: An input of the graph, used to compute Subtensor{::, :int64:}(<TensorType(float32, matrix)>, Constant{10}), was not provided and not given a value.Use the Theano flag exception_verbosity='high',for more information on this error.
and .get_value() gave me this:
AttributeError: 'TensorVariable' object has no attribute 'get_value'
So I backtracked those chains(which line calls which functions..) and tried to get values at every steps I found but in vain.
Feels like I'm in some basic pitfalls.
I use the solution described in the Keras FAQ:
http://keras.io/getting-started/faq/#how-can-i-visualize-the-output-of-an-intermediate-layer
In detail:
from keras import backend as K
intermediate_tensor_function = K.function([model.layers[0].input],[model.layers[layer_of_interest].output])
intermediate_tensor = intermediate_tensor_function([thisInput])[0]
yields:
array([[ 3., 17.]], dtype=float32)
However I'd like to use the functional API but I can't seem to get the actual tensor, only the symbolic representation. For example:
model.layers[1].output
yields:
<tf.Tensor 'add:0' shape=(?, 2) dtype=float32>
I'm missing something about the interaction of Keras and Tensorflow here but I'm not sure what. Any insight much appreciated.
One solution is to create a version of your network that is truncated at the LSTM layer of which you want to monitor the gate values, and then replace the original layer with a custom layer in which the stepfunction is modified to return not only the hidden layer values, but also the gate values.
For instance, say you want to access the access the gate values of a GRU. Create a custom layer GRU2 that inherits everything from the GRU class, but adapt the step function such that it returns a concatenation of the states you want to monitor, and then takes only the part containing the previous hidden layer activations when computing the next activations. I.e:
def step(self, x, states):
# get prev hidden layer from input that is concatenation of
# prev hidden layer + reset gate + update gate
x = x[:self.output_dim, :]
###############################################
# This is the original code from the GRU layer
#
h_tm1 = states[0] # previous memory
B_U = states[1] # dropout matrices for recurrent units
B_W = states[2]
if self.consume_less == 'gpu':
matrix_x = K.dot(x * B_W[0], self.W) + self.b
matrix_inner = K.dot(h_tm1 * B_U[0], self.U[:, :2 * self.output_dim])
x_z = matrix_x[:, :self.output_dim]
x_r = matrix_x[:, self.output_dim: 2 * self.output_dim]
inner_z = matrix_inner[:, :self.output_dim]
inner_r = matrix_inner[:, self.output_dim: 2 * self.output_dim]
z = self.inner_activation(x_z + inner_z)
r = self.inner_activation(x_r + inner_r)
x_h = matrix_x[:, 2 * self.output_dim:]
inner_h = K.dot(r * h_tm1 * B_U[0], self.U[:, 2 * self.output_dim:])
hh = self.activation(x_h + inner_h)
else:
if self.consume_less == 'cpu':
x_z = x[:, :self.output_dim]
x_r = x[:, self.output_dim: 2 * self.output_dim]
x_h = x[:, 2 * self.output_dim:]
elif self.consume_less == 'mem':
x_z = K.dot(x * B_W[0], self.W_z) + self.b_z
x_r = K.dot(x * B_W[1], self.W_r) + self.b_r
x_h = K.dot(x * B_W[2], self.W_h) + self.b_h
else:
raise Exception('Unknown `consume_less` mode.')
z = self.inner_activation(x_z + K.dot(h_tm1 * B_U[0], self.U_z))
r = self.inner_activation(x_r + K.dot(h_tm1 * B_U[1], self.U_r))
hh = self.activation(x_h + K.dot(r * h_tm1 * B_U[2], self.U_h))
h = z * h_tm1 + (1 - z) * hh
#
# End of original code
###########################################################
# concatenate states you want to monitor, in this case the
# hidden layer activations and gates z and r
all = K.concatenate([h, z, r])
# return everything
return all, [h]
(Note that the only lines I added are at the beginning and end of the function).
If you then run your network with GRU2 as last layer instead of GRU (with return_sequences = True for the GRU2 layer), you can just call predict on your network, this will give you all hidden layer and gate values.
The same thing should work for LSTM, although you might have to puzzle a bit to figure out how to store all the outputs you want in one vector and retrieve them again afterwards.
Hope that helps!
You can use theano's printing module for printing during execution (and not during definition, which is what you're doing and the reason why you're not getting values, but their abstract definition).
Print
Just use the Print function. Don't forget to use the output of Print to continue your graph, otherwise the output will be disconnected and Print will most likely be removed during optimisation. And you will see nothing.
from keras import backend as K
from theano.printing import Print
def someLossFunction(x, ref):
loss = K.square(x - ref)
loss = Print('Loss tensor (before sum)')(loss)
loss = K.sum(loss)
loss = Print('Loss scalar (after sum)')(loss)
return loss
Plot
A little bonus you might enjoy.
The Print class has a global_fn parameter, to override the default callback to print. You can provide your own function and directly access to the data, to build a plot for instance.
from keras import backend as K
from theano.printing import Print
import matplotlib.pyplot as plt
curve = []
# the callback function
def myPlottingFn(printObj, data):
global curve
# Store scalar data
curve.append(data)
# Plot it
fig, ax = plt.subplots()
ax.plot(curve, label=printObj.message)
ax.legend(loc='best')
plt.show()
def someLossFunction(x, ref):
loss = K.sum(K.square(x - ref))
# Callback is defined line below
loss = Print('Loss scalar (after sum)', global_fn=myplottingFn)(loss)
return loss
BTW the string you passed to Print('...') is stored in the print object under property name message (see function myPlottingFn). This is useful for building multi-curves plot automatically
I am programming in MATLAB and I am trying to use the Neural Network Toolbox but I have troubles in calculating the output of a network. I will try to explain my problem: I have defined a very simple ANN with one hidden layer and linear activation functions. So if I have an input x, then I expect the output of the hidden layer to be
h = w * x + b
where w are the weights and b the biases. Then I expect my output to be
o = w' * h + b'
where w' are the weights between the hidden layer and the output and b' the biases.
Now the problem is that if I do
o = net(x)
this doesn't happen. Here is my code:
net = feedforwardnet([layer1], 'traincgp');
net = configure(net, Dtrain, Dtrain);
net.trainParam.epochs = 0;
net.IW{1,1} = weights12;
net.LW{2,1} = my_weights;
net.b{1} = bias12;
for ii=1:size(net.layers, 1)
net.layers{ii}.transferFcn = 'purelin';
end;
net = train(net, Dtrain, Dtrain);
As you can see I am training for 0 epochs since this is just a test and I am also using Dtrain both as input and target since I am training an autoencoder. As I said, the problem is that if I calculate the output as I wrote before I get one result, while if I do
output = net(input)
I get another one. What should I do to have the same result?