I have trained a LinearRegressor with two features: x,y and the label: l
def train_input_fn():
x = [1,2,3,4]
y = [2,3,4,5]
feature_cols = tf.constant(x)
labels = tf.constant(y)
return feature_cols, labels
x = tf.contrib.layers.real_valued_column("x")
y = tf.contrib.layers.real_valued_column("y")
m = tf.contrib.learn.LinearRegressor(feature_columns=[ x,y],
model_dir=model_dir)
m.fit(input_fn=train_input_fn, steps=100)
After training I want to predict from two new values
new_sample = np.array([20,20])
m.predict(new_sample)
but I get this error message when calling predict
File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/layers/python/layers/feature_column.py", line 870, in insert_transformed_feature
input_tensor = columns_to_tensors[self.name]
KeyError: 'x'
Does anyone know why I get KeyError?
Try this:
my_feature_columns = [tf.contrib.layers.real_valued_column("", dimension=2)]
m = tf.contrib.learn.LinearRegressor(feature_columns=my_feature_columns,
model_dir=model_dir)
m.fit(input_fn=train_input_fn, steps=100)
I am not an expert in Tensorflow but this works for me:
new_sample = np.array([20,20],dtype='float32')
empty_y = np.zeros(len(new_sample),dtype='float32')
prediction_x = tf.contrib.learn.io.numpy_input_fn({"x":new_sample},empty_y, batch_size=45, num_epochs=100)
forecast = list(estimator.predict(input_fn=prediction_x,as_iterable=False))
Related
I am trying to do univariant time series forecasting. My model works Perfectly in different datasets. But for this dataset, the prediction is incredibly bad (tried 50,100,200 epochs, different batch sizes, and learning rates. Nothing has changed. So I think there is something wrong with my dataset.)
Here values of my dataset:
Mean: 49.840000, standard deviation: 31.786387
Here is my architecture
Here is the sample from my dataset
Here is my prediction values
Here is the code for normalization that im using:
def NormalizeMult(data):
#normalize 用于反归一化
data = np.array(data)
normalize = np.arange(2*data.shape[1],dtype='float64')
normalize = normalize.reshape(data.shape[1],2)
print(normalize.shape)
for i in range(0,data.shape[1]):
#第i列
list = data[:,i]
listlow,listhigh = np.percentile(list, [0, 100])
# print(i)
normalize[i,0] = listlow
normalize[i,1] = listhigh
delta = listhigh - listlow
if delta != 0:
#第j行
for j in range(0,data.shape[0]):
data[j,i] = (data[j,i] - listlow)/delta
#np.save("./normalize.npy",normalize)
return data,normalize
Here is the code that I'm using dataset and normalizing it:
INPUT_DIMS = 1
TIME_STEPS = 4
lstm_units = 64
#归一化
series = read_csv('/content/logs.csv')
series = series.drop(["timestamp"],axis=1)
series= series.dropna()
series = series.head(100)
data=series
data,normalize = NormalizeMult(data[0:50])
pollution_data = data[:,0].reshape(len(data[0:50]),1)
train_X, _ = split_sequence(data,TIME_STEPS)
_ , train_Y = split_sequence(data,TIME_STEPS)
optimizer = tf.keras.optimizers.Adam(lr=0.001)
m = attention_model()
m.summary()
m.compile(optimizer, loss='mse')
m.fit(train_X, train_Y, epochs=500, batch_size=2, validation_split=0.1)
I am trying to use the Triple-Loss technique to fine-tune an EfficientNet network for human Re-ID using Keras. Here is the code I am using:
This is the generator:
class SampleGen(object):
def __init__(self, file_class_mapping):
self.file_class_mapping = file_class_mapping
self.class_to_list_files = defaultdict(list)
self.list_all_files = list(file_class_mapping.keys())
self.range_all_files = list(range(len(self.list_all_files)))
for file, class_ in file_class_mapping.items():
self.class_to_list_files[class_].append(file)
self.list_classes = list(set(self.file_class_mapping.values()))
self.range_list_classes = range(len(self.list_classes))
self.class_weight = np.array([len(self.class_to_list_files[class_]) for class_ in self.list_classes])
self.class_weight = self.class_weight / np.sum(self.class_weight)
def get_sample(self):
class_idx = np.random.choice(self.range_list_classes, 1, p=self.class_weight)[0]
examples_class_idx = np.random.choice(range(len(self.class_to_list_files[self.list_classes[class_idx]])), 2)
positive_example_1, positive_example_2 = \
self.class_to_list_files[self.list_classes[class_idx]][examples_class_idx[0]], \
self.class_to_list_files[self.list_classes[class_idx]][examples_class_idx[1]]
negative_example = None
while negative_example is None or self.file_class_mapping[negative_example] == \
self.file_class_mapping[positive_example_1]:
negative_example_idx = np.random.choice(self.range_all_files, 1)[0]
negative_example = self.list_all_files[negative_example_idx]
return positive_example_1, negative_example, positive_example_2
def read_and_resize(filepath):
im = Image.open((filepath)).convert('RGB')
im = im.resize((image_size, image_size))
return np.array(im, dtype="float32")
def augment(im_array):
if np.random.uniform(0, 1) > 0.9:
im_array = np.fliplr(im_array)
return im_array
def gen(triplet_gen):
while True:
list_positive_examples_1 = []
list_negative_examples = []
list_positive_examples_2 = []
for i in range(batch_size):
positive_example_1, negative_example, positive_example_2 = triplet_gen.get_sample()
path_pos1 = join(path_train, positive_example_1)
path_neg = join(path_train, negative_example)
path_pos2 = join(path_train, positive_example_2)
positive_example_1_img = read_and_resize(path_pos1)
negative_example_img = read_and_resize(path_neg)
positive_example_2_img = read_and_resize(path_pos2)
positive_example_1_img = augment(positive_example_1_img)
negative_example_img = augment(negative_example_img)
positive_example_2_img = augment(positive_example_2_img)
list_positive_examples_1.append(positive_example_1_img)
list_negative_examples.append(negative_example_img)
list_positive_examples_2.append(positive_example_2_img)
A = preprocess_input(np.array(list_positive_examples_1))
B = preprocess_input(np.array(list_positive_examples_2))
C = preprocess_input(np.array(list_negative_examples))
label = None
yield {'anchor_input': A, 'positive_input': B, 'negative_input': C}, label
This is how I create the model:
def get_model():
base_model = efn.EfficientNetB3(weights='imagenet', include_top=False)
for layer in base_model.layers:
layer.trainable = False
x = base_model.output
x = Dropout(0.6)(x)
x = Dense(embedding_dim)(x)
x = Lambda(lambda x: K.l2_normalize(x, axis=1), name="enc_out")(x)
embedding_model = Model(base_model.input, x, name="embedding")
input_shape = (image_size, image_size, 3)
anchor_input = Input(input_shape, name='anchor_input')
positive_input = Input(input_shape, name='positive_input')
negative_input = Input(input_shape, name='negative_input')
anchor_embedding = embedding_model(anchor_input)
positive_embedding = embedding_model(positive_input)
negative_embedding = embedding_model(negative_input)
inputs = [anchor_input, positive_input, negative_input]
outputs = [anchor_embedding, positive_embedding, negative_embedding]
triplet_model = Model(inputs, outputs)
triplet_model.add_loss(K.mean(triplet_loss(outputs)))
return embedding_model, triplet_model
And this is how I'm trying to run the training:
if __name__ == '__main__':
data = pd.read_csv(path_csv)
train, test = train_test_split(data, train_size=0.7, random_state=1337)
file_id_mapping_train = {k: v for k, v in zip(train.Image.values, train.Id.values)}
file_id_mapping_test = {k: v for k, v in zip(test.Image.values, test.Id.values)}
gen_tr = gen(SampleGen(file_id_mapping_train))
gen_te = gen(SampleGen(file_id_mapping_test))
embedding_model, triplet_model = get_model()
for i, layer in enumerate(embedding_model.layers):
print(i, layer.name, layer.trainable)
for layer in embedding_model.layers[379:]:
layer.trainable = True
for layer in embedding_model.layers[:379]:
layer.trainable = False
triplet_model.compile(loss=None, optimizer=Adam(0.0001))
history = triplet_model.fit(x=gen_tr,
validation_data=gen_te,
epochs=10,
verbose=1,
steps_per_epoch=200,
validation_steps=20,
callbacks=create_callbacks())
The csv contains two columns (Image, Id) and I am generating triplets on the go using a generator. The layer 379 is the last layer of the network so I just leave that as trainable. I let it run for some epochs and it seems like it doesn't converge, it stays around 2.30. On epochs like 20, the loss is even higher than what I've started with. Here you can see what I mean: train example Is there anything wrong with the way I think about the problem?
Thank you!
I am trying to train a triple loss model using a fit_generator. it requires three input and no output. so i have a function that generates hard triplets. the output from the triplets generator has a shape of (3,5,279) which is 3 inputs(anchor,positive and negative) for 5 batches and a total of 279 features. When i run the fit_generator it throws this error that "the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 3 array(s), but instead got the following list of 1 arrays" meanwhile i have passed a list of three arrays. the code is below. it works when i use the fit, however, i want to always call the generator function to generate my triplets as my batches. thanks in advance..this has taken me three days
def load_data():
path = "arrhythmia_data.txt"
f = open( path, "r")
data = []
#remove line breaker, comma separate and store in array
for line in f:
line = line.replace('\n','').replace('?','0')
line = line.split(",")
data.append(line)
f.close()
data = np.array(data).astype(np.float64)
#print(data.shape)
#create the class labels for input data
Y_train = data[:,-1:]
train = data[:,:-1]
normaliser = preprocessing.MinMaxScaler()
train = normaliser.fit_transform(train)
val = train[320:,:]
train = train[:320,:]
#create one hot encoding of the class labels of the data and separate them into train and test data
lb = LabelBinarizer()
encode = lb.fit_transform(Y_train)
nb_classes = int(len(encode[0]))
#one_hot_labels = keras.utils.to_categorical(labels, num_classes=10) this could also be used for one hot encoding
Y_val_e = encode[320:,:]
Y_train_e = encode[:320,:]
print(Y_train_e[0])
print(np.argmax(Y_train_e[0]))
val_in = []
train_in = []
#grouping and sorting the input data based on label id or name
for n in range(nb_classes):
images_class_n = np.asarray([row for idx,row in enumerate(train) if np.argmax(Y_train_e[idx])==n])
train_in.append(images_class_n)
images_class_n = np.asarray([row for idx,row in enumerate(val) if np.argmax(Y_val_e[idx])==n])
val_in.append(images_class_n)
#print(train_in[0].shape)
return train_in,val_in,Y_train_e,Y_val_e,nb_classes
train_in,val,Y_train,Y_val,nb_classes = load_data()
input_shape = (train_in[0].shape[1],)
def build_network(input_shape , embeddingsize):
'''
Define the neural network to learn image similarity
Input :
input_shape : shape of input images
embeddingsize : vectorsize used to encode our picture
'''
#in_ = Input(train.shape)
net = Sequential()
net.add(Dense(128, activation='relu', input_shape=input_shape))
net.add(Dense(128, activation='relu'))
net.add(Dense(256, activation='relu'))
net.add(Dense(4096, activation='sigmoid'))
net.add(Dense(embeddingsize, activation= None))
#Force the encoding to live on the d-dimentional hypershpere
net.add(Lambda(lambda x: K.l2_normalize(x,axis=-1)))
return net
class TripletLossLayer(Layer):
def __init__(self, alpha, **kwargs):
self.alpha = alpha
super(TripletLossLayer, self).__init__(**kwargs)
def triplet_loss(self, inputs):
anchor, positive, negative = inputs
p_dist = K.sum(K.square(anchor-positive), axis=-1)
n_dist = K.sum(K.square(anchor-negative), axis=-1)
return K.sum(K.maximum(p_dist - n_dist + self.alpha, 0), axis=0)
def call(self, inputs):
loss = self.triplet_loss(inputs)
self.add_loss(loss)
return loss
def build_model(input_shape, network, margin=0.2):
'''
Define the Keras Model for training
Input :
input_shape : shape of input images
network : Neural network to train outputing embeddings
margin : minimal distance between Anchor-Positive and Anchor-Negative for the lossfunction (alpha)
'''
# Define the tensors for the three input images
anchor_input = Input(input_shape, name="anchor_input")
positive_input = Input(input_shape, name="positive_input")
negative_input = Input(input_shape, name="negative_input")
# Generate the encodings (feature vectors) for the three images
encoded_a = network(anchor_input)
encoded_p = network(positive_input)
encoded_n = network(negative_input)
#TripletLoss Layer
loss_layer = TripletLossLayer(alpha=margin,name='triplet_loss_layer')([encoded_a,encoded_p,encoded_n])
# Connect the inputs with the outputs
network_train = Model(inputs=[anchor_input,positive_input,negative_input],outputs=loss_layer)
# return the model
return network_train
def get_batch_random(batch_size,s="train"):
# initialize result
triplets=[np.zeros((batch_size,m)) for i in range(3)]
for i in range(batch_size):
#Pick one random class for anchor
anchor_class = np.random.randint(0, nb_classes)
nb_sample_available_for_class_AP = X[anchor_class].shape[0]
#Pick two different random pics for this class => A and P. You can use same anchor as P if there is one one element for anchor
if nb_sample_available_for_class_AP<=1:
continue
[idx_A,idx_P] = np.random.choice(nb_sample_available_for_class_AP,size=2 ,replace=False)
#Pick another class for N, different from anchor_class
negative_class = (anchor_class + np.random.randint(1,nb_classes)) % nb_classes
nb_sample_available_for_class_N = X[negative_class].shape[0]
#Pick a random pic for this negative class => N
idx_N = np.random.randint(0, nb_sample_available_for_class_N)
triplets[0][i,:] = X[anchor_class][idx_A,:]
triplets[1][i,:] = X[anchor_class][idx_P,:]
triplets[2][i,:] = X[negative_class][idx_N,:]
return np.array(triplets)
def get_batch_hard(draw_batch_size,hard_batchs_size,norm_batchs_size,network,s="train"):
if s == 'train':
X = train_in
else:
X = val
#m, features = X[0].shape
#while True:
#Step 1 : pick a random batch to study
studybatch = get_batch_random(draw_batch_size,X)
#Step 2 : compute the loss with current network : d(A,P)-d(A,N). The alpha parameter here is omited here since we want only to order them
studybatchloss = np.zeros((draw_batch_size))
#Compute embeddings for anchors, positive and negatives
A = network.predict(studybatch[0])
P = network.predict(studybatch[1])
N = network.predict(studybatch[2])
#Compute d(A,P)-d(A,N)
studybatchloss = np.sum(np.square(A-P),axis=1) - np.sum(np.square(A-N),axis=1)
#Sort by distance (high distance first) and take the
selection = np.argsort(studybatchloss)[::-1][:hard_batchs_size]
#Draw other random samples from the batch
selection2 = np.random.choice(np.delete(np.arange(draw_batch_size),selection),norm_batchs_size,replace=False)
selection = np.append(selection,selection2)
triplets = [studybatch[0][selection,:], studybatch[1][selection,:],studybatch[2][selection,:]]
triplets = triplets.reshape(triplets.shape[0],triplets.shape[1],triplets.shape[2])
yield triplets
network = build_network(input_shape,embeddingsize=10)
hard = get_batch_hard(5,4,1,network,s="train")
network_train = build_model(input_shape,network)
optimizer = Adam(lr = 0.00006)
network_train.compile(loss=None,optimizer=optimizer)
#this works
#history = network_train.fit(hard,epochs=100,steps_per_epoch=1, verbose=2)
history = network_train.fit_generator(hard,epochs=10,steps_per_epoch=16, verbose=2)
# error:: the list of Numpy arrays that you are passing to your model is not the size the model
expected. Expected to see 3 array(s), but instead got the following list of 1 arrays:
I think that's beacause in your generator you are yielding the 3 inputs array in one list, you need to yield the 3 arrays independently:
triplet_1 = studybatch[0][selection,:]
triplet_2 = studybatch[1][selection,:]
triplet_3 = studybatch[2][selection,:]
yield [triplet_1, triplet_2, triplet_3]
I am using tensorflow 2.0 and trying to make a actor critic algorithm to play the game of cartpole. I have done everything right but getting the following error: ValueError: No gradients provided for any variable: ['dense/kernel:0', 'dense/bias:0', 'dense_1/kernel:0', 'dense_1/bias:0'].
Please help me out
Here is my code:
import gym
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
MAX_EPISODES = 2000
GAMMA = 0.9
LR_A = 0.001
LR_C = 0.01
env = gym.make("CartPole-v0")
N_ACTIONS = env.action_space.n
N_FEATURES = 4
def make_actor(n_features, n_actions):
inputs = tf.keras.Input(shape=[n_features])
hidden = tf.keras.layers.Dense(20, activation=tf.nn.relu)(inputs)
dist = tf.keras.layers.Dense(n_actions, activation=tf.nn.softmax)(hidden)
model = tf.keras.Model(inputs=inputs, outputs=dist)
return model
def make_critic(n_features):
inputs = tf.keras.Input(shape=[n_features])
hidden = tf.keras.layers.Dense(20, activation=tf.nn.relu)(inputs)
value = tf.keras.layers.Dense(1)(hidden)
model = tf.keras.Model(inputs=inputs, outputs=value)
return model
actor = make_actor(N_FEATURES, N_ACTIONS)
critic = make_critic(N_FEATURES)
actor.summary()
critic.summary()
actor_optimizer = tf.keras.optimizers.Adam(LR_A)
critic_optimizer = tf.keras.optimizers.Adam(LR_C)
def loss_actor(s, a, td_error):
dist = actor(s.reshape(1, 4)).numpy()
log_prob = np.log(dist[0, a])
exp_v = np.mean(log_prob * td_error)
return tf.multiply(exp_v, -1)
def loss_critic(s, s_, r, gamma):
s, s_ = s[np.newaxis, :], s_[np.newaxis, :]
v = critic(s)
v_ = critic(s_)
td_error = r + gamma * v_ - v
return tf.multiply(td_error, 1)
def train(max_episodes):
for episode in range(max_episodes):
s = env.reset().astype(np.float32)
t = 0
track_r = []
while True:
dist = actor(s.reshape(1, 4)).numpy()
a = np.random.choice(range(N_ACTIONS), p=dist.ravel())
s_, r, done, info = env.step(a)
s_ = s_.astype(np.float32)
if done: r=-20
track_r.append(r)
with tf.GradientTape() as cri_tape, tf.GradientTape() as act_tape:
td_error = loss_critic(s, s_, r, GAMMA)
gradient = cri_tape.gradient(td_error, critic.trainable_variables)
critic_optimizer.apply_gradients(zip(gradient,critic.trainable_variables))
with tf.GradientTape() as act_tape:
neg_exp_v = loss_actor(s, a, td_error.numpy())
gradient = act_tape.gradient(neg_exp_v, critic.trainable_variables)
actor_optimizer.apply_gradients(zip(gradient, actor.trainable_variables))
s = s_
t += 1
if done:
print("Episode:{} Steps:{}".format(episode+1, t))
train(MAX_EPISODES)
The error is on line 69:actor_optimizer.apply_gradients(zip(gradient, actor.trainable_variables))
When I tried to print out the gradients for the actor the result was None.
I am really not getting where the problem is.
I would like to use the sparse_softmax_cross_entropy_with_logits
with the julia TensorFlow wrapper.
The operations is defined in the code here.
Basically, as I understand it the first argument should be logits, that would normally be fed to softmax to get them to be category probabilities (~1hot output).
And the second should be the correct labels as label ids.
I have adjusted the example code from the TensorFlow.jl readme
See below:
using Distributions
using TensorFlow
# Generate some synthetic data
x = randn(100, 50)
w = randn(50, 10)
y_prob = exp(x*w)
y_prob ./= sum(y_prob,2)
function draw(probs)
y = zeros(size(probs))
for i in 1:size(probs, 1)
idx = rand(Categorical(probs[i, :]))
y[i, idx] = 1
end
return y
end
y = draw(y_prob)
# Build the model
sess = Session(Graph())
X = placeholder(Float64)
Y_obs = placeholder(Float64)
Y_obs_lbl = indmax(Y_obs, 2)
variable_scope("logisitic_model", initializer=Normal(0, .001)) do
global W = get_variable("weights", [50, 10], Float64)
global B = get_variable("bias", [10], Float64)
end
L = X*W + B
Y=nn.softmax(L)
#costs = log(Y).*Y_obs #Dense (Orginal) way
costs = nn.sparse_softmax_cross_entropy_with_logits(L, Y_obs_lbl+1) #sparse way
Loss = -reduce_sum(costs)
optimizer = train.AdamOptimizer()
minimize_op = train.minimize(optimizer, Loss)
saver = train.Saver()
# Run training
run(sess, initialize_all_variables())
cur_loss, _ = run(sess, [Loss, minimize_op], Dict(X=>x, Y_obs=>y))
When I run it however, I get an error:
Tensorflow error: Status: Incompatible shapes: [1,100] vs. [100,10]
[[Node: gradients/SparseSoftmaxCrossEntropyWithLogits_10_grad/mul = Mul[T=DT_DOUBLE, _class=[], _device="/job:localhost/replica:0/task:0/cpu:0"](gradients/SparseSoftmaxCrossEntropyWithLogits_10_grad/ExpandDims, SparseSoftmaxCrossEntropyWithLogits_10:1)]]
in check_status(::TensorFlow.Status) at /home/ubuntu/.julia/v0.5/TensorFlow/src/core.jl:101
in run(::TensorFlow.Session, ::Array{TensorFlow.Port,1}, ::Array{Any,1}, ::Array{TensorFlow.Port,1}, ::Array{Ptr{Void},1}) at /home/ubuntu/.julia/v0.5/TensorFlow/src/run.jl:96
in run(::TensorFlow.Session, ::Array{TensorFlow.Tensor,1}, ::Dict{TensorFlow.Tensor,Array{Float64,2}}) at /home/ubuntu/.julia/v0.5/TensorFlow/src/run.jl:143
This only happens when I try to train it.
If I don't include an optimise function/output then it works fine.
So I am doing something that screws up the gradient math.