Mnist model performing very badly on custom data - pytorch

I have used the resnet50 prebuilt and pretrained model from pytorch, on the MNIST dataset,
from torch import nn
from torchvision.models import ResNet50_Weights, resnet50
class Model(nn.Module):
def __init__(self):
super(Model, self).__init__()
self.model = resnet50(weights=ResNet50_Weights.DEFAULT)
self.model.conv1 = nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3, bias=False)
num_ftrs = self.model.fc.in_features
self.model.fc = nn.Linear(num_ftrs, 10)
def forward(self, x):
return self.model(x)
it performs very well and after training for 10 epochs it has achieved an incredible 99.895% accuracy on the 50,000 test images.
model.eval()
with torch.no_grad():
correct = 0
total = 0
for images, labels in train_loader:
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the {} train images: {} %'.format(50000, 100 * correct / total))
[out]: Accuracy of the network on the 50000 train images: 99.895 %
I have used pygame to easily create my own numbers to input to the model. I start off with a very basic program just placing circles while the left mouse button is held, then I save the generated image into a png format.
if event.type == pg.MOUSEMOTION:
if (drawing):
mouse_position = pg.mouse.get_pos()
pg.draw.circle(screen, color, mouse_position, w)
elif event.type == pg.MOUSEBUTTONUP:
mouse_position = (0, 0)
drawing = False
last_pos = None
elif event.type == pg.MOUSEBUTTONDOWN:
drawing = True
I convert the image to grayscale and scale it down to 28x28 and into a tensor using PIL and torch.PILToTensor().
image = Image.open("image.png").convert("L").resize((28,28),Image.Resampling.LANCZOS)
transform = Compose([
PILToTensor(),
Lambda(lambda image: image.view(-1, 1, 28, 28))
])
img_tensor = transform(image).to(torch.float)
Then I feed this image to the network. I get no errors or anything the model just predicts really badly. For example when I gave it this
image of a 2
this code outputed:
with torch.no_grad():
outputs = model(img_tensor)
print(outputs)
_, predicted = torch.max(outputs.data, 1)
print(predicted)
[out]: tensor([[ 20.6237, 0.4952, -15.5033, 8.5165, 1.0938, 2.8278, 2.0153,
3.2825, -6.2655, -0.6992]])
tensor([0])
The sureness is outputted as list with the sureness for each class 0, 1, 2, 3... so as you can see the sureness for "2" is actually negative, does anyone know why this could be and how I could solve it?
Thank you very much

I have solved this, the problem was that when I converted the image to a tensor it had values from 0-255 instead of 0-1, that's why the model was behaving so unpredictably.

Related

Expected input batch_size (18) to match target batch_size (6)

Is RNN for image classification available only for gray image?
The following program works for gray image classification.
If RGB images are used, I have this error:
Expected input batch_size (18) to match target batch_size (6)
at this line loss = criterion(outputs, labels).
My data loading for train, valid and test are as follows.
input_size = 300
inputH = 300
inputW = 300
#Data transform (normalization & data augmentation)
stats = ((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
train_resize_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
tt.ToTensor(),
tt.Normalize(*stats)])
train_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
tt.RandomHorizontalFlip(),
tt.ToTensor(),
tt.Normalize(*stats)])
valid_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
tt.ToTensor(),
tt.Normalize(*stats)])
test_tfms = tt.Compose([tt.Resize((inputH, inputW), interpolation=2),
tt.ToTensor(),
tt.Normalize(*stats)])
#Create dataset
train_ds = ImageFolder('./data/train', train_tfms)
valid_ds = ImageFolder('./data/valid', valid_tfms)
test_ds = ImageFolder('./data/test', test_tfms)
from torch.utils.data.dataloader import DataLoader
batch_size = 6
#Training data loader
train_dl = DataLoader(train_ds, batch_size, shuffle = True, num_workers = 8, pin_memory=True)
#Validation data loader
valid_dl = DataLoader(valid_ds, batch_size, shuffle = True, num_workers = 8, pin_memory=True)
#Test data loader
test_dl = DataLoader(test_ds, 1, shuffle = False, num_workers = 1, pin_memory=True)
My model is as follows.
num_steps = 300
hidden_size = 256 #size of hidden layers
num_classes = 5
num_epochs = 20
learning_rate = 0.001
# Fully connected neural network with one hidden layer
num_layers = 2 # 2 RNN layers are stacked
class RNN(nn.Module):
def __init__(self, input_size, hidden_size, num_layers, num_classes):
super(RNN, self).__init__()
self.num_layers = num_layers
self.hidden_size = hidden_size
self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True, dropout=0.2)#batch must have first dimension
#our inpyt needs to have shape
#x -> (batch_size, seq, input_size)
self.fc = nn.Linear(hidden_size, num_classes)#this fc is after RNN. So needs the last hidden size of RNN
def forward(self, x):
#according to ducumentation of RNN in pytorch
#rnn needs input, h_0 for inputs at RNN (h_0 is initial hidden state)
#the following one is initial hidden layer
h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)#first one is number of layers and second one is batch size
#output has two outputs. The first tensor contains the output features of the hidden last layer for all time steps
#the second one is hidden state f
out, _ = self.rnn(x, h0)
#output has batch_size, num_steps, hidden size
#we need to decode hidden state only the last time step
#out (N, 30, 128)
#Since we need only the last time step
#Out (N, 128)
out = out[:, -1, :] #-1 for last time step, take all for N and 128
out = self.fc(out)
return out
stacked_rnn_model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)
# Loss and optimizer
criterion = nn.CrossEntropyLoss()#cross entropy has softmax at output
#optimizer = torch.optim.Adam(stacked_rnn_model.parameters(), lr=learning_rate) #optimizer used gradient optimization using Adam
optimizer = torch.optim.SGD(stacked_rnn_model.parameters(), lr=learning_rate)
# Train the model
n_total_steps = len(train_dl)
for epoch in range(num_epochs):
t_losses=[]
for i, (images, labels) in enumerate(train_dl):
# origin shape: [6, 3, 300, 300]
# resized: [6, 300, 300]
images = images.reshape(-1, num_steps, input_size).to(device)
print('images shape')
print(images.shape)
labels = labels.to(device)
# Forward pass
outputs = stacked_rnn_model(images)
print('outputs shape')
print(outputs.shape)
loss = criterion(outputs, labels)
t_losses.append(loss)
# Backward and optimize
optimizer.zero_grad()
loss.backward()
optimizer.step()
Printing images and outputs shapes are
images shape
torch.Size([18, 300, 300])
outputs shape
torch.Size([18, 5])
Where is the mistake?
Tl;dr: You are flattening the first two axes, namely batch and channels.
I am not sure you are taking the right approach but I will write about that layer.
In any case, let's look at the issue you are facing. You have a data loader that produces (6, 3, 300, 300), i.e. batches of 6 three-channel 300x300 images. By the look of it you are looking to reshape each batch element (3, 300, 300) into (step_size=300, -1).
However instead of that you are affecting the first axis - which you shouldn't - with images.reshape(-1, num_steps, input_size). This will have the desired effect when working with a single-channel images since dim=1 wouldn't be the "channel axis". In your case your have 3 channels, therefore, the resulting shape is: (6*3*300*300//300//300, 300, 300) which is (18, 300, 300) since num_steps=300 and input_size=300. As a result you are left with 18 batch elements instead of 6.
Instead what you want is to reshape with (batch_size, num_steps, -1). Leaving the last axis (a.k.a. seq_length) of variable size. This will result in a shape (6, 300, 900).
Here is a corrected and reduced snippet:
batch_size = 6
channels = 3
inputH, inputW = 300, 300
train_ds = TensorDataset(torch.rand(100, 3, inputH, inputW), torch.rand(100, 5))
train_dl = DataLoader(train_ds, batch_size)
class RNN(nn.Module):
def __init__(self, input_size, hidden_size, num_layers, num_classes):
super(RNN, self).__init__()
# (batch_size, seq, input_size)
self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True)
# (batch_size, hidden_size)
self.fc = nn.Linear(hidden_size, num_classes)
# (batch_size, num_classes)
def forward(self, x):
out, _ = self.rnn(x)
out = out[:, -1, :]
out = self.fc(out)
return out
num_steps = 300
input_size = inputH*inputW*channels//num_steps
hidden_size = 256
num_classes = 5
num_layers = 2
rnn = RNN(input_size, hidden_size, num_layers, num_classes)
for x, y in train_dl:
print(x.shape, y.shape)
images = images.reshape(batch_size, num_steps, -1)
print(images.shape)
outputs = rnn(images)
print(outputs.shape)
break
As I said in the beginning I am a bit wary about this approach because you are essentially feeding your RNN a RGB 300x300 image in the form of a sequence of 300 flattened vectors... I can't say if that makes sense and terms of training and if the model will be able to learn from that. I could be wrong!

Measuring uncertainty using MC Dropout on pytorch

I am trying to implement Bayesian CNN using Mc Dropout on Pytorch,
the main idea is that by applying dropout at test time and running over many forward passes , you get predictions from a variety of different models.
I’ve found an application of the Mc Dropout and I really did not get how they applied this method and how exactly they did choose the correct prediction from the list of predictions
here is the code
def mcdropout_test(model):
model.train()
test_loss = 0
correct = 0
T = 100
for data, target in test_loader:
if args.cuda:
data, target = data.cuda(), target.cuda()
data, target = Variable(data, volatile=True), Variable(target)
output_list = []
for i in xrange(T):
output_list.append(torch.unsqueeze(model(data), 0))
output_mean = torch.cat(output_list, 0).mean(0)
test_loss += F.nll_loss(F.log_softmax(output_mean), target, size_average=False).data[0] # sum up batch loss
pred = output_mean.data.max(1, keepdim=True)[1] # get the index of the max log-probability
correct += pred.eq(target.data.view_as(pred)).cpu().sum()
test_loss /= len(test_loader.dataset)
print('\nMC Dropout Test set: Average loss: {:.4f}, Accuracy: {}/{} ({:.2f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
train()
mcdropout_test()
I have replaced
data, target = Variable(data, volatile=True), Variable(target)
by adding
with torch.no_grad(): at the beginning
And this is how I have defined my CNN
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 192, 5, padding=2)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(192, 192, 5, padding=2)
self.fc1 = nn.Linear(192 * 8 * 8, 1024)
self.fc2 = nn.Linear(1024, 256)
self.fc3 = nn.Linear(256, 10)
self.dropout = nn.Dropout(p=0.3)
nn.init.xavier_uniform_(self.conv1.weight)
nn.init.constant_(self.conv1.bias, 0.0)
nn.init.xavier_uniform_(self.conv2.weight)
nn.init.constant_(self.conv2.bias, 0.0)
nn.init.xavier_uniform_(self.fc1.weight)
nn.init.constant_(self.fc1.bias, 0.0)
nn.init.xavier_uniform_(self.fc2.weight)
nn.init.constant_(self.fc2.bias, 0.0)
nn.init.xavier_uniform_(self.fc3.weight)
nn.init.constant_(self.fc3.bias, 0.0)
def forward(self, x):
x = self.pool(F.relu(self.dropout(self.conv1(x)))) # recommended to add the relu
x = self.pool(F.relu(self.dropout(self.conv2(x)))) # recommended to add the relu
x = x.view(-1, 192 * 8 * 8)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(self.dropout(x)))
x = self.fc3(self.dropout(x)) # no activation function needed for the last layer
return x
Can anyone help me to get the right implementation of the Monte Carlo Dropout method on CNN?
Implementing MC Dropout in Pytorch is easy. All that is needed to be done is to set the dropout layers of your model to train mode. This allows for different dropout masks to be used during the different various forward passes. Below is an implementation of MC Dropout in Pytorch illustrating how multiple predictions from the various forward passes are stacked together and used for computing different uncertainty metrics.
import sys
import numpy as np
import torch
import torch.nn as nn
def enable_dropout(model):
""" Function to enable the dropout layers during test-time """
for m in model.modules():
if m.__class__.__name__.startswith('Dropout'):
m.train()
def get_monte_carlo_predictions(data_loader,
forward_passes,
model,
n_classes,
n_samples):
""" Function to get the monte-carlo samples and uncertainty estimates
through multiple forward passes
Parameters
----------
data_loader : object
data loader object from the data loader module
forward_passes : int
number of monte-carlo samples/forward passes
model : object
keras model
n_classes : int
number of classes in the dataset
n_samples : int
number of samples in the test set
"""
dropout_predictions = np.empty((0, n_samples, n_classes))
softmax = nn.Softmax(dim=1)
for i in range(forward_passes):
predictions = np.empty((0, n_classes))
model.eval()
enable_dropout(model)
for i, (image, label) in enumerate(data_loader):
image = image.to(torch.device('cuda'))
with torch.no_grad():
output = model(image)
output = softmax(output) # shape (n_samples, n_classes)
predictions = np.vstack((predictions, output.cpu().numpy()))
dropout_predictions = np.vstack((dropout_predictions,
predictions[np.newaxis, :, :]))
# dropout predictions - shape (forward_passes, n_samples, n_classes)
# Calculating mean across multiple MCD forward passes
mean = np.mean(dropout_predictions, axis=0) # shape (n_samples, n_classes)
# Calculating variance across multiple MCD forward passes
variance = np.var(dropout_predictions, axis=0) # shape (n_samples, n_classes)
epsilon = sys.float_info.min
# Calculating entropy across multiple MCD forward passes
entropy = -np.sum(mean*np.log(mean + epsilon), axis=-1) # shape (n_samples,)
# Calculating mutual information across multiple MCD forward passes
mutual_info = entropy - np.mean(np.sum(-dropout_predictions*np.log(dropout_predictions + epsilon),
axis=-1), axis=0) # shape (n_samples,)
Moving on to the implementation which is posted in the question above, multiple predictions from T different forward passes are obtained by first setting the model to train mode (model.train()). Note that this is not desirable because unwanted stochasticity will be introduced in the predictions if there are layers other than dropout such as batch-norm in the model. Hence the best way is to just set the dropout layers to train mode as shown in the snippet above.

PyTorch nn.Transformer learns to copy target

I’m trying to train a Transformer Seq2Seq model using nn.Transformer class. I believe I am implementing it wrong, since when I train it, it seems to fit too fast, and during inference it repeats itself often. This seems like a masking issue in the decoder, and when I remove the target mask, the training performance is the same. This leads me to believe I am doing the target masking wrong. Here is my model code:
class TransformerModel(nn.Module):
def __init__(self,
vocab_size, input_dim, heads, feedforward_dim, encoder_layers, decoder_layers,
sos_token, eos_token, pad_token, max_len=200, dropout=0.5,
device=(torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu"))):
super(TransformerModel, self).__init__()
self.target_mask = None
self.embedding = nn.Embedding(vocab_size, input_dim, padding_idx=pad_token)
self.pos_embedding = nn.Embedding(max_len, input_dim, padding_idx=pad_token)
self.transformer = nn.Transformer(
d_model=input_dim, nhead=heads, num_encoder_layers=encoder_layers,
num_decoder_layers=decoder_layers, dim_feedforward=feedforward_dim,
dropout=dropout)
self.out = nn.Sequential(
nn.Linear(input_dim, feedforward_dim),
nn.ReLU(),
nn.Linear(feedforward_dim, vocab_size))
self.device = device
self.max_len = max_len
self.sos_token = sos_token
self.eos_token = eos_token
# Initialize all weights to be uniformly distributed between -initrange and initrange
def init_weights(self):
initrange = 0.1
self.encoder.weight.data.uniform_(-initrange, initrange)
self.decoder.bias.data.zero_()
self.decoder.weight.data.uniform_(-initrange, initrange)
# Generate mask covering the top right triangle of a matrix
def generate_square_subsequent_mask(self, size):
mask = (torch.triu(torch.ones(size, size)) == 1).transpose(0, 1)
mask = mask.float().masked_fill(mask == 0, float('-inf')).masked_fill(mask == 1, float(0.0))
return mask
def forward(self, src, tgt):
# src: (Max source seq len, batch size, 1)
# tgt: (Max target seq len, batch size, 1)
# Embed source and target with normal and positional embeddings
embedded_src = (self.embedding(src) +
self.pos_embedding(
torch.arange(0, src.shape[1]).to(self.device).unsqueeze(0).repeat(src.shape[0], 1)))
# Generate target mask
target_mask = self.generate_square_subsequent_mask(size=tgt.shape[0]).to(self.device)
embedded_tgt = (self.embedding(tgt) +
self.pos_embedding(
torch.arange(0, tgt.shape[1]).to(self.device).unsqueeze(0).repeat(tgt.shape[0], 1)))
# Feed through model
outputs = self.transformer(src=embedded_src, tgt=embedded_tgt, tgt_mask=target_mask)
outputs = F.log_softmax(self.out(outputs), dim=-1)
return outputs
For those having the same problem, my issue was that I wasn't properly adding the SOS token to the target I was feeding the model, and the EOS token to the target I was using in the loss function.
For reference:
The target fed to the model should be: [SOS] ....
And the target used for the loss should be: .... [EOS]

PyTorch CNN never converges (implementation issue suspected)

I am having trouble getting this network to work as desired. I have tried so many iterations of this model and yet cannot get a reasonable error (it never fits, can’t even get it to overfit).
Where have I gone wrong? Any help would be greatly appreciated
For reference, there are 12 input ‘images’ (they’re actually water surface elevation at 9 stations in an estuary) of shape 49,9 and 12 labels of shape 1,9.
Full examples with data can be found at https://gitlab.com/jb4earth/effonn/
net = []
class Net(torch.nn.Module):
def __init__(self, kernel_size):
super(Net, self).__init__()
mid_size = (49*49*9)
self.predict = torch.nn.Sequential(
nn.Conv2d(
in_channels=1,
out_channels=mid_size,
kernel_size=kernel_size,
stride=1,
padding=(0, 0)
),
nn.ReLU(),
nn.MaxPool2d(1),
nn.ReLU(),
nn.Conv2d(
in_channels=mid_size,
out_channels=1,
kernel_size=kernel_size,
stride=1,
padding=(0, 0)
),
nn.ReLU()
)
def forward(self, x):
x = self.predict(x)
return x
def train_network(x,y,optimizer,loss_func):
prediction = net(x)
loss = loss_func(prediction, y.squeeze())
optimizer.zero_grad()
loss.backward()
optimizer.step()
return prediction, loss
net = Net((1,1))
optimizer = torch.optim.Adam(net.parameters(), lr=0.01)
loss_func = torch.nn.MSELoss()
cnt = 0
t = True
while t == True:
# get_xy in place of DataLoader
(x,y) = get_xy(input_data,output_data,cnt)
# x.shape is 1,1,49,9
# y.shape is 1,1,1,9
# train and predict
(prediction,loss) = train_network(x,y,optimizer,loss_func)
# prediction shape different than desired so averaging all results
prediction_ = torch.mean(prediction)
# only 12 IO's so loop through
cnt += 1
if cnt > 11:
cnt = 0
take a look here, this looks suspicious. you are calculating the loss and then making the gradients zeros. calling zero grad should be called before calculating the loss. So you need to switch the optimizer.zero_grad() to the top and I assume it will work. I couldn't reproduce your example that's why I'm guessing this is your Error.
loss = loss_func(prediction, y.squeeze())
optimizer.zero_grad() # switch this to the top
loss.backward()
optimizer.step()

How do I obtain predictions and probabilities from new data input to a CNN in Tensorflow

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.

Resources