Related
I'm trying to run the DeepCrack model, a CNN to find a pavement crack detection model. But I'm getting this error. I found the following error. I understood that the problem is in Outputs = model(image) here because my model is returning a tuple here instead of tensors. I tried to convert the output to tensor but it is not working. So, How can I solve this? I added my full code here. please help me to get rid of this.
#!/usr/bin/env python
# coding: utf-8
# In[ ]:
# License: BSD
# Author: Sasank Chilamkurthy
from __future__ import print_function, division
import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import torch.backends.cudnn as cudnn
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
from torch.utils.data import random_split
import matplotlib.pyplot as plt
import time
import os
import copy
cudnn.benchmark = True
plt.ion() # interactive mode
from random import *
from tqdm.notebook import tqdm, trange
from time import sleep
from pathlib import Path
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import transforms, models
from torchvision.datasets import ImageFolder
from warnings import filterwarnings
filterwarnings('ignore')
# functions to show an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
plt.savefig('labels.JPG')
## codes for data augmentation
train_trans = transforms.Compose([
transforms.Resize((224, 224)),
transforms.RandomHorizontalFlip(p=0.5), ## tamim: image will move left and right
transforms.RandomVerticalFlip(p=0.5), ## tamim: image will come to eye vertically
transforms.RandomRotation(degrees=(.5, 5)), ## very small rotation of the cracks
transforms.ToTensor(),
transforms.Normalize(
mean=[0.5, 0.5, 0.5],
std=[0.5, 0.5, 0.5]
)
])
test_trans = transforms.Compose([
transforms.Resize((224, 224)),
transforms.RandomHorizontalFlip(p=0.5), ## tamim: image will move left and right
transforms.RandomVerticalFlip(p=0.5), ## tamim: image will come to eye vertically
transforms.RandomRotation(degrees=(.5, 5)), ## very small rotation of the cracks
transforms.ToTensor(),
transforms.Normalize(
mean=[0.5, 0.5, 0.5],
std=[0.5, 0.5, 0.5]
)
])
## Load data
from torchvision.datasets import ImageFolder
data = ImageFolder('../Data/Data_Structure(Annotated)', transform=train_trans , )
test_folder= ImageFolder("../Data/DATA_iPhone_13_Pro_Max", transform=test_trans, )
batch_size = 32
num_classes = 4
learning_rate = 0.01
num_epochs = 10
print("Follwing classes are there : \n",data.classes)
classes = ('Alligator Cracks', 'Delamination', 'Longitudinal Cracks', 'Transverse Cracks')
len(data)
##Splitting Data and Prepare Batches:
## Source: https://medium.com/thecyphy/train-cnn-model-with-pytorch-21dafb918f48
val_size = 127 ## Tamim:30% data for validation ##
train_size = len(data) - val_size
train_loader,val_loader = random_split(data,[train_size,val_size]) ## To randomly split the images into training and testing, PyTorch provides random_split()
print(f"Length of Train Data : {len(train_loader)}") ## changed the folder names
print(f"Length of Validation Data : {len(val_loader)}")
# Splitting train and validation data on batches
train_loader = torch.utils.data.DataLoader(train_loader, shuffle=True, batch_size=batch_size) ## defined train data & val data
val_loader = torch.utils.data.DataLoader(val_loader, shuffle=True, batch_size=batch_size)
test_loader = torch.utils.data.DataLoader(test_folder, shuffle=False, batch_size=batch_size)
# visualize images of a single batch
dataiter = iter(train_loader)
images, labels = next(dataiter)
# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join(f'{classes[labels[j]]:5s}' for j in range(batch_size)))
# print(model)
from torch import nn
import torch
import torch.nn.functional as F
def Conv3X3(in_, out):
return torch.nn.Conv2d(in_, out, 3, padding=1)
class ConvRelu(nn.Module):
def __init__(self, in_, out):
super().__init__()
self.conv = Conv3X3(in_, out)
self.activation = torch.nn.ReLU(inplace=True)
def forward(self, x):
x = self.conv(x)
x = self.activation(x)
return x
class Down(nn.Module):
def __init__(self, nn):
super(Down,self).__init__()
self.nn = nn
self.maxpool_with_argmax = torch.nn.MaxPool2d(kernel_size=2, stride=2, return_indices=True)
def forward(self,inputs):
down = self.nn(inputs)
unpooled_shape = down.size()
outputs, indices = self.maxpool_with_argmax(down)
return outputs, down, indices, unpooled_shape
class Up(nn.Module):
def __init__(self, nn):
super().__init__()
self.nn = nn
self.unpool=torch.nn.MaxUnpool2d(2,2)
def forward(self,inputs,indices,output_shape):
outputs = self.unpool(inputs, indices=indices, output_size=output_shape)
outputs = self.nn(outputs)
return outputs
class Fuse(nn.Module):
def __init__(self, nn, scale):
super().__init__()
self.nn = nn
self.scale = scale
self.conv = Conv3X3(64,1)
def forward(self,down_inp,up_inp):
outputs = torch.cat([down_inp, up_inp], 1)
outputs = F.interpolate(outputs, scale_factor=self.scale, mode='bilinear')
outputs = self.nn(outputs)
return self.conv(outputs)
class DeepCrack(nn.Module):
def __init__(self, num_classes=1000):
super(DeepCrack, self).__init__()
self.down1 = Down(torch.nn.Sequential(
ConvRelu(3,64),
ConvRelu(64,64),
))
self.down2 = Down(torch.nn.Sequential(
ConvRelu(64,128),
ConvRelu(128,128),
))
self.down3 = Down(torch.nn.Sequential(
ConvRelu(128,256),
ConvRelu(256,256),
ConvRelu(256,256),
))
self.down4 = Down(torch.nn.Sequential(
ConvRelu(256, 512),
ConvRelu(512, 512),
ConvRelu(512, 512),
))
self.down5 = Down(torch.nn.Sequential(
ConvRelu(512, 512),
ConvRelu(512, 512),
ConvRelu(512, 512),
))
self.up1 = Up(torch.nn.Sequential(
ConvRelu(64, 64),
ConvRelu(64, 64),
))
self.up2 = Up(torch.nn.Sequential(
ConvRelu(128, 128),
ConvRelu(128, 64),
))
self.up3 = Up(torch.nn.Sequential(
ConvRelu(256, 256),
ConvRelu(256, 256),
ConvRelu(256, 128),
))
self.up4 = Up(torch.nn.Sequential(
ConvRelu(512, 512),
ConvRelu(512, 512),
ConvRelu(512, 256),
))
self.up5 = Up(torch.nn.Sequential(
ConvRelu(512, 512),
ConvRelu(512, 512),
ConvRelu(512, 512),
))
self.fuse5 = Fuse(ConvRelu(512 + 512, 64), scale=16)
self.fuse4 = Fuse(ConvRelu(512 + 256, 64), scale=8)
self.fuse3 = Fuse(ConvRelu(256 + 128, 64), scale=4)
self.fuse2 = Fuse(ConvRelu(128 + 64, 64), scale=2)
self.fuse1 = Fuse(ConvRelu(64 + 64, 64), scale=1)
self.final = Conv3X3(5,1)
def forward(self,inputs):
# encoder part
out, down1, indices_1, unpool_shape1 = self.down1(inputs)
out, down2, indices_2, unpool_shape2 = self.down2(out)
out, down3, indices_3, unpool_shape3 = self.down3(out)
out, down4, indices_4, unpool_shape4 = self.down4(out)
out, down5, indices_5, unpool_shape5 = self.down5(out)
# decoder part
up5 = self.up5(out, indices=indices_5, output_shape=unpool_shape5)
up4 = self.up4(up5, indices=indices_4, output_shape=unpool_shape4)
up3 = self.up3(up4, indices=indices_3, output_shape=unpool_shape3)
up2 = self.up2(up3, indices=indices_2, output_shape=unpool_shape2)
up1 = self.up1(up2, indices=indices_1, output_shape=unpool_shape1)
fuse5 = self.fuse5(down_inp=down5,up_inp=up5)
fuse4 = self.fuse4(down_inp=down4, up_inp=up4)
fuse3 = self.fuse3(down_inp=down3, up_inp=up3)
fuse2 = self.fuse2(down_inp=down2, up_inp=up2)
fuse1 = self.fuse1(down_inp=down1, up_inp=up1)
output = self.final(torch.cat([fuse5,fuse4,fuse3,fuse2,fuse1],1))
return output, fuse5, fuse4, fuse3, fuse2, fuse1
if __name__ == '__main__':
inp = torch.randn((1,3,512,512))
model = DeepCrack()
out = model(inp)
model = DeepCrack()
print(model)
# specify loss function
criterion = nn.CrossEntropyLoss()
# specify loss function
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
# number of epochs to train the model
n_epochs = 10
for epoch in range(1, n_epochs+1):
# monitor training loss
train_loss = 0.0
###################
# train the model #
###################
for data in train_loader:
# _ stands in for labels, here
# no need to flatten images
images, _ = data
# clear the gradients of all optimized variables
optimizer.zero_grad()
# forward pass: compute predicted outputs by passing inputs to the model
outputs = model(images)
# calculate the loss
loss = criterion(outputs, images)
# backward pass: compute gradient of the loss with respect to model parameters
loss.backward()
# perform a single optimization step (parameter update)
optimizer.step()
# update running training loss
train_loss += loss.item()*images.size(0)
# print avg training statistics
train_loss = train_loss/len(train_loader)
print('Epoch: {} \tTraining Loss: {:.6f}'.format(
epoch,
train_loss
)) ```
Traceback (most recent call last):
File "test_deepcrack.py", line 320, in <module>
loss = criterion(outputs, images)
File "/apps/pkg/pytorch/1.10.2/cuda/lib/python3.8/site-
packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/apps/pkg/pytorch/1.10.2/cuda/lib/python3.8/site-
packages/torch/nn/modules/loss.py", line 1150, in forward
> return F.cross_entropy(input, target, weight=self.weight,
> File "/apps/pkg/pytorch/1.10.2/cuda/lib/python3.8/site-packages/torch/nn/functional.py", > line 2846, in cross_entropy
> return torch._C._nn.cross_entropy_loss(input, target, weight,
> _Reduction.get_enum(reduction), ignore_index, label_smoothing)
>TypeError: cross_entropy_loss(): argument 'input' (position 1) must be Tensor, not tuple
I am learning neural network modeling and its uses in time series prediction.
First, thank you for reading this post and for your help :)
On this page there are various NN models (LSTM, CNN etc.) for predicting "traffic volume":
https://michael-fuchs-python.netlify.app/2020/11/01/time-series-analysis-neural-networks-for-forecasting-univariate-variables/#train-validation-split
I got inspired and decided to use/shorten/adapt the code in there for a problem of my own: predicting the bitcoin price.
I have the bitcoin daily prices starting 1.1.2017
in total 2024 daily prices
I use the first 85% of the data for the training data, and the rest as the validation (except the last 10 observation, which I would like to use as test data to see how good my model is)
I would like to use a Feedforward model
My goal is merely having a code that runs.
I have managed so far to have most of my code run. However, I get a strange format for my test forecast results: It should be simply an array of 10 numbers (i.e. predicted prices corresponding to the 10 day at the end of my data). To my surprise what is printed out is a long list of numbers. I need help to find out what changes I need to make to make to the code to make it run.
Thank you for helping me :)
The code is pasted down there, followed by the error:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import preprocessing #import MinMaxScaler
from sklearn import metrics #import mean_squared_error
import seaborn as sns
sns.set()
import tensorflow as tf
from tensorflow import keras
from keras.layers import Input, Dense, Flatten
from keras.optimizers import Adam
from keras.models import Sequential
from keras.callbacks import EarlyStopping
tf.__version__
df = pd.read_csv('/content/BTC-USD.csv')
def mean_absolute_percentage_error_func(y_true, y_pred):
y_true, y_pred = np.array(y_true), np.array(y_pred)
return np.mean(np.abs((y_true - y_pred) / y_true)) * 100
def timeseries_evaluation_metrics_func(y_true, y_pred):
print('Evaluation metric results: ')
print(f'MSE is : {metrics.mean_squared_error(y_true, y_pred)}')
print(f'MAE is : {metrics.mean_absolute_error(y_true, y_pred)}')
print(f'RMSE is : {np.sqrt(metrics.mean_squared_error(y_true, y_pred))}')
print(f'MAPE is : {mean_absolute_percentage_error_func(y_true, y_pred)}')
print(f'R2 is : {metrics.r2_score(y_true, y_pred)}',end='\n\n')
def univariate_data_prep_func(dataset, start, end, window, horizon):
X = []
y = []
start = start + window
if end is None:
end = len(dataset) - horizon
for i in range(start, end):
indicesx = range(i-window, i)
X.append(np.reshape(dataset[indicesx], (window, 1)))
indicesy = range(i,i+horizon)
y.append(dataset[indicesy])
return np.array(X), np.array(y)
# Generating the test set
test_data = df['close'].tail(10)
df = df.drop(df['close'].tail(10).index)
df.shape
# Defining the target variable
uni_data = df['close']
uni_data.index = df['formatted_date']
uni_data.head()
#scaling
from sklearn import preprocessing
uni_data = uni_data.values
scaler_x = preprocessing.MinMaxScaler()
x_scaled = scaler_x.fit_transform(uni_data.reshape(-1, 1))
# Single Step Style (sss) modeling
univar_hist_window_sss = 50
horizon_sss = 1
# 2014 observations in total
# 2014*0.85=1710 should be part of the training (304 validation)
train_split_sss = 1710
x_train_uni_sss, y_train_uni_sss = univariate_data_prep_func(x_scaled, 0, train_split_sss,
univar_hist_window_sss, horizon_sss)
x_val_uni_sss, y_val_uni_sss = univariate_data_prep_func(x_scaled, train_split_sss, None,
univar_hist_window_sss, horizon_sss)
print ('Length of first Single Window:')
print (len(x_train_uni_sss[0]))
print()
print ('Target horizon:')
print (y_train_uni_sss[0])
BATCH_SIZE_sss = 32
BUFFER_SIZE_sss = 150
train_univariate_sss = tf.data.Dataset.from_tensor_slices((x_train_uni_sss, y_train_uni_sss))
train_univariate_sss = train_univariate_sss.cache().shuffle(BUFFER_SIZE_sss).batch(BATCH_SIZE_sss).repeat()
validation_univariate_sss = tf.data.Dataset.from_tensor_slices((x_val_uni_sss, y_val_uni_sss))
validation_univariate_sss = validation_univariate_sss.batch(BATCH_SIZE_sss).repeat()
n_steps_per_epoch = 55
n_validation_steps = 10
n_epochs = 100
#FFNN architecture
model = tf.keras.models.Sequential([
tf.keras.layers.Dense(8, input_shape=x_train_uni_sss.shape[-2:]),
tf.keras.layers.Dense(units=horizon_sss)])
model.compile(loss='mse',
optimizer='adam')
#fit the model
model_path = '/content/FFNN_model_sss.h5'
keras_callbacks = [tf.keras.callbacks.EarlyStopping(monitor='val_loss',
min_delta=0, patience=10,
verbose=1, mode='min'),
tf.keras.callbacks.ModelCheckpoint(model_path,monitor='val_loss',
save_best_only=True,
mode='min', verbose=0)]
history = model.fit(train_univariate_sss, epochs=n_epochs, steps_per_epoch=n_steps_per_epoch,
validation_data=validation_univariate_sss, validation_steps=n_validation_steps, verbose =1,
callbacks = keras_callbacks)
#validation
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(loss) + 1)
plt.plot(epochs, loss, 'r', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.legend()
plt.show()
# Testing our model
trained_ffnn_model_sss = tf.keras.models.load_model(model_path)
df_temp = df['close']
test_horizon = df_temp.tail(univar_hist_window_sss)
test_history = test_horizon.values
result = []
# Define Forecast length here
window_len = len(test_data)
test_scaled = scaler_x.fit_transform(test_history.reshape(-1, 1))
for i in range(1, window_len+1):
test_scaled = test_scaled.reshape((1, test_scaled.shape[0], 1))
# Inserting the model
predicted_results = trained_ffnn_model_sss.predict(test_scaled)
print(f'predicted : {predicted_results}')
result.append(predicted_results[0])
test_scaled = np.append(test_scaled[:,1:],[[predicted_results]])
result_inv_trans = scaler_x.inverse_transform(result)
result_inv_trans
I believe the problem might have to do with the shapes of data. How exactly I do not yet know.
Data:
click here
Traceback:
click here
I have trained an LSTM Model in python to predict future prices in order to integrate it later in a flutter app. The training and conversion were successful but as soon as i run the converted model in my app using this code:
Future<void> predData() async {
final interpreter = await Interpreter.fromAsset('diesel_model.tflite');
print('########BEFORE########### ');
var input = [[[1.99]]];
var output = List<double>.filled(2, 0);
// The run method will run inference and
// store the resulting values in output.
interpreter.run(input, output);
print(output);
}
i get the following error:
I/flutter (24764): ########BEFORE###########
E/tflite (24764): Regular TensorFlow ops are not supported by this interpreter. Make sure you apply/link the Flex delegate before inference.
E/tflite (24764): Node number 5 (FlexTensorListReserve) failed to prepare.
E/flutter (24764): [ERROR:flutter/lib/ui/ui_dart_state.cc(209)] Unhandled Exception: Bad state: failed precondition
E/flutter (24764): #0 checkState (package:quiver/check.dart:74:5)
E/flutter (24764): #1 Interpreter.invoke (package:tflite_flutter/src/interpreter.dart:150:5)
E/flutter (24764): #2 Interpreter.runForMultipleInputs (package:tflite_flutter/src/interpreter.dart:190:5)
E/flutter (24764): #3 Interpreter.run (package:tflite_flutter/src/interpreter.dart:157:5)
E/flutter (24764): #4 _StationsPageState.predData (package:smart_refuel/views/stations_page.dart:179:17)
E/flutter (24764): <asynchronous suspension>
Here's how i converted the H5 Model into Tflite:
First i put my model in the "content" folder, then i ran the following code:
from keras.models import load_model
diesel_model = load_model('/content/diesel_model.h5')
# Convert the model.
converter = tf.lite.TFLiteConverter.from_keras_model(diesel_model)
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]
converter.allow_custom_ops = True
tflite_model = converter.convert()
# Save the model.
with open('diesel_model.tflite', 'wb') as f:
f.write(tflite_model)
Note that i added converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS] converter.allow_custom_ops = True to avoid to errors during the conversion.
Finally here's the code for the training of the LSTM model:
import pandas as pd
import numpy as np
import datetime
import glob
import matplotlib.pyplot as plt
from sklearn.preprocessing import normalize, MinMaxScaler
from sklearn.metrics import mean_squared_error, r2_score
from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation, Dropout, LSTM
from pylab import rcParams
rcParams['figure.figsize'] = (15, 8)
import warnings
warnings.filterwarnings('ignore')
import time
def load_data(filepath):
'''
Load daily fuel data
Input:filepath
Output: dataframe with daily fuel prices
'''
start = time.time()
# Columns to load
cols = ['diesel', 'e5', 'e10']
# cols = ['date', 'diesel', 'e5', 'e10']
# date Column for parsing
date_col = ['date']
# Create empty dataframe
prices=pd.DataFrame()
# Get list of all CSV files
files = glob.glob(filepath + "/prices.csv")
# Loop throgh all the files and get daily data
for file in files:
print(file)
# Read CSV file
df = pd.read_csv(file, usecols = cols, dtype={'diesel': np.float32})
# Convert to datetime
# df['date'] = pd.to_datetime(df['date'], utc=True)
# Get daily data by using median value of the day
# daily = df.set_index('date').resample('d').median().ffill()
# concate the new data with old
prices = pd.concat([prices,df], sort=False)
# Remove duplicates and keep first
prices = prices[~prices.index.duplicated(keep='first')]
# Return resulted price dataframe
print("Total time taken: ", (time.time() - start))
return prices
filepath = "C:/Users/marou/Desktop/B.Arbeit/dataset"
# filepath = "d:/a"
prices = load_data(filepath)
# print(prices.shape)
# print(prices.to_numpy()[0])
prices.to_csv('prices.csv', index=False)
prices.index
# the values have to be normalized for LSTM
scaled = prices['diesel'].values.reshape(-1,1)
train_size = prices.shape[0]-150
vali_size = 20 # let's take 20 days as validation set for fitting
test_size = len(scaled) - train_size - vali_size
trainX, valiX, testX = scaled[:train_size,:], scaled[train_size:train_size+vali_size,:], scaled[train_size+vali_size:, :]
def create_data(dataset, look_back=1):
'''creates two array of x and y out of the given array
Input: Array of data, steps to look back
Output: X, Y
'''
dataY = []
for i in range(len(dataset) - look_back):
# a = dataset[i:(i+look_back), 0]
# dataX.append(a)
dataY.append(dataset[i+look_back, 0])
print(len(dataY))
return np.array(dataY)
look_back =1
trainY = create_data(trainX, look_back)
valiY = create_data(valiX, look_back)
testY = create_data(testX, look_back)
trainX = trainX[0:trainX.shape[0]-look_back,:]
valiX = valiX[0:valiX.shape[0]-look_back,:]
testX = testX[0:testX.shape[0]-look_back,:]
# reshape to make it usable as input for LSTM
trainX = np.reshape(trainX, (trainX.shape[0], 1, 1))
valiX = np.reshape(valiX, (valiX.shape[0], 1, 1))
testX = np.reshape(testX, (testX.shape[0], 1, 1))
# build a LSTM model
model = Sequential()
model.add(LSTM(50, input_shape=(trainX.shape[1], trainX.shape[2]), return_sequences=True))
model.add(Dropout(0.1))
model.add(LSTM(50))
model.add(Dense(1))
model.compile(loss='mae', optimizer='adam')
for i in range (20):
print(i)
history = model.fit(trainX, trainY, epochs=1, batch_size=16, validation_data=(valiX, valiY), verbose=2, shuffle=False)
s = 'C:/Users/marou/Desktop/B.Arbeit/dataset/mod_'
s = s + str(i)
s = s + '.h5'
model.save(s)
Im stuck in this error for a while and can't go through, so i'll be grateful for any king of help.
Don't hesitate to ask me if you need further informations.
I am getting an error when i run the below code. The error says
MisconfigurationException: No training_step() method defined. Lightning Trainer expects as minimum a training_step(), train_dataloader() and configure_optimizers() to be defined.
Can someone please let me know what is the issue here? I am very new to Pytorch. I am trying to simulate Sin wave using MLP
import numpy as np ## using again numpy library for Sin function
import torch ## using pytorch
import matplotlib.pyplot as plt
import pytorch_lightning as pl
import torch.optim as optim
from torch import nn
from pytorch_lightning import Trainer
from sklearn.model_selection import train_test_split
import pandas as pd
from torch.utils.data import DataLoader
N=1000 ## 1000 samples to be generated
L=1000 ## length of each sample
T=20 ## width of wave
x = np.random.randn(1000)
y = np.sin(x)
df = pd.DataFrame({'x':x, 'y':y})
train, test = train_test_split(df, test_size=0.2, random_state=42, shuffle=True)
target_fields=['y']
train_features, train_targets = train.drop(target_fields, axis=1), train[target_fields]
test_features, test_targets = test.drop(target_fields, axis=1), test[target_fields]
class MLP(pl.LightningModule):
def __init__(self):
super(MLP,self).__init__()
self.fc1 = nn.Linear(1, 10)
self.fc2 = nn.Linear(10, 1)
def forward(self, x):
x = torch.Relu(self.fc1(x))
x = self.fc2(x)
return x
l_rate = 0.2
mse_loss = nn.MSELoss(reduction = 'mean')
def train_dataloader(self):
train_dataset = TensorDataset(torch.tensor(train_features.values).float(), torch.tensor(train_targets[['cnt']].values).float())
train_loader = DataLoader(dataset = train_dataset, batch_size = 128)
return train_loader
def test_dataloader(self):
test_dataset = TensorDataset(torch.tensor(test_features.values).float(), torch.tensor(test_targets[['cnt']].values).float())
test_loader = DataLoader(dataset = test_dataset, batch_size = 128)
return test_loader
def configure_optimizers(self):
return optim.SGD(self.parameters(), lr=l_rate)
def training_step(self, batch, batch_idx):
x, y = batch
logits = self.forward(x)
loss = mse_loss(logits, y)
# Add logging
logs = {'loss': loss}
return {'loss': loss, 'log': logs}
def test_step(self, batch, batch_idx):
x, y = batch
logits = self.forward(x)
loss = mse_loss(logits, y)
correct = torch.sum(logits == y.data)
predictions_pred.append(logits)
predictions_actual.append(y.data)
return {'test_loss': loss, 'test_correct': correct, 'logits': logits}
def test_epoch_end(self, outputs):
avg_loss = torch.stack([x['test_loss'] for x in outputs]).mean()
logs = {'test_loss': avg_loss}
return {'avg_test_loss': avg_loss, 'log': logs, 'progress_bar': logs }
model = MLP()
trainer = Trainer(max_epochs = 50)
trainer.fit(model)
Error
GPU available: False, used: False
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
---------------------------------------------------------------------------
MisconfigurationException Traceback (most recent call last)
<ipython-input-9-7bdf5ac9771f> in <module>()
1 model = MLP()
2 trainer = Trainer(max_epochs = 50)
----> 3 trainer.fit(model)
3 frames
/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/configuration_validator.py in __verify_train_loop_configuration(self, model)
50 if not has_training_step:
51 raise MisconfigurationException(
---> 52 "No `training_step()` method defined. Lightning `Trainer` expects as minimum a"
53 " `training_step()`, `train_dataloader()` and `configure_optimizers()` to be defined."
54 )
MisconfigurationException: No `training_step()` method defined. Lightning `Trainer` expects as minimum a `training_step()`, `train_dataloader()` and `configure_optimizers()` to be defined.
You are missing 2 parameters in your trainer.fit() call. See the documentation
I want use keras Lstm to get the time series features, then use the features to Kmeans. But now I can not get the layers output values. How can I get the layers output values?
This is my lstm network
Layer (type) Output Shape Param #
lstm_66 (LSTM) (None, None, 50) 10400
lstm_67 (LSTM) (None, 100) 60400
dense_19 (Dense) (None, 1) 101
activation_19 (Activation) (None, 1) 0
I want to get the lstm_67 output values,my code is:
import keras.backend as K
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
sess = tf.Session()
sess.run(tf.global_variables_initializer())
import numpy as np
statesAll=[]
layers = model.layers
print layers[1].output,type(layers[1].output[1]),sess.run(layers[1].output)
and the result is:
Tensor("lstm_61/TensorArrayReadV3:0", shape=(?, 100), dtype=float32)
So, how can I get the layers output value?
Thanks!
But it not work,my code is:
def load_data(file_name, sequence_length=10, split=0.8):
df = pd.read_csv(file_name, sep=',', usecols=[1])
data_all = np.array(df).astype(float)
scaler = MinMaxScaler()
data_all = scaler.fit_transform(data_all)
data = []
print len(data_all)
for i in range(len(data_all) - sequence_length - 1):
data.append(data_all[i: i + sequence_length + 1])
reshaped_data = np.array(data).astype('float64')
np.random.shuffle(reshaped_data)
x = reshaped_data[:, :-1]
y = reshaped_data[:, -1]
split_boundary = int(reshaped_data.shape[0] * split)
train_x = x[: split_boundary]
test_x = x[split_boundary:]
train_y = y[: split_boundary]
test_y = y[split_boundary:]
return train_x, train_y, test_x, test_y, scaler
def build_model(n_samples, time_steps, input_dim):
model = Sequential()
model.add(LSTM(input_dim=1, output_dim=50,return_sequences=True))
model.add(LSTM(100, return_sequences=False))
model.add(Dense(output_dim=1))
model.add(Activation('linear'))
model.compile(loss='mse', optimizer='rmsprop')
print(model.layers)
return model
def train_model(train_x, train_y, test_x, test_y):
model = build_model()
model.fit(train_x, train_y, batch_size=128, nb_epoch=30,validation_split=0.1)
return model
train_x, train_y, test_x, test_y, scaler = load_data(file path)
train_x = np.reshape(train_x, (train_x.shape[0], train_x.shape[1], 1))
test_x = np.reshape(test_x, (test_x.shape[0], test_x.shape[1], 1))
model = train_model(train_x, train_y, test_x, test_y)
from keras import backend as K
layers = model.layers
K.eval(layers[1].output)
In TensorFlow 2.x, you can do like this:
from tensorflow.python.keras import backend as K
model = build_model()
# lstm_67 is the second layer.
lstm = K.function([model.layers[0].input], [model.layers[1].output])
lstm_output = lstm([test_x])[0]
keras.backend.eval() should do.
Look at the documentation here and here
First of all, this is a tensor, you need to use the tf. Print () method to see the specific value. If you use Spyder, you will not see this information in the console. You need to execute this program in the command line.