I’ve made a custom CNN in PyTorch for classifying 10 classes in the CIFAR-10 dataset. My classification accuracy on the test dataset is 45.739%, this is very low and I thought it’s because my model is not very deep but I implemented the same model in Keras and the classification accuracy come outs to be 78.92% on test dataset. No problem in Keras however I think there's something I'm missing in my PyTorch program.
I have used the same model architecture, strides, padding, dropout rate, optimizer, loss function, learning rate, batch size, number of epochs on both PyTorch and Keras and despite that, the difference in the classification accuracy is still huge thus I’m not able to decide how I should debug my PyTorch program further.
For now I suspect 3 things: in Keras, I use the categorical cross entropy loss function (one hot vector labels) and in PyTorch I use the standard cross entropy loss function (scalar indices labels), can this be a problem?, if not then I suspect either my training loop or the code for calculating classification accuracy in PyTorch. I have attached both my programs below, will be grateful to any suggestions.
My program in Keras:
#================Function that defines the CNN model===========
def CNN_model():
model = Sequential()
model.add(Conv2D(32,(3,3),activation='relu',padding='same', input_shape=(size,size,channels))) #SAME PADDING
model.add(Conv2D(32,(3,3),activation='relu')) #VALID PADDING
model.add(MaxPooling2D(pool_size=(2,2))) #VALID PADDING
model.add(Dropout(0.25))
model.add(Conv2D(64,(3,3),activation='relu', padding='same')) #SAME PADDING
model.add(Conv2D(64,(3,3),activation='relu')) #VALID PADDING
model.add(MaxPooling2D(pool_size=(2,2))) #VALID PADDING
model.add(Dropout(0.25))
model.add(Conv2D(128,(3,3),activation='relu', padding='same')) #SAME PADDING
model.add(Conv2D(128,(3,3),activation='relu')) #VALID PADDING
model.add(MaxPooling2D(pool_size=(2,2),name='feature_extractor_layer')) #VALID PADDING
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(512, activation='relu', name='second_last_layer'))
model.add(Dropout(0.25))
model.add(Dense(10, activation='softmax', name='softmax_layer')) #10 nodes in the softmax layer
model.summary()
return model
#=====Main program starts here========
#get_train_data() and get_test_data() are my own custom functions to get CIFAR-10 dataset
images_train, labels_train, class_train = get_train_data(0,10)
images_test, labels_test, class_test = get_test_data(0,10)
model = CNN_model()
model.compile(loss='categorical_crossentropy', #loss function of the CNN
optimizer=Adam(lr=1.0e-4), #Optimizer
metrics=['accuracy'])#'accuracy' metric is to be evaluated
#images_train and images_test contain images and
#class_train and class_test contains one hot vectors labels
model.fit(images_train,class_train,
batch_size=128,
epochs=50,
validation_data=(images_test,class_test),
verbose=1)
scores=model.evaluate(images_test,class_test,verbose=0)
print("Accuracy: "+str(scores[1]*100)+"% \n")
My program in PyTorch:
#========DEFINE THE CNN MODEL=====
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 32, 3,1,1)#SAME PADDING
self.conv2 = nn.Conv2d(32,32,3,1,0)#VALID PADDING
self.pool1 = nn.MaxPool2d(2,2) #VALID PADDING
self.drop1 = nn.Dropout2d(0.25) #DROPOUT OF 0.25
self.conv3 = nn.Conv2d(32,64,3,1,1)#SAME PADDING
self.conv4 = nn.Conv2d(64,64,3,1,0)#VALID PADDING
self.pool2 = nn.MaxPool2d(2,2)#VALID PADDING
self.drop2 = nn.Dropout2d(0.25) #DROPOUT OF 0.25
self.conv5 = nn.Conv2d(64,128,3,1,1)#SAME PADDING
self.conv6 = nn.Conv2d(128,128,3,1,0)#VALID PADDING
self.pool3 = nn.MaxPool2d(2,2)#VALID PADDING
self.drop3 = nn.Dropout2d(0.25) #DROPOUT OF 0.25
self.fc1 = nn.Linear(128*2*2, 512)#128*2*2 IS OUTPUT DIMENSION AFTER THE PREVIOUS LAYER
self.drop4 = nn.Dropout(0.25) #DROPOUT OF 0.25
self.fc2 = nn.Linear(512,10) #10 output nodes
def forward(self, x):
x = F.relu(self.conv1(x))
x = F.relu(self.conv2(x))
x = self.pool1(x)
x = self.drop1(x)
x = F.relu(self.conv3(x))
x = F.relu(self.conv4(x))
x = self.pool2(x)
x = self.drop2(x)
x = F.relu(self.conv5(x))
x = F.relu(self.conv6(x))
x = self.pool3(x)
x = self.drop3(x)
x = x.view(-1,2*2*128) #FLATTENING OPERATION 2*2*128 IS OUTPUT AFTER THE PREVIOUS LAYER
x = F.relu(self.fc1(x))
x = self.drop4(x)
x = self.fc2(x) #LAST LAYER DOES NOT NEED SOFTMAX BECAUSE THE LOSS FUNCTION WILL TAKE CARE OF IT
return x
#=======FUNCTION TO CONVERT INPUT AND TARGET TO TORCH TENSORS AND LOADING INTO GPU======
def PrepareInputDataAndTargetData(device,images,labels,batch_size):
#GET MINI BATCH OF TRAINING IMAGES AND RESHAPE THE TORCH TENSOR FOR CNN PROCESSING
mini_batch_images = torch.tensor(images)
mini_batch_images = mini_batch_images.view(batch_size,3,32,32)
#GET MINI BATCH OF TRAINING LABELS, TARGET SHOULD BE IN LONG FORMAT SO CONVERT THAT TOO
mini_batch_labels = torch.tensor(labels)
mini_batch_labels = mini_batch_labels.long()
#FEED THE INPUT DATA AND TARGET LABELS TO GPU
mini_batch_images = mini_batch_images.to(device)
mini_batch_labels = mini_batch_labels.to(device)
return mini_batch_images,mini_batch_labels
#==========MAIN PROGRAM==========
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
#get_train_data() and get_test_data() are my own custom functions to get CIFAR-10 dataset
Images_train, Labels_train, Class_train = get_train_data(0,10)
Images_test, Labels_test, Class_test = get_test_data(0,10)
net = Net()
net = net.double() #https://discuss.pytorch.org/t/runtimeerror-expected-object-of-scalar-type-double-but-got-scalar-type-float-for-argument-2-weight/38961
print(net)
#MAP THE MODEL ONTO THE GPU
net = net.to(device)
#CROSS ENTROPY LOSS FUNCTION AND ADAM OPTIMIZER
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=1e-4)
#PREPARE THE DATALOADER
#Images_train contains images and Labels_trains contains indices i.e. 0,1,...,9
dataset = TensorDataset( Tensor(Images_train), Tensor(Labels_train) )
trainloader = DataLoader(dataset, batch_size= 128, shuffle=True)
#START TRAINING THE CNN MODEL FOR 50 EPOCHS
for epoch in range(0,50):
for i, data in enumerate(trainloader, 0):
inputs, labels = data
inputs = torch.tensor(inputs).double()
inputs = inputs.view(len(inputs),3,32,32) #RESHAPE THE IMAGES
labels = labels.long() #MUST CONVERT LABEL TO LONG FORMAT
#MAP THE INPUT AND LABELS TO THE GPU
inputs=inputs.to(device)
labels=labels.to(device)
#FORWARD PROP, BACKWARD PROP, PARAMETER UPDATE
optimizer.zero_grad()
outputs = net.forward(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
#CALCULATE CLASSIFICATION ACCURACY ON ALL 10 CLASSES
with torch.no_grad():
Images_class,Labels_class = PrepareInputDataAndTargetData(device,Images_test,Labels_test,len(Images_test))
network_outputs = net.forward(Images_class)
correct = (torch.argmax(network_outputs.data,1) == Labels_class.data).float().sum()
acc = float(100.0*(correct/len(Images_class)))
print("Accuracy is: "+str(acc)+"\n")
del Images_class
del Labels_class
del network_outputs
del correct
del acc
torch.cuda.empty_cache()
print("Done\n")
I am not fully aware of how the actual core backend works in both libraries however I suppose that the classification accuracy of any model should be almost the same regardless of the library.
Related
I've trained an LSTM model with 8 features and 1 output. I have one dataset and split it into two separate files to train and predict with the first half of the set, and then attempt to predict the second half of the set using the trained model from the first part of my dataset. My model predicts the trained and testing sets from the dataset I used to train the model pretty well (RMSE of around 5-7), however when I attempt to predict using the second half of the set I get very poor predictions (RMSE of around 50-60). How can I get my trained model to predict outside datasets well?
dataset at this link
file = r'/content/drive/MyDrive/only_force_pt1.csv'
df = pd.read_csv(file)
df.head()
X = df.iloc[:, 1:9]
y = df.iloc[:,9]
print(X.shape)
print(y.shape)
plt.figure(figsize = (20, 6), dpi = 100)
plt.plot(y)
WINDOW_LEN = 50
def window_size(size, inputdata, targetdata):
X = []
y = []
i=0
while(i + size) <= len(inputdata)-1:
X.append(inputdata[i: i+size])
y.append(targetdata[i+size])
i+=1
assert len(X)==len(y)
return (X,y)
X_series, y_series = window_size(WINDOW_LEN, X, y)
print(len(X))
print(len(X_series))
print(len(y_series))
X_train, X_val, y_train, y_val = train_test_split(np.array(X_series),np.array(y_series),test_size=0.3, shuffle = True)
X_val, X_test,y_val, y_test = train_test_split(np.array(X_val),np.array(y_val),test_size=0.3, shuffle = False)
n_timesteps, n_features, n_outputs = X_train.shape[1], X_train.shape[2],1
[verbose, epochs, batch_size] = [1, 300, 32]
input_shape = (n_timesteps, n_features)
model = Sequential()
# LSTM
model.add(LSTM(64, input_shape=input_shape, return_sequences = False))
model.add(Dropout(0.2))
model.add(Dense(64, activation='relu', kernel_regularizer=keras.regularizers.l2(0.001)))
#model.add(Dropout(0.2))
model.add(Dense(32, activation='relu', kernel_regularizer=keras.regularizers.l2(0.001)))
model.add(Dense(1, activation='relu'))
earlystopper = EarlyStopping(monitor='val_loss', min_delta=0, patience = 30, verbose =1, mode = 'auto')
model.summary()
model.compile(loss = 'mse', optimizer = Adam(learning_rate = 0.001), metrics=[tf.keras.metrics.RootMeanSquaredError()])
history = model.fit(X_train, y_train, batch_size = batch_size, epochs = epochs, verbose = verbose, validation_data=(X_val,y_val), callbacks = [earlystopper])
Second dataset:
tests = r'/content/drive/MyDrive/only_force_pt2.csv'
df_testing = pd.read_csv(tests)
X_testing = df_testing.iloc[:4038,1:9]
torque = df_testing.iloc[:4038,9]
print(X_testing.shape)
print(torque.shape)
plt.figure(figsize = (20, 6), dpi = 100)
plt.plot(torque)
X_testing = X_testing.to_numpy()
X_testing_series, y_testing_series = window_size(WINDOW_LEN, X_testing, torque)
X_testing_series = np.array(X_testing_series)
y_testing_series = np.array(y_testing_series)
scores = model.evaluate(X_testing_series, y_testing_series, verbose =1)
X_prediction = model.predict(X_testing_series, batch_size = 32)
If your model is working fine on training data but performs bad on validation data, then your model did not learn the "true" connection between input and output variables but simply memorized the corresponding output to your input. To tackle this you can do multiple things:
Typically you would use 80% of your data to train and 20% to test, this will present more data to the model, which should make it learn more of the true underlying function
If your model is too complex, it will have neurons which will just be used to memorize input-output data pairs. Try to reduce the complexity of your model (layers, neurons) to make it more simple, so that the remaining layers can really learn instead of memorize
Look into more detail on training performance here
I have created a simple pytorch classification model with sample datasets generated using sklearns make_classification. Even after training for thousands of epochs the accuracy of the model hovers between 30 and 40 percentage. During training itself the loss value is fluctuating very far and wide. I am wondering why this model is not learning, whether it's due to some logical error in the code.
import torch
from torch.utils.data import Dataset, DataLoader
import torch.nn as nn
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
X,y = make_classification(n_features=15,n_classes=5,n_informative=4)
DEVICE = torch.device('cuda')
epochs = 5000
class CustomDataset(Dataset):
def __init__(self,X,y):
self.X = torch.from_numpy(X)
self.y = torch.from_numpy(y)
def __len__(self):
return len(self.X)
def __getitem__(self, index):
X = self.X[index]
y = self.y[index]
return (X,y)
class Model(nn.Module):
def __init__(self):
super().__init__()
self.l1 = nn.Linear(15,10)
self.l2 = nn.Linear(10,5)
self.relu = nn.ReLU()
def forward(self,x):
x = self.l1(x)
x = self.relu(x)
x = self.l2(x)
x = self.relu(x)
return x
model = Model().double().to(DEVICE)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
loss_function = nn.CrossEntropyLoss()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
train_data = CustomDataset(X_train,y_train)
test_data = CustomDataset(X_test,y_test)
trainloader = DataLoader(train_data, batch_size=32, shuffle=True)
testloader = DataLoader(test_data, batch_size=32, shuffle=True)
for i in range(epochs):
for (x,y) in trainloader:
x = x.to(DEVICE)
y = y.to(DEVICE)
optimizer.zero_grad()
output = model(x)
loss = loss_function(output,y)
loss.backward()
optimizer.step()
if i%200==0:
print("epoch: ",i," Loss: ",loss.item())
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 x, y in testloader:
# calculate outputs by running x through the network
outputs = model(x.to(DEVICE)).to(DEVICE)
# the class with the highest energy is what we choose as prediction
_, predicted = torch.max(outputs.data, 1)
total += y.size(0)
correct += (predicted == y.to(DEVICE)).sum().item()
print(f'Accuracy of the network on the test data: {100 * correct // total} %')
EDIT
I tried to over-fit my model with only 10 samples (batch_size=5) X,y = make_classification(n_samples=10,n_features=15,n_classes=5,n_informative=4) but now the accuracy decreased to 15-20%. I then normalize the input data between the values 0 and 1 which pushed the accuracy a bit higher but not over 50 percentage. Any idea why this might be happening?
You should not be using ReLU activation on your output layer. Usually softmax activation is used for multi class classification on the final layer, or the logits are fed to the loss function directly without explicitly adding a softmax activation layer.
Try removing the ReLU activation from the final layer.
I am trying to classify 2 classes of images. Though I am getting high train and validation accuracy (0.97) after 10 epochs, my test results are awful (precision 0.48) and the confusion matrix shows the network is predicting the images for the wrong class (attached results).
There are only 2 classes in the dataset, each class has 10,000 image examples (after augmentation). I am using the VGG16 network. The full dataset is split 20% to test set (this split was performed by taking random images from each class therefore it is shuffled). The remaining images are split to 80% train and 20% valid sets (as indicated in the ImageDataGenerator line of the code). So in the end there are:
12,904 Train images belonging to 2 classes
3,224 Valid images belonging to 2 classes
4,032 Test images belonging to 2 classes
This is my code:
def CNN(CNN='VGG16', choice='predict', prediction='./dataset/Test/image.jpg'):
''' Train images using one of several CNNs '''
Train = './dataset/Train'
Tests = './dataset/Test'
shape = (224, 224)
epochs = 10
batches = 16
classes = []
for c in os.listdir(Train): classes.append(c)
IDG = keras.preprocessing.image.ImageDataGenerator(validation_split=0.2)
train = IDG.flow_from_directory(Train, target_size=shape, color_mode='rgb',
classes=classes, batch_size=batches, shuffle=True, subset='training')
valid = IDG.flow_from_directory(Train, target_size=shape, color_mode='rgb',
classes=classes, batch_size=batches, shuffle=True, subset='validation')
tests = IDG.flow_from_directory(Tests, target_size=shape, color_mode='rgb',
classes=classes, batch_size=batches, shuffle=True)
input_shape = train.image_shape
if CNN == 'VGG16' or 'vgg16':
model = VGG16(weights=None, input_shape=input_shape,
classes=len(classes))
elif CNN == 'VGG19' or 'vgg19':
model = VGG19(weights=None, input_shape=input_shape,
classes=len(classes))
elif CNN == 'ResNet50' or 'resnet50':
model = ResNet50(weights=None, input_shape=input_shape,
classes=len(classes))
elif CNN == 'DenseNet201' or 'densenet201':
model = DenseNet201(weights=None, input_shape=input_shape,
classes=len(classes))
model.compile(optimizer=keras.optimizers.SGD(
lr=1e-3,
decay=1e-6,
momentum=0.9,
nesterov=True),
loss='categorical_crossentropy',
metrics=['accuracy'])
Esteps = int(train.samples/train.next()[0].shape[0])
Vsteps = int(valid.samples/valid.next()[0].shape[0])
if choice == 'train':
history= model.fit_generator(train,
steps_per_epoch=Esteps,
epochs=epochs,
validation_data=valid,
validation_steps=Vsteps,
verbose=1)
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model Loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train', 'Validation'], loc='upper left')
plt.show()
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('Model Accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train', 'Validation'], loc='upper left')
plt.show()
Y_pred = model.predict_generator(tests, verbose=1)
y_pred = np.argmax(Y_pred, axis=1)
matrix = confusion_matrix(tests.classes, y_pred)
df_cm = pd.DataFrame(matrix, index=classes, columns=classes)
plt.figure(figsize=(10,7))
sn.heatmap(df_cm, annot=True)
print(classification_report(tests.classes,y_pred,target_names=classes))
model.save_weights('weights.h5')
elif choice == 'predict':
model.load_weights('./weights.h5')
img = image.load_img(prediction, target_size=shape)
im = image.img_to_array(img)
im = np.expand_dims(im, axis=0)
if CNN == 'VGG16' or 'vgg16':
im = keras.applications.vgg16.preprocess_input(im)
prediction = model.predict(im)
print(prediction)
elif CNN == 'VGG19' or 'vgg19':
im = keras.applications.vgg19.preprocess_input(im)
prediction = model.predict(im)
print(prediction)
elif CNN == 'ResNet50' or 'resnet50':
im = keras.applications.resnet50.preprocess_input(im)
prediction = model.predict(im)
print(prediction)
print(keras.applications.resnet50.decode_predictions(prediction))
elif CNN == 'DenseNet201' or 'densenet201':
im = keras.applications.densenet201.preprocess_input(im)
prediction = model.predict(im)
print(prediction)
print(keras.applications.densenet201.decode_predictions(prediction))
CNN(CNN='VGG16', choice='train')
Results:
precision recall f1-score support
Predator 0.49 0.49 0.49 2016
Omnivore 0.49 0.49 0.49 2016
accuracy -- -- 0.49 4032
I suspect that the ImageDataGenerator() is not shuffling the images "before" the train/valid split. If this is the case how can i force the ImageDataGenerator here in Keras to shuffle the dataset before the split?
If shuffling is not the case, how can i solve my issue? what am I doing wrong?
So your model is basically overfitting, which means that it is "memorizing" your training set. I have a few suggestions:
check that your 2 prediction classes are balanced in your training set. I.e. 50-50 split of 0 and 1. For example, if 90% of your training data is labeled 0, then your model will simply predict everything to be 0 and get right in the validation 90% of the time.
if your training data is already balanced, it means that your model isn't generalizing. Perhaps you could try using the pre-trained model instead of custom training every layer of VGG? You can load the pre-trained weights of VGG but do not include top and train only the dense layers.
Use cross validation. Reshuffle the data in each validation and see whether results in the test set improve.
Somehow, the image generator of Keras works well when combined with fit() or fit_generator() function, but fails miserably when combined
with predict_generator() or the predict() function.
When using Plaid-ML Keras back-end for AMD processor, I would rather loop through all test images one-by-one and get the prediction for each image in each iteration.
import os
from PIL import Image
import keras
import numpy
# code for creating dan training model is not included
print("Prediction result:")
dir = "/path/to/test/images"
files = os.listdir(dir)
correct = 0
total = 0
#dictionary to label all animal category class.
classes = {
0:'This is Cat',
1:'This is Dog',
}
for file_name in files:
total += 1
image = Image.open(dir + "/" + file_name).convert('RGB')
image = image.resize((100,100))
image = numpy.expand_dims(image, axis=0)
image = numpy.array(image)
image = image/255
pred = model.predict_classes([image])[0]
animals_category = classes[pred]
if ("cat" in file_name) and ("cat" in sign):
print(correct,". ", file_name, animals_category)
correct+=1
elif ("dog" in file_name) and ("dog" in animals_category):
print(correct,". ", file_name, animals_category)
correct+=1
print("accuracy: ", (correct/total))
I am working on a binary classification problem on Keras. The loss function I use is binary_crossentropy and metrics is metrics=['accuracy']. Since two classes are imbalanced, I use class_weight='auto' when I fit training data set to the model.
To see the performance, I print out the accuracy by
print GNN.model.test_on_batch([test_sample_1, test_sample_2], test_label)[1]
The output is 0.973. But this result is different when I use following lines to get the prediction accuracy
predict_label = GNN.model.predict([test_sample_1, test_sample_2])
rounded = predict_label.round(1)
print (rounded == test_label).sum()/float(rounded.shape[0])
which is 0.953.
So I am wondering how metrics=['accuracy'] evaluate the model performance and why the result is different.
For details, I attached the model summary below.
input_size = self.n_feature
encoder_size = 2000
dropout_rate = 0.5
X1 = Input(shape=(input_size, ), name='input_1')
X2 = Input(shape=(input_size, ), name='input_2')
encoder = Sequential()
encoder.add(Dropout(dropout_rate, input_shape=(input_size, )))
encoder.add(Dense(encoder_size, activation='tanh'))
encoded_1 = encoder(X1)
encoded_2 = encoder(X2)
merged = concatenate([encoded_1, encoded_2])
comparer = Sequential()
comparer.add(Dropout(dropout_rate, input_shape=(encoder_size * 2, )))
comparer.add(Dense(500, activation='relu'))
comparer.add(Dropout(dropout_rate))
comparer.add(Dense(200, activation='relu'))
comparer.add(Dropout(dropout_rate))
comparer.add(Dense(1, activation='sigmoid'))
Y = comparer(merged)
model = Model(inputs=[X1, X2], outputs=Y)
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
self.model = model
And I train model by
self.hist = self.model.fit(
x=[train_sample_1, train_sample_2],
y=train_label,
class_weight = 'auto',
validation_split=0.1,
batch_size=batch_size,
epochs=epochs,
callbacks=callbacks)
I have built a simple neural network,
model = Sequential()
model.add(Dense(20, input_dim=5, activation='sigmoid'))
model.add(Dense(1, activation='sigmoid'))
and I would get its weights by:
summary = model.summary()
W_Input_Hidden = model.layers[0].get_weights()[0]
W_Output_Hidden = model.layers[1].get_weights()[0]
print(summary)
print('INPUT-HIDDEN LAYER WEIGHTS:')
print(W_Input_Hidden)
print('HIDDEN-OUTPUT LAYER WEIGHTS:')
print(W_Output_Hidden)
but, in this way, I only get the weights matrices (5x20 , 1x20) without the biases. How can I get the biases values?
Quite simple, its just the second element in the array returned by get_weights() (For Dense layers):
B_Input_Hidden = model.layers[0].get_weights()[1]
B_Output_Hidden = model.layers[1].get_weights()[1]
Here's a complete working example (implemented with TensorFlow 2 and Keras).
import tensorflow as tf
import numpy as np
def get_model():
inp = tf.keras.layers.Input(shape=(1,))
# Use the parameter bias_initializer='random_uniform'
# in case you want the initial biases different than zero.
x = tf.keras.layers.Dense(8)(inp)
out = tf.keras.layers.Dense(1)(x)
model = tf.keras.models.Model(inputs=inp, outputs=out)
return model
def main():
model = get_model()
model.compile(loss="mse")
weights = model.layers[1].get_weights()[0]
biases = model.layers[1].get_weights()[1]
print("initial weights =", weights)
print("initial biases =", biases)
X = np.random.randint(-10, 11, size=(1000, 1))
y = np.random.randint(0, 2, size=(1000, 1))
model.fit(X, y)
weights = model.layers[1].get_weights()[0]
biases = model.layers[1].get_weights()[1]
print("learned weights =", weights)
# Biases are similar because they are all initialized with zeros (by default).
print("learned biases =", biases)
if __name__ == '__main__':
main()
YOu can view and output biases and weights using the following code:
for layer in model.layers:
g=layer.get_config()
h=layer.get_weights()
print (g)
print (h)
if you're looking for weights and bias from the validation dataset, you need to do model.predict on each vector from the dataset.
for i in range(len(valData)):
ValResults = model.predict(valData[i])
B_Input_Hidden = model.layers[0].get_weights()[1]
B_Output_Hidden = model.layers[1].get_weights()[1]