I am trying my first NN with tensorflow and unable to produce results for a single input sample. I have created a minimal example where I am feeding it multiple y = a * x + b inputs (for varying a, b) and trying to get a result back but it fails. Note that I don't care about accuracy here, I'm doing this as a POC. Some parameters are below:
N is the number of x grid points. Each input row is of length 2*N
(N for x, N for y).
M is the number of training rows I give.
2 is the number of outputs I expect (a and b).
Thus, my training data is x_train of size (m, 2*n) and y_train of size (m, 2). It seems that I build the model OK but I am unable to feed it a single input of size (1, 2*n) and get a result back of size (1, 2) as desired. Instead I get the following error:
Traceback (most recent call last):
File "xdriver.py", line 92, in <module>
main()
File "xdriver.py", line 89, in main
ab2 = model.predict(rys) # This fails
File "/apps/anaconda/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 909, in predict
use_multiprocessing=use_multiprocessing)
File "/apps/anaconda/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 462, in predict
steps=steps, callbacks=callbacks, **kwargs)
File "/apps/anaconda/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 396, in _model_iteration
distribution_strategy=strategy)
File "/apps/anaconda/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 594, in _process_inputs
steps=steps)
File "/apps/anaconda/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 2472, in _standardize_user_data
exception_prefix='input')
File "/apps/anaconda/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_utils.py", line 574, in standardize_input_data
str(data_shape))
ValueError: Error when checking input: expected dense_input to have shape (20,) but got array with shape (1,)
Below is the code I am using which is the minimal example I have been able to develop to reproduce this (along with documentation to explain my process). Can anyone assess what I am doing wrong and what to change?
#!/usr/bin/env python3
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
#################
### CONSTANTS ###
#################
ARANGE = (-5.0, 5.0) # Possible values for m in training data
BRANGE = (0.0, 10.0) # Possible values for b in training data
X_MIN = 1.0
X_MAX = 9.0
N = 10 # Number of grid points
M = 2 # Number of {(x,y)} sets to train on
def gen_ab(arange, brange):
""" mrange, brange are tuples of floats """
a = (arange[1] - arange[0])*np.random.rand() + arange[0]
b = (brange[1] - brange[0])*np.random.rand() + brange[0]
return (a, b)
def build_model(x_data, y_data):
""" Build the model using input / output training data
Args:
x_data (np array): Size (m, n*2) grid of input training data.
y_data (np array): Size (m, 2) grid of output training data.
Returns:
model (Sequential model)
"""
model = keras.Sequential()
model.add(layers.Dense(64, activation='relu', input_dim=len(x_data[0])))
model.add(layers.Dense(len(y_data[0])))
optimizer = tf.keras.optimizers.RMSprop(0.001)
model.compile(loss='mse', optimizer=optimizer, metrics=['mae', 'mse'])
return model
def gen_data(xs, arange, brange, m):
""" Generate training data for lines of y = m*x + b
Args:
xs (list): Grid points (size N1)
arange (tuple): Range to use for a (a_min, a_max)
brange (tuple): Range to use for b (b_min, b_max)
m (int): Number of y grids to generate
Returns:
x_data (np array): Size (m, n*2) grid of input training data.
y_data (np array): Size (m, 2) grid of output training data.
"""
n = len(xs)
x_data = np.zeros((m, 2*n))
y_data = np.zeros((m, 2))
for ix in range(m):
(a, b) = gen_ab(arange, brange)
ys = a*xs + b*np.ones(xs.size)
x_data[ix, :] = np.concatenate((xs, ys))
y_data[ix, :] = [a, b]
return (x_data, y_data)
def main():
""" Main routin """
# Generate the x axis grid to be used for all training sets
xs = np.linspace(X_MIN, X_MAX, N)
# Generate the training data
# x_train has M rows (M is the number of training samples)
# x_train has 2*N columns (first N columns are x, second N columns are y)
# y_train has M rows, each of which has two columns (a, b) for y = ax + b
(x_train, y_train) = gen_data(xs, ARANGE, BRANGE, M)
model = build_model(x_train, y_train)
model.fit(x_train, y_train, epochs=10, batch_size=32)
model.summary()
####################
### Test example ###
####################
(a, b) = gen_ab(ARANGE, BRANGE)
ys = a*xs + b*np.ones(xs.size)
rys = np.concatenate((xs, ys))
ab1 = model.predict(x_train) # This succeeds
print(a, b)
print(ab1)
ab2 = model.predict(rys) # This fails
if __name__ == "__main__":
main()
The solution to this turned out to be pretty simple. You simply need to pass in the input data as a batch of size one. Changing:
ab2 = model.predict(rys)
to
ab2 = model.predict(np.array([rys]))
made it work!
Related
I'm trying to train a network in pytorch along the lines of this idea.
The author creates a simple MLP (4 hidden layers) and then explicitly works out what the partial derivatives of the output is wrt the inputs. He then trains the network on the training labels as well as the gradients of the output wrt the input data (which is also part of the training data).
To replicate the idea in pytorch, my training loop looks like this:
import torch
import torch.nn.functional as F
class vanilla_net(torch.nn.Module):
def __init__(self,
input_dim, # dimension of inputs, e.g. 10
hidden_units, # units in hidden layers, assumed constant, e.g. 20
hidden_layers): # number of hidden layers, e.g. 4):
super(vanilla_net, self).__init__()
self.input = torch.nn.Linear(input_dim, hidden_units)
self.hidden = torch.nn.ModuleList()
for hl in range(hidden_layers):
layer = torch.nn.Linear(hidden_units, hidden_units)
self.hidden.append(layer)
self.output = torch.nn.Linear(hidden_units, 1)
def forward(self, x):
x = self.input(x)
x = F.softplus(x)
for h in self.hidden:
x = h(x)
x = F.softplus(x)
x = self.output(x)
return x
....
def lossfn(x, y, dx, dy):
# some loss function involving both sets of training data (y and dy)
# the network outputs x and what's needed is an efficient way of calculating dx - the partial
# derivatives of x wrt the batch inputs.
pass
def train(net, x_train, y_train, dydx_train, batch_size=256)
m, n = x_train.shape
first = 0
last = min(batch_size, m)
while first < m:
xi = x_train[first:last]
yi = y_train[first:last]
zi = dydx_train[first:last]
xi.requires_grad_()
# Perform forward pass
outputs = net(xi)
minimizer.zero_grad()
outputs.backward(torch.ones_like(outputs), create_graph=True)
xi_grad = xi.grad
# Compute loss
loss = lossfn(outputs, yi, xi_grad, zi)
minimizer.zero_grad()
# Perform backward pass
loss.backward()
# Perform optimization
minimizer.step()
first = last
last = min(first + batch_size, m)
net = vanilla_net(4, 10, 4)
minimizer = torch.optim.Adam(net.parameters(), lr=1e-4)
...
This seems to work but is there a more elegant/efficient way to achieve the same thing? Also - not sure I know where the best place to put the minimizer.zero_grad()
Thanks
I'm working on a project where I have to predict the future states of a 1D vector with y entries. I'm trying to do this using an ANN setup with LSTM units in combination with a convolution layer. The method I'm using is based on the method they used in a (pre-release paper). The suggested setup is as follows:
In the picture c is the 1D vector with y entries. The ANN gets the n previous states as an input and produces o next states as an output.
Currently, my ANN setup looks like this:
inputLayer = Input(shape = (n, y))
encoder = LSTM(200)(inputLayer)
x = RepeatVector(1)(encoder)
decoder = LSTM(200, return_sequences=True)(x)
x = Conv1D(y, 4, activation = 'linear', padding = 'same')(decoder)
model = Model(inputLayer, x)
Here n is the length of the input sequences and y is the length of the state array. As can be seen I'm repeating the d vector only 1 time, as I'm trying to predict only 1 time step in the future. Is this the way to setup the above mentioned network?
Furthermore, I have a numpy array (data) with a shape of (Sequences, Time Steps, State Variables) to train with. I was trying to divide this in randomly selected batches with a generator like this:
def BatchGenerator(batch_size, n, y, data):
# Infinite loop.
while True:
# Allocate a new array for the batch of input-signals.
x_shape = (batch_size, n, y)
x_batch = np.zeros(shape=x_shape, dtype=np.float16)
# Allocate a new array for the batch of output-signals.
y_shape = (batch_size, 1, y)
y_batch = np.zeros(shape=y_shape, dtype=np.float16)
# Fill the batch with random sequences of data.
for i in range(batch_size):
# Select a random sequence
seq_idx = np.random.randint(data.shape[0])
# Get a random start-index.
# This points somewhere into the training-data.
start_idx = np.random.randint(data.shape[1] - n)
# Copy the sequences of data starting at this
# Each batch inside x_batch has a shape of [n, y]
x_batch[i,:,:] = data[seq_idx, start_idx:start_idx+n, :]
# Each batch inside y_batch has a shape of [1, y] (as we predict only 1 time step in advance)
y_batch[i,:,:] = data[seq_idx, start_idx+n, :]
yield (x_batch, y_batch)
The problem is that it gives an error if I'm using a batch_size of more than 1. Could anyone help me to set this data up in a way that it can be used optimally to train my neural network?
The model is now trained using:
generator = BatchGenerator(batch_size, n, y, data)
model.fit_generator(generator = generator, steps_per_epoch = steps_per_epoch, epochs = epochs)
Thanks in advance!
Can someone provide a toy example of how to compute IoU (intersection over union) for semantic segmentation in pytorch?
As of 2021, there's no need to implement your own IoU, as torchmetrics comes equipped with it - here's the link.
It is named torchmetrics.JaccardIndex (previously torchmetrics.IoU) and calculates what you want.
It works with PyTorch and PyTorch Lightning, also with distributed training.
From the documentation:
torchmetrics.JaccardIndex(num_classes, ignore_index=None, absent_score=0.0, threshold=0.5, multilabel=False, reduction='elementwise_mean', compute_on_step=None, **kwargs)
Computes Intersection over union, or Jaccard index calculation:
J(A,B) = \frac{|A\cap B|}{|A\cup B|}
Where: A and B are both tensors of the same size, containing integer class values. They may be subject to conversion from input data (see description below). Note that it is different from box IoU.
Works with binary, multiclass and multi-label data. Accepts probabilities from a model output or integer class values in prediction. Works with multi-dimensional preds and target.
Forward accepts
preds (float or long tensor): (N, ...) or (N, C, ...) where C is the number of classes
target (long tensor): (N, ...) If preds and target
are the same shape and preds is a float tensor, we use the
self.threshold argument to convert into integer labels. This is the case for binary and multi-label probabilities.
If preds has an extra dimension as in the case of multi-class scores we perform an argmax on dim=1.
Official example:
>>> from torchmetrics import JaccardIndex
>>> target = torch.randint(0, 2, (10, 25, 25))
>>> pred = torch.tensor(target)
>>> pred[2:5, 7:13, 9:15] = 1 - pred[2:5, 7:13, 9:15]
>>> jaccard = JaccardIndex(num_classes=2)
>>> jaccard(pred, target)
tensor(0.9660)
I found this somewhere and adapted it for me. I'll post the link if I can find it again. Sorry in case this was a dublicate.
The key function here is the function called iou. The wrapping function evaluate_performance is not universal, but it shows that one needs to iterate over all results before computing IoU.
import torch
import pandas as pd # For filelist reading
import myPytorchDatasetClass # Custom dataset class, inherited from torch.utils.data.dataset
def iou(pred, target, n_classes = 12):
ious = []
pred = pred.view(-1)
target = target.view(-1)
# Ignore IoU for background class ("0")
for cls in xrange(1, n_classes): # This goes from 1:n_classes-1 -> class "0" is ignored
pred_inds = pred == cls
target_inds = target == cls
intersection = (pred_inds[target_inds]).long().sum().data.cpu()[0] # Cast to long to prevent overflows
union = pred_inds.long().sum().data.cpu()[0] + target_inds.long().sum().data.cpu()[0] - intersection
if union == 0:
ious.append(float('nan')) # If there is no ground truth, do not include in evaluation
else:
ious.append(float(intersection) / float(max(union, 1)))
return np.array(ious)
def evaluate_performance(net):
# Dataloader for test data
batch_size = 1
filelist_name_test = '/path/to/my/test/filelist.txt'
data_root_test = '/path/to/my/data/'
dset_test = myPytorchDatasetClass.CustomDataset(filelist_name_test, data_root_test)
test_loader = torch.utils.data.DataLoader(dataset=dset_test,
batch_size=batch_size,
shuffle=False,
pin_memory=True)
data_info = pd.read_csv(filelist_name_test, header=None)
num_test_files = data_info.shape[0]
sample_size = num_test_files
# Containers for results
preds = Variable(torch.zeros((sample_size, 60, 36, 60)))
gts = Variable(torch.zeros((sample_size, 60, 36, 60)))
dataiter = iter(test_loader)
for i in xrange(sample_size):
images, labels, filename = dataiter.next()
images = Variable(images).cuda()
labels = Variable(labels)
gts[i:i+batch_size, :, :, :] = labels
outputs = net(images)
outputs = outputs.permute(0, 2, 3, 4, 1).contiguous()
val, pred = torch.max(outputs, 4)
preds[i:i+batch_size, :, :, :] = pred.cpu()
acc = iou(preds, gts)
return acc
Say your outputs are of shape [32, 256, 256] # 32 is the minibatch size and 256x256 is the image's height and width, and the labels are also the same shape.
Then you can use sklearn's jaccard_similarity_score after some reshaping.
If both are torch tensors, then:
lbl = labels.cpu().numpy().reshape(-1)
target = output.cpu().numpy().reshape(-1)
Now:
from sklearn.metrics import jaccard_similarity_score as jsc
print(jsc(target,lbl))
I'll preface this by saying this is my first posted question on SO. I've just recently started working with Tensorflow, and have been attempting to apply a convolutional-neural network model approach for classification of .csv records in a file representing images from scans of microarray data. (FYI: Microarrays are a grid of spotted DNA on a glass slide, representing specific DNA target sequences for determining the presence of those DNA targets in a sample. The individual pixels represent fluorescence intensity value from 0-1). The file has ~200,000 records in total. Each record (image) has 10816 pixels that represent DNA sequences from known viruses, and one index label which identifies the virus species. The pixels create a pattern which is unique to each of the different viruses. There are 2165 different viruses in total represented within the 200,000 records. I have trained the network on images of labeled microarray datasets, but when I try to pass a new dataset through to classify it/them as one of the 2165 different viruses and determine predicted values and probabilities, I don't seem to be having much luck. This is the code that I am currently using for this:
import tensorflow as tf
import numpy as np
import csv
def extract_data(filename):
print("extracting data...")
NUM_LABELS = 2165
NUM_FEATURES = 10816
labels = []
fvecs = []
rowCount = 0
#iterate over the rows, split the label from the features
#convert the labels to integers and features to floats
for line in open(filename):
rowCount = rowCount + 1
row = line.split(',')
labels.append(row[3])#(int(row[7])) #<<<IT ALWAYS PREDICTS THIS VALUE!
for x in row [4:10820]:
fvecs.append(float(x))
#convert the array of float arrasy into a numpy float matrix
fvecs_np = np.matrix(fvecs).astype(np.float32)
#convert the array of int lables inta a numpy array
labels_np = np.array(labels).astype(dtype=np.uint8)
#convert the int numpy array into a one-hot matrix
labels_onehot = (np.arange(NUM_LABELS) == labels_np[:, None]).astype(np.float32)
print("arrays converted")
return fvecs_np, labels_onehot
def TestModels():
fvecs_np, labels_onehot = extract_data("MicroarrayTestData.csv")
print('RESTORING NN MODEL')
weights = {}
biases = {}
sess=tf.Session()
init = tf.global_variables_initializer()
#Load meta graph and restore weights
ModelID = "MicroarrayCNN_Data-1000.meta"
print("RESTORING:::", ModelID)
saver = tf.train.import_meta_graph(ModelID)
saver.restore(sess,tf.train.latest_checkpoint('./'))
graph = tf.get_default_graph()
x = graph.get_tensor_by_name("x:0")
y = graph.get_tensor_by_name("y:0")
keep_prob = tf.placeholder(tf.float32)
y_ = tf.placeholder("float", shape=[None, 2165])
wc1 = graph.get_tensor_by_name("wc1:0")
wc2 = graph.get_tensor_by_name("wc2:0")
wd1 = graph.get_tensor_by_name("wd1:0")
Wout = graph.get_tensor_by_name("Wout:0")
bc1 = graph.get_tensor_by_name("bc1:0")
bc2 = graph.get_tensor_by_name("bc2:0")
bd1 = graph.get_tensor_by_name("bd1:0")
Bout = graph.get_tensor_by_name("Bout:0")
weights = {wc1, wc2, wd1, Wout}
biases = {bc1, bc2, bd1, Bout}
print("NEXTArgmax")
prediction=tf.argmax(y,1)
probabilities = y
predY = prediction.eval(feed_dict={x: fvecs_np, y: labels_onehot}, session=sess)
probY = probabilities.eval(feed_dict={x: fvecs_np, y: labels_onehot}, session=sess)
accuracy = tf.reduce_mean(tf.cast(prediction, "float"))
print(sess.run(accuracy, feed_dict={x: fvecs_np, y: labels_onehot}))
print("%%%%%%%%%%%%%%%%%%%%%%%%%%")
print("Predicted::: ", predY, accuracy)
print("%%%%%%%%%%%%%%%%%%%%%%%%%%")
feed_dictTEST = {y: labels_onehot}
probabilities=probY
print("probabilities", probabilities.eval(feed_dict={x: fvecs_np}, session=sess))
########## Run Analysis ###########
TestModels()
So, when I run this code I get the correct prediction for the test set, although I am not sure I believe it, because it appears that whatever value I append in line 14 (see below) is the output it predicts:
labels.append(row[3])#<<<IT ALWAYS PREDICTS THIS VALUE!
I don't understand this, and it makes me suspicious that I've set up the CNN incorrectly, as I would have expected it to ignore my input label and determine a bast match from the trained network based on the trained patterns. The only thing I can figure is that when I pass the value through for the prediction; it is instead training the model on this data as well, and then predicting itself. Is this a correct assumption, or am I misinterpreting how Tensorflow works?
The other issue is that when I try to use code that (based on other tutorials) which is supposed to output the probabilities of all of the 2165 possible outputs, I get the error:
InvalidArgumentError (see above for traceback): Shape [-1,2165] has negative dimensions
[[Node: y = Placeholder[dtype=DT_FLOAT, shape=[?,2165], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
To me, it looks like it is the correct layer based on the 2165 value in the Tensor shape, but I don't understand the -1 value. So, to wrap up the summary, my questions are:
Based on the fact that I get the value that I have in the label of the input data, is this the correct method to make a classification using this model?
Am I missing a layer or have I configured the model incorrectly in order to extract the probabilities of all of the possible output classes, or am I using the wrong code to extract the information? I try to print out the accuracy to see if that would work, but instead it outputs the description of a tensor, so clearly that is incorrect as well.
(ADDITIONAL INFORMATION)
As requested, I'm also including the original code that was used to train the model, which is now below. You can see I do sort of a piece meal training of a limited number of related records at a time by their taxonomic relationships as I iterate through the file. This is mostly because the Mac that I'm training on (Mac Pro w/ 64GB ram) tends to give me the "Killed -9" error due to overuse of resources if I don't do it this way. There may be a better way to do it, but this seems to work.
Original Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
from __future__ import print_function
import tensorflow as tf
import numpy as np
import csv
import random
# Parameters
num_epochs = 2
train_size = 1609
learning_rate = 0.001 #(larger >speed, lower >accuracy)
training_iters = 5000 # How much do you want to train (more = better trained)
batch_size = 32 #How many samples to train on, size of the training batch
display_step = 10 # How often to diplay what is going on during training
# Network Parameters
n_input = 10816 # MNIST data input (img shape: 28*28)...in my case 104x104 = 10816(rough array size)
n_classes = 2165 #3280 #2307 #787# Switched to 100 taxa/training set, dynamic was too wonky.
dropout = 0.75 # Dropout, probability to keep units. Jeffery Hinton's group developed it, that prevents overfitting to find new paths. More generalized model.
# Functions
def extract_data(filename):
print("extracting data...")
# arrays to hold the labels and feature vectors.
NUM_LABELS = 2165
NUM_FEATURES = 10826
taxCount = 0
taxCurrent = 0
labels = []
fvecs = []
rowCount = 0
#iterate over the rows, split the label from the features
#convert the labels to integers and features to floats
print("entering CNN loop")
for line in open(filename):
rowCount = rowCount + 1
row = line.split(',')
taxCurrent = row[3]
print("profile:", row[0:12])
labels.append(int(row[3]))
fvecs.append([float(x) for x in row [4:10820]])
#convert the array of float arrasy into a numpy float matrix
fvecs_np = np.matrix(fvecs).astype(np.float32)
#convert the array of int lables inta a numpy array
labels_np = np.array(labels).astype(dtype=np.uint8)
#convert the int numpy array into a one-hot matrix
labels_onehot = (np.arange(NUM_LABELS) == labels_np[:, None]).astype(np.float32)
print("arrays converted")
return fvecs_np, labels_onehot
# Create some wrappers for simplicity
def conv2d(x, W, b, strides=1): #Layer 1 : Convolutional layer
# Conv2D wrapper, with bias and relu activation
print("conv2d")
x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME') # Strides are the tensors...list of integers. Tensors=data
x = tf.nn.bias_add(x, b) #bias is the tuning knob
return tf.nn.relu(x) #rectified linear unit (activation function)
def maxpool2d(x, k=2): #Layer 2 : Takes samples from the image. (This is a 4D tensor)
print("maxpool2d")
# MaxPool2D wrapper
return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],
padding='SAME')
# Create model
def conv_net(x, weights, biases, dropout):
print("conv_net setup")
# Reshape input picture
x = tf.reshape(x, shape=[-1, 104, 104, 1]) #-->52x52 , -->26x26x64
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1']) #defined above already
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=2)
print(conv1.get_shape)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2']) #wc2 and bc2 are just placeholders...could actually skip this layer...maybe
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)
print(conv2.get_shape)
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.relu(fc1) #activation function for the NN
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)
# Output, class prediction
out = tf.add(tf.matmul(fc1, weights['Wout']), biases['Bout'])
return out
def Train_Network(Txid_IN, Sess_File_Name):
import tensorflow as tf
tf.reset_default_graph()
x,y = 0,0
weights = {}
biases = {}
# tf Graph input
print("setting placeholders")
x = tf.placeholder(tf.float32, [None, n_input], name="x") #Gateway for data (images)
y = tf.placeholder(tf.float32, [None, n_classes], name="y") # Gateway for data (labels)
keep_prob = tf.placeholder(tf.float32) #dropout # Gateway for dropout(keep probability)
# Store layers weight & bias
#CREATE weights
weights = {
# 5x5 conv, 1 input, 32 outputs
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32]),name="wc1"), #
# 5x5 conv, 32 inputs, 64 outputs
'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64]),name="wc2"),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([26*26*64, 1024]),name="wd1"),
# 1024 inputs, 10 outputs (class prediction)
'Wout': tf.Variable(tf.random_normal([1024, n_classes]),name="Wout")
}
biases = {
'bc1': tf.Variable(tf.random_normal([32]), name="bc1"),
'bc2': tf.Variable(tf.random_normal([64]), name="bc2"),
'bd1': tf.Variable(tf.random_normal([1024]), name="bd1"),
'Bout': tf.Variable(tf.random_normal([n_classes]), name="Bout")
}
# Construct model
print("constructing model")
pred = conv_net(x, weights, biases, keep_prob)
print(pred)
# Define loss(cost) and optimizer
#cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y)) Deprecated version of the statement
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = pred, labels=y)) #added reduce_mean 6/27
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
print("%%%%%%%%%%%%%%%%%%%%")
print ("%% ", correct_pred)
print ("%% ", accuracy)
print("%%%%%%%%%%%%%%%%%%%%")
# Initializing the variables
#init = tf.initialize_all_variables()
init = tf.global_variables_initializer()
saver = tf.train.Saver()
fvecs_np, labels_onehot = extract_data("MicroarrayDataOUT.csv") #CHAGE TO PICORNAVIRUS!!!!!AHHHHHH!!!
print("starting session")
# Launch the graph
FitStep = 0
with tf.Session() as sess: #graph is encapsulated by its session
sess.run(init)
step = 1
# Keep training until reach max iterations (training_iters)
while step * batch_size < training_iters:
if FitStep >= 5:
break
else:
#iterate and train
print(step)
print(fvecs_np, labels_onehot)
for step in range(num_epochs * train_size // batch_size):
sess.run(optimizer, feed_dict={x: fvecs_np, y: labels_onehot, keep_prob:dropout}) #no dropout???...added Keep_prob:dropout
if FitStep >= 5:
break
#else:
###batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
###sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
### keep_prob: dropout}) <<<<SOMETHING IS WRONG IN HERE?!!!
if step % display_step == 0:
# Calculate batch loss and accuracy
loss, acc = sess.run([cost, accuracy], feed_dict={x: fvecs_np,
y: labels_onehot,
keep_prob: 1.})
print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(np.mean(loss)) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
TrainAcc = float("{:.5f}".format(acc))
#print("******", TrainAcc)
if TrainAcc >= .99: #Changed from .95 temporarily
print(FitStep)
FitStep = FitStep+1
saver.save(sess, Sess_File_Name, global_step=1000) #
print("Saved Session:", Sess_File_Name)
step += 1
print("Optimization Finished!")
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: fvecs_np[:256],
y: labels_onehot[:256],
keep_prob: 1.}))
#feed_dictTEST = {x: fvecs_np[50]}
#prediction=tf.argmax(y,1)
#print(prediction)
#best = sess.run([prediction],feed_dictTEST)
#print(best)
print("DONE")
sess.close()
def Tax_Iterator(CSV_inFile, CSV_outFile): #Deprecate
#Need to copy *.csv file to MySQL for sorting
resultFileINIT = open(CSV_outFile,'w')
resultFileINIT.close()
TaxCount = 0
TaxThreshold = 2165
ThresholdStep = 2165
PrevTax = 0
linecounter = 0
#Open all GenBank profile list
for line in open(CSV_inFile):
linecounter = linecounter+1
print(linecounter)
resultFile = open(CSV_outFile,'a')
wr = csv.writer(resultFile, dialect='excel')
# Check for new TXID
row = line.split(',')
print(row[7], "===", PrevTax)
if row[7] != PrevTax:
print("X1")
TaxCount = TaxCount+1
PrevTax = row[7]
#Check it current Tax count is < or > threshold
# < threshold
print(TaxCount,"=+=", TaxThreshold)
if TaxCount<=3300:
print("X2")
CurrentTax= row[7]
CurrTxCount = CurrentTax
print("TaxCount=", TaxCount)
print( "Add to CSV")
print("row:", CurrentTax, "***", row[0:15])
wr.writerow(row[0:-1])
# is > threshold
else:
print("X3")
# but same TXID....
print(row[7], "=-=", CurrentTax)
if row[7]==CurrentTax:
print("X4")
CurrentTax= row[7]
print("TaxCount=", TaxCount)
print( "Add to CSV")
print("row:", CurrentTax, "***", row[0:15])
wr.writerow(row[0:-1])
# but different TXID...
else:
print(row[7], "=*=", CurrentTax)
if row[7]>CurrentTax:
print("X5")
TaxThreshold=TaxThreshold+ThresholdStep
resultFile.close()
Sess_File_Name = "CNN_VirusIDvSPECIES_XXALL"+ str(TaxThreshold-ThresholdStep)
print("<<<< Start Training >>>>"
print("Training on :: ", CurrTxCount, "Taxa", TaxCount, "data points.")
Train_Network(CurrTxCount, Sess_File_Name)
print("Training complete")
resultFileINIT = open(CSV_outFile,'w')
resultFileINIT.close()
CurrentTax= row[7]
#reset tax count
CurrTxCount = 0
TaxCount = 0
resultFile.close()
Sess_File_Name = "MicroarrayCNN_Data"+ str(TaxThreshold+ThresholdStep)
print("<<<< Start Training >>>>")
print("Training on :: ", CurrTxCount, "Taxa", TaxCount, "data points.")
Train_Network(CurrTxCount, Sess_File_Name)
resultFileINIT = open(CSV_outFile,'w')
resultFileINIT.close()
CurrentTax= row[7]
Tax_Iterator("MicroarrayInput.csv", "MicroarrayOutput.csv")
You defined prediction as prediction=tf.argmax(y,1). And in both feed_dict, you feed labels_onehot for y. Consequently, your "prediction" is always equal to the labels.
As you didn't post the code you used to train your network, I can't tell you what exactly you need to change.
Edit: I have isses understanding the underlying problem you're trying to solve - based on your code, you're trying to train a neural network with 2165 different classes using 1609 training examples. How is this even possible? If each example had a different class, there would still be some classes without any training example. Or does one image belong to many classes? From your statement at the beginning of your question, I had assumed you're trying to output a real-valued number between 0-1.
I'm actually surprised that the code actually worked as it looks like you're adding only a single number to your labels list, but your model expects a list with length 2165 for each training example.
I am trying to implement multi-varibale linear regression using tensorflow. I have a csv file with 200 rows and 3 columns (features) with the last column as output. Something like this:
I have written the following code:
from __future__ import print_function
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import csv
import pandas
rng = np.random
# Parameters
learning_rate = 0.01
training_epochs = 1000
display_step = 50
I get the data from the file using pandas and store it:
# Training Data
dataframe = pandas.read_csv("Advertising.csv", delim_whitespace=True, header=None)
dataset = dataframe.values
X1,X2,X3,y1 = [],[],[],[]
for i in range(1,len(dataset)):
X = dataset[i][0]
X1.append(np.float32(X.split(",")[1]))
X2.append(np.float32(X.split(",")[2]))
X3.append(np.float32(X.split(",")[3]))
y1.append(np.float32(X.split(",")[4]))
X = np.column_stack((X1,X2))
X = np.column_stack((X,X3))
I assign the placeholders and variables and the linear regression model:
n_samples = len(X1)
#print(n_samples) = 17
# tf Graph Input
X_1 = tf.placeholder(tf.float32, [3, None])
Y = tf.placeholder(tf.float32, [None])
# Set model weights
W1 = tf.Variable(rng.randn(), [n_samples,3])
b = tf.Variable(rng.randn(), [n_samples])
# Construct a linear model
pred = tf.add(tf.matmul(W1, X_1), b)
# Mean squared error
cost = tf.reduce_sum(tf.pow(pred-Y, 2))/(2*n_samples)
# Gradient descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
# Initializing the variables
init = tf.global_variables_initializer()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
# Fit all training data
for epoch in range(training_epochs):
for (x1, y) in zip(X, y1):
sess.run(optimizer, feed_dict={X_1: x1, Y: y})
# Display logs per epoch step
if (epoch+1) % display_step == 0:
c = sess.run(cost, feed_dict={X_1: x1, Y: y})
print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c), \
"Weights=", sess.run(W1),"b=", sess.run(b))
I get the following error which I am not able to debug:
ValueError: Shape must be rank 2 but is rank 0 for 'MatMul' (op:
'MatMul') with input shapes: [], [3,?].
Can you help me with hot to solve this?
Thanks in advance.
tf.variable doesn't take inputs as you are thinking, the second parameter is not shape. To set the shape of the variable you do this with the initializer (the first parameter). see https://www.tensorflow.org/api_docs/python/tf/Variable
Your code
# Set model weights
W1 = tf.Variable(rng.randn(), [n_samples,3])
b = tf.Variable(rng.randn(), [n_samples])
My suggested change
initial1 = tf.constant(rng.randn(), dtype=tf.float32, shape=[n_samples,3])
initial2 = tf.constant(rng.randn(), dtype=tf.float32, shape=[n_samples,3])
W1 = tf.Variable(initial_value=initial1)
b = tf.Variable(initial_value=initial2)
In answer to the additional issues which arise after fixing the initial question the following code runs - but there still might be some logical error which you need to think about - like your #display logs per epoch step.
from __future__ import print_function
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import csv
import pandas
rng = np.random
# Parameters
learning_rate = 0.01
training_epochs = 1000
display_step = 50
# Training Data
#Created some fake data
dataframe = [[230.1,37.8,69.2,22.1],[2230.1,32.8,61.2,21.1]] #pandas.read_csv("Advertising.csv", delim_whitespace=True, header=None)
dataset = dataframe
X1,X2,X3,y1 = [],[],[],[]
for i in range(0,len(dataset)):
X = dataset[i][0]
X1.append(np.float32(dataset[i][0]))
X2.append(np.float32(dataset[i][1]))
X3.append(np.float32(dataset[i][2]))
y1.append(np.float32(dataset[i][3]))
#X=np.array([X1,X2,X3])
X = np.column_stack((X1,X2,X3)) ##MYEDIT: This combines all three values. If you find you need to stack in a different way then you will need to ensure the shapes below match this shape.
#X = np.column_stack((X,X3))
n_samples = len(X1)
#print(n_samples) = 17
# tf Graph Input
X_1 = tf.placeholder(tf.float32, [ None,3])##MYEDIT: Changed order
Y = tf.placeholder(tf.float32, [None])
# Set model weights
initial1 = tf.constant(rng.randn(), dtype=tf.float32, shape=[3,1]) ###MYEDIT: change order and you are only giving 1 sample at a time with your method of calling
initial2 = tf.constant(rng.randn(), dtype=tf.float32, shape=[3,1])
W1 = tf.Variable(initial_value=initial1)
b = tf.Variable(initial_value=initial2)
mul=tf.matmul(W1, X_1) ##MYEDIT: remove matmul from pred for clarity and shape checking
# Construct a linear model
pred = tf.add(mul, b)
# Mean squared error
cost = tf.reduce_sum(tf.pow(pred-Y, 2))/(2*n_samples)
# Gradient descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
# Initializing the variables
init = tf.global_variables_initializer()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
# Fit all training data
for epoch in range(training_epochs):
for (x1, y) in zip(X, y1):
Xformatted=np.array([x1]) #has shape (1,3) #MYEDIT: separated this to demonstrate shapes
yformatted=np.array([y]) #shape (1,) #MYEDIT: separated this to demonstrate shapes
#NB. X_1 shape is (?,3) and Y shape is (?,)
sess.run(optimizer, feed_dict={X_1: Xformatted, Y: yformatted})
# Display logs per epoch step
if (epoch+1) % display_step == 0:
c = sess.run(cost, feed_dict={X_1: Xformatted, Y: yformatted}) #NB. x1 an y are out of scope here - you will only get the last values. Double check if this is what you meant.
print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c), \
"Weights=", sess.run(W1),"b=", sess.run(b))
You need to feed a matrix into tf.matmul(W1, X_1). Check the types for your W1 and X_1 for your code.
See the question here for more details