I am struggling to see inside an object in a spyder. when I run this snippet, in variable explorer I can see only the attached fig, however, I need to see the probs and other object tensor and also I need to access to the value of probs? any comment would appreciate.
import torch
from U_Net_demo import device
from dataset import test_loader
import matplotlib.pyplot as plt
from torchvision.utils import make_grid
import torch.nn as nn
import numpy
criterion = nn.NLLLoss()
def test():
model_load = torch.load('model.pth')
#test model
model_load.eval()
total = 0
test_loss = 0
correct = 0
count = 0
#iterate through test dataset
for ii, data in enumerate(test_loader):
t_image, mask = data
t_image, mask = t_image.to(device), mask.to(device)
with torch.no_grad():
outputs = model_load(t_image)
#print(outputs.shape) # torch.Size([1, 2, 240, 320])
test_loss += criterion(outputs, mask).item() / len(test_loader)
probs = torch.exp(outputs)
_, predicted = torch.max(outputs.data, 1)
total += mask.nelement()
correct += predicted.eq(mask.data).sum().item()
accuracy = 100 * correct / total
count +=1
print(count, "Test Loss: {:.3f}".format(test_loss), "Test Accuracy: %d %%" % (accuracy))
if __name__=='__main__':
test = test()
(Spyder maintainer here) Pytorch tensors are not supported in Spyder's Variable Explorer as of 2019/01.
Related
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
train_set = torchvision.datasets.MNIST(root = './data/MNIST',train = True,download = True,\transform = transfroms.Compose([transfroms.ToTensor()])
print(len(train_set))
# 60000
train_loader = torch.utils.data.DataLoader(train_set, batch_size=100)
print(len(train_loader))
# 600
It seems like because of the batch_size, length of train_loader decreased.
I think there are 100 tensors and one classification in a batch.
I just want to see the elements or shape of it. How can I do?
Also,
### Model Omitted ###
model = ConvNet().to(device)
criterion = nn.CrossEntropyLoss().to(device)
optimizer = torch.optim.Adam(model.parameters(), lr = learning_rate)
for epoch in range(5):
avg_cost = 0
for data, target in train_loader:
data = data.to(device)
target = target.to(device)
optimizer.zero_grad()
hypothesis = model(data)
cost = criterion(hypothesis, target)
cost.backward()
optimizer.step()
avg_cost += cost / len(train_loader)
print('[Epoch: {:>4}] cost = {:>.9}'.format(epoch + 1, avg_cost))
I think the training per epoch trains with 60,000 tensors right? Then I think the avg_cost should be divided by 60,000, not 600(which is len(train_loader))... Am I wrong with it?
You can get one batch of train data from trainloader using the code below and you can easily check it's shape. I hope this may help to get what you want.
batch= iter(trainloader)
images, labels = batch.next()
print(images.shape)
# torch.Size([num_samples, in_channels, H, W])
print(labels.shape)
I am new to Pytorch and am aiming to do an image classification task using a CNN based on the EMNIST dataset.
I read my data in as follows:
emnist = scipy.io.loadmat(DATA_DIR + '/emnist-letters.mat')
data = emnist ['dataset']
X_train = data ['train'][0, 0]['images'][0, 0]
X_train = X_train.reshape((-1,28,28), order='F')
y_train = data ['train'][0, 0]['labels'][0, 0]
X_test = data ['test'][0, 0]['images'][0, 0]
X_test = X_test.reshape((-1,28,28), order = 'F')
y_test = data ['test'][0, 0]['labels'][0, 0]
train_dataset = torch.utils.data.TensorDataset(torch.from_numpy(X_train), torch.from_numpy(y_train))
test_dataset = torch.utils.data.TensorDataset(torch.from_numpy(X_test), torch.from_numpy(y_test))
batch_size = 128
n_iters = 3000
num_epochs = n_iters / (len(train_dataset) / batch_size)
num_epochs = int(num_epochs)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
Then, I found the following configurations (that I still have to adjust to fit to my data):
class CNNModel(nn.Module):
def __init__(self):
super(CNNModel, self).__init__()
# Convolution 1
self.cnn1 = nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=0)
self.relu1 = nn.ReLU()
# Max pool 1
self.maxpool1 = nn.MaxPool2d(kernel_size=2)
# Convolution 2
self.cnn2 = nn.Conv2d(in_channels=16, out_channels=32, kernel_size=5, stride=1, padding=0)
self.relu2 = nn.ReLU()
# Max pool 2
self.maxpool2 = nn.MaxPool2d(kernel_size=2)
# Fully connected 1 (readout)
self.fc1 = nn.Linear(32 * 4 * 4, 10)
def forward(self, x):
# Convolution 1
out = self.cnn1(x)
out = self.relu1(out)
# Max pool 1
out = self.maxpool1(out)
# Convolution 2
out = self.cnn2(out)
out = self.relu2(out)
# Max pool 2
out = self.maxpool2(out)
# Resize
# Original size: (100, 32, 7, 7)
# out.size(0): 100
# New out size: (100, 32*7*7)
out = out.view(out.size(0), -1)
# Linear function (readout)
out = self.fc1(out)
return out
model = CNNModel()
criterion = nn.CrossEntropyLoss()
To train the model, I use the following code:
iter = 0
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
# Add a single channel dimension
# From: [batch_size, height, width]
# To: [batch_size, 1, height, width]
images = images.unsqueeze(1)
# Forward pass to get output/logits
outputs = model(images)
# Clear gradients w.r.t. parameters
optimizer.zero_grad()
# Forward pass to get output/logits
outputs = model(images)
# Calculate Loss: softmax --> cross entropy loss
loss = criterion(outputs, labels)
# Getting gradients w.r.t. parameters
loss.backward()
# Updating parameters
optimizer.step()
iter += 1
if iter % 500 == 0:
# Calculate Accuracy
correct = 0
total = 0
# Iterate through test dataset
for images, labels in test_loader:
images = images.unsqueeze(1)
# Forward pass only to get logits/output
outputs = model(images)
# Get predictions from the maximum value
_, predicted = torch.max(outputs.data, 1)
# Total number of labels
total += labels.size(0)
correct += (predicted == labels).sum()
accuracy = 100 * correct / total
# Print Loss
print('Iteration: {}. Loss: {}. Accuracy: {}'.format(iter, loss.data[0], accuracy))
However, when I run this, I get the following error:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-27-1fbdd53d1194> in <module>()
12
13 # Forward pass to get output/logits
---> 14 outputs = model(images)
15
16 # Clear gradients w.r.t. parameters
4 frames
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight)
348 _pair(0), self.dilation, self.groups)
349 return F.conv2d(input, weight, self.bias, self.stride,
--> 350 self.padding, self.dilation, self.groups)
351
352 def forward(self, input):
RuntimeError: value cannot be converted to type uint8_t without overflow: -0.0510302
I found this question already and think that the solution might work for me as well. However, I don't understand where in my code I can implement this.
What can I do to overcome this problem?
Ps.
I have used the following import statements:
import scipy .io
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision.datasets as dsets
from torch.autograd import Variable
import cv2
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
import numpy as np
import os
from PIL import Image
from PIL import ImageOps
from torchvision import datasets, transforms
from torch.autograd import Variable
import matplotlib.pyplot as plt
from torchvision.datasets import ImageFolder
from torch.utils.data import DataLoader
from torchvision.transforms import ToTensor
from torch.nn import Sequential
from torch.nn import Conv2d
from torch.nn import BatchNorm2d
from torch.nn import MaxPool2d
from torch.nn import ReLU
from torch.nn import Linear
What fixed my problem was replacing out = self.cnn1(x) with out = self.cnn1(x.float())
I'm learning to use pytorch and I got an error that won't let me continue programming.
My code:
import torch.nn as nn
from skorch import NeuralNetClassifier #integracao com sklearn
from sklearn.model_selection import cross_val_score,GridSearchCV
from sklearn.preprocessing import LabelEncoder, MinMaxScaler
import torch
import torch.nn.functional as F
from torch import nn,optim
class classificadorFinal(nn.Module):
def __init__(self, activation=F.tanh, neurons=16, initializer=torch.nn.init.uniform_, dropout=0.3):
##from melhores_parametros
super().__init__()
self.dense0 = nn.Linear(4, neurons)
initializer(self.dense0.weight)
self.activation0 = activation
self.dense1 = nn.Linear(neurons, neurons)
initializer(self.dense1.weight)
self.activation1 = activation
self.dense2 = nn.Linear(neurons, 3)
self.dropout = nn.Dropout(dropout)
def forward(self, X):
X = self.dense0(X)
X = self.activation0(X)
X = self.dropout(X)
X = self.dense1(X)
X = self.activation1(X)
X = self.dropout(X)
X = self.dense2(X)
return X
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(classificador.parameters(), lr = 0.001, weight_decay = 0.0001)
#treino
for epoch in range(200):##from melhores_parametros
running_loss = 0.
running_accuracy = 0.
for data in train_loader:
inputs, labels = data
optimizer.zero_grad()
outputs = classificadorFinal(inputs)
loss = criterion(outputs, labels)###erro
loss.backward()
optimizer.step()
running_loss += loss.item()
ps = F.softmax(outputs)
top_p, top_class = ps.topk(k = 1, dim = 1)
equals = top_class == labels.view(*top_class.shape)
running_accuracy += torch.mean(equals.type(torch.float))
print('Época {:3d}: perda {:3.5f} - precisão {:3.5f}'.format(epoch + 1, running_loss/len(train_loader), running_accuracy/len(train_loader)))
The error occurs exactly on loss = criterion(outputs, labels):
AttributeError: 'classificadorFinal' object has no attribute 'log_softmax'
I found out this error is well known, but I did not understand the proposed solution:
disable aux_logits when the model is created aux_logits=False.
A little help, please!
The outputs are not actually the output of the model, but rather the model itself. classificadorFinal is the class, calling it creates an object/instance of that class, and inputs will be the first argument to the __init__ method, namely activation.
# Creates an instance of the model
outputs = classificadorFinal(inputs)
You first have to create the model (an instance), which should be done once, then call that model with the inputs. It looks like you have already created the model before, as you are using classificador.parameters() for the optimiser, hence classificador is presumably the instance of the model. You need to call classificador (instance) not classificadorFinal (class) to create the outputs.
# Call the instance of the model, not the class
outputs = classificador(inputs)
Using this mnist image classification model :
%reset -f
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
import torch.utils.data as data_utils
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_moons
from matplotlib import pyplot
from pandas import DataFrame
import torchvision.datasets as dset
import os
import torch.nn.functional as F
import time
import random
import pickle
from sklearn.metrics import confusion_matrix
import pandas as pd
import sklearn
trans = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
root = './data'
if not os.path.exists(root):
os.mkdir(root)
train_set = dset.MNIST(root=root, train=True, transform=trans, download=True)
test_set = dset.MNIST(root=root, train=False, transform=trans, download=True)
batch_size = 64
train_loader = torch.utils.data.DataLoader(
dataset=train_set,
batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(
dataset=test_set,
batch_size=batch_size,
shuffle=True)
class NeuralNet(nn.Module):
def __init__(self):
super(NeuralNet, self).__init__()
self.fc1 = nn.Linear(28*28, 500)
self.fc2 = nn.Linear(500, 256)
self.fc3 = nn.Linear(256, 2)
def forward(self, x):
x = x.view(-1, 28*28)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
num_epochs = 2
random_sample_size = 200
values_0_or_1 = [t for t in train_set if (int(t[1]) == 0 or int(t[1]) == 1)]
values_0_or_1_testset = [t for t in test_set if (int(t[1]) == 0 or int(t[1]) == 1)]
print(len(values_0_or_1))
print(len(values_0_or_1_testset))
train_loader_subset = torch.utils.data.DataLoader(
dataset=values_0_or_1,
batch_size=batch_size,
shuffle=True)
test_loader_subset = torch.utils.data.DataLoader(
dataset=values_0_or_1_testset,
batch_size=batch_size,
shuffle=False)
train_loader = train_loader_subset
# Hyper-parameters
input_size = 100
hidden_size = 100
num_classes = 2
# learning_rate = 0.00001
learning_rate = .0001
# Device configuration
device = 'cpu'
print_progress_every_n_epochs = 1
model = NeuralNet().to(device)
# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
N = len(train_loader)
# Train the model
total_step = len(train_loader)
most_recent_prediction = []
test_actual_predicted_dict = {}
rm = random.sample(list(values_0_or_1), random_sample_size)
train_loader_subset = data_utils.DataLoader(rm, batch_size=4)
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader_subset):
# Move tensors to the configured device
images = images.reshape(-1, 2).to(device)
labels = labels.to(device)
# Forward pass
outputs = model(images)
loss = criterion(outputs, labels)
# Backward and optimize
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (epoch) % print_progress_every_n_epochs == 0:
print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
predicted_test = []
model.eval() # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
probs_l = []
predicted_values = []
actual_values = []
labels_l = []
with torch.no_grad():
for images, labels in test_loader_subset:
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
predicted_test.append(predicted.cpu().numpy())
sm = torch.nn.Softmax()
probabilities = sm(outputs)
probs_l.append(probabilities)
labels_l.append(labels.cpu().numpy())
predicted_values.append(np.concatenate(predicted_test).ravel())
actual_values.append(np.concatenate(labels_l).ravel())
if (epoch) % 1 == 0:
print('test accuracy : ', 100 * len((np.where(np.array(predicted_values[0])==(np.array(actual_values[0])))[0])) / len(actual_values[0]))
I'm to attempting to integrate 'Local Interpretable Model-Agnostic Explanations for machine learning classifiers' : https://marcotcr.github.io/lime/
It appears PyTorch support is not enabled as it is not mentioned in doc and following tutorial :
https://marcotcr.github.io/lime/tutorials/Tutorial%20-%20images.html
With my updated code for PyTorch :
from lime import lime_image
import time
explainer = lime_image.LimeImageExplainer()
explanation = explainer.explain_instance(images[0].reshape(28,28), model(images[0]), top_labels=5, hide_color=0, num_samples=1000)
Causes error :
/opt/conda/lib/python3.6/site-packages/skimage/color/colorconv.py in gray2rgb(image, alpha)
830 is_rgb = False
831 is_alpha = False
--> 832 dims = np.squeeze(image).ndim
833
834 if dims == 3:
AttributeError: 'Tensor' object has no attribute 'ndim'
So appears tensorflow object is expected here ?
How to integrate LIME with PyTorch image classification ?
Here's my solution:
Lime expects an image input of type numpy. This is why you get the attribute error and a solution would be to convert the image (from Tensor) to numpy before passing it to the explainer object. Another solution would be to select a specific image with the test_loader_subset and convert it with img = img.numpy().
Secondly, in order to make LIME work with pytorch (or any other framework), you'll need to specify a batch prediction function which outputs the prediction scores of each class for each image. The name of this function (here I've called it batch_predict) is then passed to explainer.explain_instance(img, batch_predict, ...). The batch_predict needs to loop through all images passed to it, convert them to Tensor, make a prediction and finally return the prediction score list (with numpy values). This is how I got it working.
Note also that the images need to have shape (... ,... ,3) or (... ,... ,1) in order to be properly segmented by the default segmentation algorithm. This means that you might have to use np.transpose(img, (...)). You may specify the segmentation algorithm as well if the results are poor.
Finally you'll need to display the LIME image mask on top of the original image. This snippet shows how this may be done:
from skimage.segmentation import mark_boundaries
temp, mask = explanation.get_image_and_mask(explanation.top_labels[0], positive_only=False, num_features=5, hide_rest=False)
img_boundry = mark_boundaries(temp, mask)
plt.imshow(img_boundry)
plt.show()
This notebook is a good reference:
https://github.com/marcotcr/lime/blob/master/doc/notebooks/Tutorial%20-%20images%20-%20Pytorch.ipynb
I am trying to use 20 news groups data set available in sklearn to train a LSTM to do incremental learning (classification). I used the sklearn's TfidfVectorizer to pre-process the data. Then I turned the resulting sparse matrix into a numpy array before feeding it. After that when coding the below line:
outputs, final_state = tf.nn.dynamic_rnn(cell, inputs_, initial_state=initial_state)
It gave an error saying that the 'inputs_' should have 3 dimensions. so I used:
inputs_ = tf.expand_dims(inputs_, 0)
To expand the dimension. But when I do that i get the error:
ValueError: Input size (depth of inputs) must be accessible via shape
inference, but saw value None.
The shape of 'input_' is:
(1, 134410)
I already went through this post, but it did not help.
I cannot seem to understand how to solve this issue. Any help is much appreciated. Thank you in advance!
show below is my complete code:
import os
from collections import Counter
import tensorflow as tf
import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.datasets import fetch_20newsgroups
import matplotlib as mplt
from matplotlib import cm
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec
from sklearn.metrics import f1_score, recall_score, precision_score
from string import punctuation
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer
def pre_process():
newsgroups_data = fetch_20newsgroups(subset='all', remove=('headers', 'footers', 'quotes'))
vectorizer = TfidfVectorizer()
features = vectorizer.fit_transform(newsgroups_data.data)
lb = LabelBinarizer()
labels = np.reshape(newsgroups_data.target, [-1])
labels = lb.fit_transform(labels)
return features, labels
def get_batches(x, y, batch_size=1):
for ii in range(0, len(y), batch_size):
yield x[ii:ii + batch_size], y[ii:ii + batch_size]
def plot_error(errorplot, datapoint, numberOfWrongPreds):
errorplot.set_xdata(np.append(errorplot.get_xdata(), datapoint))
errorplot.set_ydata(np.append(errorplot.get_ydata(), numberOfWrongPreds))
errorplot.autoscale(enable=True, axis='both', tight=None)
plt.draw()
def train_test():
features, labels = pre_process()
#Defining Hyperparameters
epochs = 1
lstm_layers = 1
batch_size = 1
lstm_size = 30
learning_rate = 0.003
print(lstm_size)
print(batch_size)
print(epochs)
#--------------placeholders-------------------------------------
# Create the graph object
graph = tf.Graph()
# Add nodes to the graph
with graph.as_default():
tf.set_random_seed(1)
inputs_ = tf.placeholder(tf.float32, [None,None], name = "inputs")
# labels_ = tf.placeholder(dtype= tf.int32)
labels_ = tf.placeholder(tf.int32, [None,None], name = "labels")
#getting dynamic batch size according to the input tensor size
# dynamic_batch_size = tf.shape(inputs_)[0]
#output_keep_prob is the dropout added to the RNN's outputs, the dropout will have no effect on the calculation of the subsequent states.
keep_prob = tf.placeholder(tf.float32, name = "keep_prob")
# Your basic LSTM cell
lstm = tf.contrib.rnn.BasicLSTMCell(lstm_size)
# Add dropout to the cell
drop = tf.contrib.rnn.DropoutWrapper(lstm, output_keep_prob=keep_prob)
#Stack up multiple LSTM layers, for deep learning
cell = tf.contrib.rnn.MultiRNNCell([drop] * lstm_layers)
# Getting an initial state of all zeros
initial_state = cell.zero_state(batch_size, tf.float32)
inputs_ = tf.expand_dims(inputs_, 0)
outputs, final_state = tf.nn.dynamic_rnn(cell, inputs_, initial_state=initial_state)
#hidden layer
hidden = tf.layers.dense(outputs[:, -1], units=25, activation=tf.nn.relu)
logit = tf.contrib.layers.fully_connected(hidden, 1, activation_fn=None)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logit, labels=labels_))
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost)
saver = tf.train.Saver()
# ----------------------------online training-----------------------------------------
with tf.Session(graph=graph) as sess:
tf.set_random_seed(1)
sess.run(tf.global_variables_initializer())
iteration = 1
state = sess.run(initial_state)
wrongPred = 0
errorplot, = plt.plot([], [])
for ii, (x, y) in enumerate(get_batches(features, labels, batch_size), 1):
feed = {inputs_: x.toarray(),
labels_: y,
keep_prob: 0.5,
initial_state: state}
predictions = tf.round(tf.nn.softmax(logit)).eval(feed_dict=feed)
print("----------------------------------------------------------")
print("Iteration: {}".format(iteration))
print("Prediction: ", predictions)
print("Actual: ",y)
pred = np.array(predictions)
print(pred)
print(y)
if not ((pred==y).all()):
wrongPred += 1
if ii % 27 == 0:
plot_error(errorplot,ii,wrongPred)
loss, states, _ = sess.run([cost, final_state, optimizer], feed_dict=feed)
print("Train loss: {:.3f}".format(loss))
iteration += 1
saver.save(sess, "checkpoints/sentiment.ckpt")
errorRate = wrongPred/len(labels)
print("ERROR RATE: ", errorRate )
if __name__ == '__main__':
train_test()
ValueError: Input size (depth of inputs) must be accessible via shape inference, but saw value None.
This error is given because you don't specify the size nor the amount of inputs.
I got the script working like this:
inputs_ = tf.placeholder(tf.float32, [1,None], name = "inputs")
inputs_withextradim = tf.expand_dims(inputs_, 2)
outputs, final_state = tf.nn.dynamic_rnn(cell, inputs_withextradim, initial_state=initial_state)