I'm trying to train Faster RCNN model. After training, I try to predict the result of image but the result is empty.
My data is w: 1600, h: 800, c: 3, classes: 7, bounding boxes:(x1, y1, x2, y2)
My model is below.
My model
import torchvision
from torchvision.models.detection.faster_rcnn import FastRCNNPredictor
from torchvision.models.detection.mask_rcnn import MaskRCNNPredictor
from torchvision.models.detection import FasterRCNN
from torchvision.models.detection.rpn import AnchorGenerator
def get_instance_segmentation_model(num_classes):
backbone = torchvision.models.vgg16(pretrained=True).features
backbone.out_channels = 512
anchor_generator = AnchorGenerator(sizes=((32, 64, 128, 256, 512),),
aspect_ratios=((0.5, 1.0, 2.0),))
roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=['0'],
output_size=7,
sampling_ratio=2)
model = FasterRCNN(backbone,
num_classes=2,
rpn_anchor_generator=anchor_generator,
box_roi_pool=roi_pooler)
in_features = model.roi_heads.box_predictor.cls_score.in_features
model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)
return model
device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
num_classes = 2
model = get_instance_segmentation_model(num_classes)
model.to(device)
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params, lr=0.005,
momentum=0.9, weight_decay=0.0005)
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=3,
gamma=0.1)
training
# let's train it for 10 epochs
num_epochs = 10
for epoch in range(num_epochs):
# train for one epoch, printing every 10 iterations
train_one_epoch(model, optimizer, train_data_loader, device, epoch, print_freq=10)
# update the learning rate
lr_scheduler.step()
# evaluate on the test dataset
evaluate(model, valid_data_loader, device=device)
prediction:
prediction
[{'boxes': tensor([], device='cuda:0', size=(0, 4)),
'labels': tensor([], device='cuda:0', dtype=torch.int64),
'scores': tensor([], device='cuda:0')}]
You should change the number of classes to
model = FasterRCNN(backbone,
num_classes=YOUR_CLASSES+1, # +1 is for the background
rpn_anchor_generator=anchor_generator,
box_roi_pool=roi_pooler)
Remember that the class 0 is reserved for the background, so your classes should start from 1.
Also, please make sure your network has converged during the training.
Related
I am trying to build a powerful image classifier.
But I have an issue. I use CIFRAS-100 dataset, and I trained a model from it.
Issue here that the correct classificatons are equal to 15%.
I tried continuing learn process, but after 2-3 attempts, model has not changed.
Code that I used for training:
import torch
import sys,os
import torchvision
import torchvision.transforms as transforms
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
batch_size = 4
trainset = torchvision.datasets.CIFAR100(root='./dataone', train=True,
download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR100(root='./dataone', train=False,
download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size,
shuffle=False, num_workers=2)
classes = ('aquatic mammals','fish','flowers','food containers','fruit and vegetables','household electrical devices','household furniture','insects','large carnivores','large man-made outdoor things','large natural outdoor scenes','large omnivores and herbivores','medium-sized mammals','non-insect invertebrates','people','reptiles','small mammals','trees','vehicles 1','vehicles 2')
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 100)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = torch.flatten(x, 1) # flatten all dimensions except batch
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
import torch.optim as optim
PATH = "./model.pt"
model = Net()
net = Net()
print(os.path.exists(PATH))
if os.path.exists(PATH):
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
checkpoint = torch.load(PATH)
model.load_state_dict(checkpoint['model_state_dict'])
optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
epoch = checkpoint['epoch']
loss = checkpoint['loss']
print("using checkpoint")
#model.eval()
# - or -
model.train()
#criterion = nn.CrossEntropyLoss()
#optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
for epoch in range(2): # loop over the dataset multiple times
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
print("training..")
# print statistics
#running_loss += loss.item()
#if i % 2000 == 1999: # print every 2000 mini-batches
# print(f'[{epoch + 1}, {i + 1:5d}] loss: {running_loss / 2000:.3f}')
# running_loss = 0.0
print('Finished Training')
#PATH = './cifar_net.pth'
#torch.save(net.state_dict(), PATH)
EPOCH = 5
LOSS = 0.4
torch.save({
'epoch': EPOCH,
'model_state_dict': net.state_dict(),
'optimizer_state_dict': optimizer.state_dict(),
'loss': LOSS,
}, PATH)```
It's based on PyTorch tutorial about image cassifiers, that can be found [here](https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html).
I took code for resuming training from [here.](https://pytorch.org/tutorials/recipes/recipes/saving_and_loading_a_general_checkpoint.html)
Code that I used for testing model:
import torch
import torchvision
import torchvision.transforms as transforms
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
batch_size = 4
trainset = torchvision.datasets.CIFAR100(root='./dataone', train=False,
download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR100(root='./dataone', train=False,
download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size,
shuffle=False, num_workers=2)
classes = ('aquatic mammals','fish','flowers','food containers','fruit and vegetables','household electrical devices','household furniture','insects','large carnivores','large man-made outdoor things','large natural outdoor scenes','large omnivores and herbivores','medium-sized mammals','non-insect invertebrates','people','reptiles','small mammals','trees','vehicles 1','vehicles 2')
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 100)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = torch.flatten(x, 1) # flatten all dimensions except batch
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
PATH = './cifar_net.pth'
net.load_state_dict(torch.load(PATH))
correct = 0
total = 0
# since we're not training, we don't need to calculate the gradients for our outputs
with torch.no_grad():
for data in testloader:
images, labels = data
# calculate outputs by running images through the network
outputs = net(images)
# the class with the highest energy is what we choose as prediction
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print(correct)
print(total)
print(f'Accuracy of the network on the 100000 test images: {100 * correct // total} %')```
It's from the same image classifier tutorial by PyTorch. I added printing total and correct detected images for testing.
How can I increase accuracy, so it will be at least around 50-70%?
Or is this normal, and it means that these 15% are incorrect?
Please help.
Have you tried increasing the number of epochs? Training usually requires hundreds to thousands of iterations to obtain good results.
You could also improve the architecture by continuing the convolutional layers until you are left with a 1×1×N image where N is the number of filters in the final convolution. Then flatten and add linear layer(s). Batch Normalization and LeakyReLU activation before pooling layers may also help. Finally, you should use Softmax activation on the output since you are dealing with a classifier.
I highly recommend looking into popular classifiers such as VGG and ResNet. ResNet in particular has a feature called "residual/skip connections" that passes a copy of the output of a layer forward down the line to compensate for feature loss.
Could you provide accuracies and loss plots so we can understand better what is happening in the training (or maybe the list of accuracies and losses during training).
Also, it is a good practice to compute the validation accuracy and loss after every epoch to monitor the behaviour of the network on unseen data.
Although, as it has been said by Xynias, there are some improvements you could do on your architecture I believe the first step would be to investigate from the accuracies and losses.
Given CIFAR100 having 100 classes, this is expectable. You'll need a resonably complex network to perform well on this task. Definitely more feature maps, starting with 64 or more channels.
This Q&D architecture surpasses 50% overall accuracy after 10 epochs or so (using learning rate of 0.1 and batch size of 256, I also added RandomHorizontalFlip() transform):
class Net(nn.Module):
def __init__(self):
super().__init__()
self.layers = nn.Sequential(
nn.Conv2d(3, 128, 3, stride=1, padding=1),
nn.ReLU(),
nn.Conv2d(128, 128, 3, stride=1, padding=1),
nn.ReLU(),
nn.AvgPool2d(2, 2),
nn.Conv2d(128, 256, 3, stride=1, padding=1),
nn.ReLU(),
nn.Conv2d(256, 256, 3, stride=1, padding=1),
nn.ReLU(),
nn.AvgPool2d(2, 2),
nn.Flatten(),
nn.Dropout(0.5),
nn.Linear(16384, 100),
)
def forward(self, x):
return self.layers(x)
For a better result you may try implementing something ResNet-like, or utilize a premade (and possibly pretrained) model, for example, using timm:
import timm
net = timm.create_model('resnet18d', pretrained=True, num_classes=100)
It achieves your target metrics pretty fast with the same parameters as above.
I am using a simple autoencoder to learn images from the FashionMnist dataset. I have preprocessed the dataset by grayscaling and normalizing it. I did not make the network too deep, to prevent it from creating a direct mapping.
Here's my PyTorch code -
import torch
import torchvision as tv
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
from torch import nn
import os
from torchviz import make_dot
transforms = tv.transforms.Compose([tv.transforms.Grayscale(num_output_channels=1)])
trainset = tv.datasets.FashionMNIST(root='./data', train=True,
download=True, transform=transforms)
PATH = './ae.pth'
data = trainset.data.float()
data = data/255
# print(trainset.data.shape)
plt.imshow(trainset.data[0], cmap = 'gray')
plt.show()
class NeuralNetwork(nn.Module):
def __init__(self):
super(NeuralNetwork, self).__init__()
self.flatten = nn.Flatten()
self.encode = nn.Sequential(
nn.Linear(28*28, 512),
nn.ReLU(),
nn.Linear(512, 30),
nn.ReLU()
)
self.decode = nn.Sequential(
nn.Linear(30, 512),
nn.ReLU(),
nn.Linear(512, 28*28),
nn.Sigmoid()
)
def forward(self, x):
x = self.flatten(x)
encoded = self.encode(x)
decoded = self.decode(encoded)
return decoded
if(os.path.exists(PATH)):
print("Loading data on cpu")
device = torch.device('cpu')
model = NeuralNetwork()
model.load_state_dict(torch.load(PATH, map_location=device))
else:
device = "cuda" if torch.cuda.is_available() else "cpu"
data = data.to(device)
print(f"Using device = {device}")
model = NeuralNetwork().to(device)
# print(model)
lossFn = nn.BCELoss()
optimizer = torch.optim.SGD(model.parameters(), lr = 1e-3)
for epoch in range(1000):
print("Epoch = ", epoch)
optimizer.zero_grad()
outputs = model(data)
loss = lossFn(outputs, data.reshape(-1, 784))
loss.backward()
optimizer.step()
torch.save(model.state_dict(), PATH)
data = data.to("cpu")
model = model.to("cpu")
pred = model(data)
pred = pred.reshape(-1, 28, 28)
# print(pred.shape)
plt.imshow(pred.detach().numpy()[0], cmap = 'gray')
plt.show()
For testing, I am inputting the following image -
However, I get this as output -
I had an intuition that there was an issue with your loss function. When working with images, distance-based losses such as L1 or L2 losses work really well, as you are essentially measuring how far-away your predictions are from the ground-truth images. This was what I had observed as well, as the loss wasn't converging with BCE and it was rather oscillating.
I rewrote the entire thing and replaced BCE loss with MSE Loss and in just 50 epochs, the loss has gone down considerably, and it is still going down.
Here is the prediction after just 50 epochs -
The ground-truth image is -
I believe that you can get the loss down much more if you train for longer.
Here is the full code. I used a dataloader for batchifying and processing the data.
I also changed the transformations so that the resulting data is a torch tensor.
import torch
import torchvision as tv
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
from torch import nn
from torch.utils.data import DataLoader
transforms = tv.transforms.Compose([
transforms.Grayscale(num_output_channels=1),
transforms.ToTensor()
])
trainset = tv.datasets.FashionMNIST(root='./data', train=True,
download=True, transform=transforms)
loader = DataLoader(trainset, batch_size=32, num_workers=1, shuffle=True)
class NeuralNetwork(nn.Module):
def __init__(self):
super(NeuralNetwork, self).__init__()
self.flatten = nn.Flatten()
self.encode = nn.Sequential(
nn.Linear(28*28, 512),
nn.ReLU(),
nn.Linear(512, 30),
nn.ReLU()
)
self.decode = nn.Sequential(
nn.Linear(30, 512),
nn.ReLU(),
nn.Linear(512, 28*28),
nn.Sigmoid()
)
def forward(self, x):
x = self.flatten(x)
encoded = self.encode(x)
decoded = self.decode(encoded)
return decoded
model = NeuralNetwork().to(device)
lossFn = nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr = 1e-2)
epochs = 50
for epoch in range(epochs):
for images, labels in loader:
optimizer.zero_grad()
images, labels = images.to(device), labels.to(device)
outputs = model(images)
loss = lossFn(outputs, images.reshape(-1, 28*28))
loss.backward()
optimizer.step()
print(f'Loss : {loss.item()}')
print(f'Epochs done : {epoch}')
Here is some inference code -
# infer on some test data
testset = tv.datasets.FashionMNIST(root='./data', train=False,
download=False, transform=transforms)
testloader = DataLoader(testset, shuffle=False, batch_size=32, num_workers=1)
test_images, test_labels = next(iter(testloader))
test_images = test_images.to(device)
predictions = model(test_images)
prediction = predictions[0]
prediction = prediction.view(1, 28, 28)
prediction = prediction.detach().cpu().numpy()
prediction = prediction.transpose(1, 2, 0)
# plot the prediction
plt.imshow(prediction, cmap = 'gray')
plt.show()
# plot the actual image
test_image = test_images[0]
test_image = test_image.detach().cpu().numpy()
test_image = test_image.transpose(1, 2, 0)
plt.imshow(test_image, cmap='gray')
plt.show()
This is the loss going down --
Epochs done : 39
Loss : 0.04641226679086685
Epochs done : 40
Loss : 0.04445071145892143
Epochs done : 41
Loss : 0.05033266171813011
Epochs done : 42
Loss : 0.04813298210501671
Epochs done : 43
Loss : 0.0474831722676754
Epochs done : 44
Loss : 0.044186390936374664
Epochs done : 45
Loss : 0.049083154648542404
Epochs done : 46
Loss : 0.04645842686295509
Epochs done : 47
Loss : 0.04586248844861984
Epochs done : 48
Loss : 0.0467853844165802
Epochs done : 49
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import matplotlib.pyplot as plt
import numpy as np
import torch.optim as optim
class NeuralNetwork(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(1, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 3)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = torch.flatten(x, 1) # flatten all dimensions except batch
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = NeuralNetwork()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
from torchvision import datasets, transforms
from torch.utils.data import DataLoader, random_split
def UploadData(path, train):
#set up transforms for train and test datasets
train_transforms = transforms.Compose([transforms.Grayscale(num_output_channels=1), transforms.Resize(255), transforms.CenterCrop(224), transforms.RandomRotation(30),
transforms.RandomHorizontalFlip(), transforms.transforms.ToTensor()])
valid_transforms = transforms.Compose([transforms.Grayscale(num_output_channels=1), transforms.Resize(255), transforms.CenterCrop(224), transforms.RandomRotation(30),
transforms.RandomHorizontalFlip(), transforms.transforms.ToTensor()])
test_transforms = transforms.Compose([transforms.Grayscale(num_output_channels=1), transforms.Resize(255), transforms.CenterCrop(224), transforms.ToTensor()])
#set up datasets from Image Folders
train_dataset = datasets.ImageFolder(path + '/train', transform=train_transforms)
valid_dataset = datasets.ImageFolder(path + '/validation', transform=valid_transforms)
test_dataset = datasets.ImageFolder(path + '/test', transform=test_transforms)
#set up dataloaders with batch size of 32
trainloader = torch.utils.data.DataLoader(train_dataset, batch_size=32, shuffle=True)
validloader = torch.utils.data.DataLoader(valid_dataset, batch_size=32, shuffle=True)
testloader = torch.utils.data.DataLoader(test_dataset, batch_size=32, shuffle=True)
return trainloader, validloader, testloader
trainloader, validloader, testloader = UploadData("/home/lns/research/dataset", True)
epochs = 5
min_valid_loss = np.inf
for e in range(epochs):
train_loss = 0.0
for data, labels in trainloader:
# Transfer Data to GPU if available
if torch.cuda.is_available():
print("using GPU for data")
data, labels = data.cuda(), labels.cuda()
# Clear the gradients
optimizer.zero_grad()
# Forward Pass
target = net(data)
# Find the Loss
loss = criterion(target,labels)
# Calculate gradients
loss.backward()
# Update Weights
optimizer.step()
# Calculate Loss
train_loss += loss.item()
valid_loss = 0.0
model.eval() # Optional when not using Model Specific layer
for data, labels in validloader:
# Transfer Data to GPU if available
if torch.cuda.is_available():
print("using GPU for data")
data, labels = data.cuda(), labels.cuda()
# Forward Pass
target = net(data)
# Find the Loss
loss = criterion(target,labels)
# Calculate Loss
valid_loss += loss.item()
print('Epoch ',e+1, '\t\t Training Loss: ',train_loss / len(trainloader),' \t\t Validation Loss: ',valid_loss / len(validloader))
if min_valid_loss > valid_loss:
print("Validation Loss Decreased(",min_valid_loss,"--->",valid_loss,") \t Saving The Model")
min_valid_loss = valid_loss
# Saving State Dict
torch.save(net.state_dict(), '/home/lns/research/MODEL.pth')
After searching a lot i am asking for help. Can someone help me
understand why this error is occuring in backward propagation.
i followed pytorch cnn tutorail and geeksforgeeks tutorial
dataset is x ray images transformed into grayscale and resize to 255
Is my neural network is wrong or data is not processed correctly?
This is a size mismmatch between the output of your CNN and the number of neurons on on your first fully-connected layer. Because of missing padding, the number of elements when flattened is 16*4*4 i.e. 256 (and not 16*5*5):
self.fc1 = nn.Linear(256, 120)
Once modified, the model will run correctly:
>>> model = NeuralNetwork()
>>> model(torch.rand(1, 1, 28, 28)).shape
torch.Size([1, 3])
Alternatively, you can use an nn.LazyLinear which will deduce the in_feature argument during the very first inference based on its input shape.
self.fc1 = nn.LazyLinear(120)
I am using Python 3.7.5 and TensorFlow 2.0's 'GradientTape' API for classification of MNIST dataset using 300 100 dense fully connected architecture. I would like to use TensorFlow's 'EarlyStopping' with GradientTape() so that the training stops according to the variable being watched or monitored and according to patience parameters.
The code I have is below:
# Use tf.data to batch and shuffle the dataset
train_ds = tf.data.Dataset.from_tensor_slices((X_train, y_train)).shuffle(100).batch(batch_size)
test_ds = tf.data.Dataset.from_tensor_slices((X_test, y_test)).batch(batch_size)
# Choose an optimizer and loss function for training-
loss_fn = tf.keras.losses.BinaryCrossentropy()
optimizer = tf.keras.optimizers.Adam(lr = 0.001)
def create_nn_gradienttape():
"""
Function to create neural network for use
with GradientTape API following MNIST
300 100 architecture
"""
model = Sequential()
model.add(
Dense(
units = 300, activation = 'relu',
kernel_initializer = tf.keras.initializers.GlorotNormal,
input_shape = (784,)
)
)
model.add(
Dense(
units = 100, activation = 'relu',
kernel_initializer = tf.keras.initializers.GlorotNormal
)
)
model.add(
Dense(
units = 10, activation = 'softmax'
)
)
return model
# Instantiate the model to be trained using GradientTape-
model = create_nn_gradienttape()
# Select metrics to measure the error & accuracy of model.
# These metrics accumulate the values over epochs and then
# print the overall result-
train_loss = tf.keras.metrics.Mean(name = 'train_loss')
train_accuracy = tf.keras.metrics.BinaryAccuracy(name = 'train_accuracy')
test_loss = tf.keras.metrics.Mean(name = 'test_loss')
test_accuracy = tf.keras.metrics.BinaryAccuracy(name = 'train_accuracy')
# Use tf.GradientTape to train the model-
#tf.function
def train_step(data, labels):
"""
Function to perform one step of Gradient
Descent optimization
"""
with tf.GradientTape() as tape:
# 'training=True' is only needed if there are layers with different
# behavior during training versus inference (e.g. Dropout).
# predictions = model(data, training=True)
predictions = model(data)
loss = loss_fn(labels, predictions)
# 'gradients' is a list variable!
gradients = tape.gradient(loss, model.trainable_variables)
# IMPORTANT:
# Multiply mask with computed gradients-
# List to hold element-wise multiplication between-
# computed gradient and masks-
grad_mask_mul = []
# Perform element-wise multiplication between computed gradients and masks-
for grad_layer, mask in zip(gradients, mask_model_stripped.trainable_weights):
grad_mask_mul.append(tf.math.multiply(grad_layer, mask))
# optimizer.apply_gradients(zip(gradients, model.trainable_variables))
optimizer.apply_gradients(zip(grad_mask_mul, model.trainable_variables))
train_loss(loss)
train_accuracy(labels, predictions)
#tf.function
def test_step(data, labels):
"""
Function to test model performance
on testing dataset
"""
# training=False is only needed if there are layers with different
# behavior during training versus inference (e.g. Dropout).
predictions = model(data)
t_loss = loss_fn(labels, predictions)
test_loss(t_loss)
test_accuracy(labels, predictions)
EPOCHS = 15
for epoch in range(EPOCHS):
# Reset the metrics at the start of the next epoch
train_loss.reset_states()
train_accuracy.reset_states()
test_loss.reset_states()
test_accuracy.reset_states()
for x, y in train_ds:
train_step(x, y)
for x_t, y_t in test_ds:
test_step(x_t, y_t)
template = 'Epoch {0}, Loss: {1:.4f}, Accuracy: {2:.4f}, Test Loss: {3:.4f}, Test Accuracy: {4:4f}'
print(template.format(epoch + 1,
train_loss.result(), train_accuracy.result()*100,
test_loss.result(), test_accuracy.result()*100))
# Count number of non-zero parameters in each layer and in total-
# print("layer-wise manner model, number of nonzero parameters in each layer are: \n")
model_sum_params = 0
for layer in model.trainable_weights:
# print(tf.math.count_nonzero(layer, axis = None).numpy())
model_sum_params += tf.math.count_nonzero(layer, axis = None).numpy()
print("Total number of trainable parameters = {0}\n".format(model_sum_params))
In the code above, How can I use 'tf.keras.callbacks.EarlyStopping' with GradientTape() API ?
Thanks!
I have executed the following code and getting the error shown at extreme bottom. I would like to know how to resolve this. thanks
import torch.nn as nn
import torch.nn.functional as F
from torch import optim
from torchvision import transforms
_tasks = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
from torchvision.datasets import MNIST
mnist = MNIST("data", download=True, train=True, transform=_tasks)
from torch.utils.data import DataLoader
from torch.utils.data.sampler import SubsetRandomSampler
create training and validation split
split = int(0.8 * len(mnist))
index_list = list(range(len(mnist)))
train_idx, valid_idx = index_list[:split], index_list[split:]
create sampler objects using SubsetRandomSampler
tr_sampler = SubsetRandomSampler(train_idx)
val_sampler = SubsetRandomSampler(valid_idx)
create iterator objects for train and valid datasets
trainloader = DataLoader(mnist, batch_size=256, sampler=tr_sampler)
validloader = DataLoader(mnist, batch_size=256, sampler=val_sampler)
Creating model for execution
class Model(nn.Module):
def init(self):
super().init()
self.hidden = nn.Linear(784, 128)
self.output = nn.Linear(128, 10)
def forward(self, x):
x = self.hidden(x)
x = F.sigmoid(x)
x = self.output(x)
return x
model = Model()
loss_function = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, weight_decay= 1e-6, momentum = 0.9, nesterov = True)
for epoch in range(1, 11): ## run the model for 10 epochs
train_loss, valid_loss = [], []
#training part
model.train()
for data, target in trainloader:
optimizer.zero_grad()
#1. forward propagation
output = model(data)
#2. loss calculation
loss = loss_function(output, target)
#3. backward propagation
loss.backward()
#4. weight optimization
optimizer.step()
train_loss.append(loss.item())
# evaluation part
model.eval()
for data, target in validloader:
output = model(data)
loss = loss_function(output, target)
valid_loss.append(loss.item())
Executing this I am getting the following error :
RuntimeError Traceback (most recent call last) in ()
----> 1 output = model(data) 2 3 ## 2. loss calculation 4 loss = loss_function(output, target) 5
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in
call(self, *input, **kwargs) 487 result = self._slow_forward(*input,
**kwargs)
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in
linear(input, weight, bias) 1352 ret =
torch.addmm(torch.jit._unwrap_optional(bias), input, weight.t()) 1353
else:
-> 1354 output = input.matmul(weight.t()) 1355 if bias is not None: 1356 output += torch.jit._unwrap_optional(bias)
RuntimeError: size mismatch, m1: [3584 x 28], m2: [784 x 128] at
/pytorch/aten/src/TH/generic/THTensorMath.cpp:940
Your input MNIST data has shape [256, 1, 28, 28] corresponding to [B, C, H, W]. You need to flatten the input images into a single 784 long vector before feeding it to the Linear layer Linear(784, 128) such that the input becomes [256, 784] corresponding to [B, N], where N is 1x28x28, your image size. This can be done as follows:
for data, target in trainloader:
# Flatten MNIST images into a 784 long vector
data = data.view(data.shape[0], -1)
optimizer.zero_grad()
...
The same is needed to be done in the validation loop.