When I use the code below to perform Semantic semgentation on my owndataset(40 images) and annotations(1 class(myface) and the annotations in cocojson format) I got just black image no mask and all bits are the same and the model accuracy in all epochs is 67.87% but loss is going down in each epoch :
import cv2
import os
import json
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D
from tensorflow.keras.models import Model
from pycocotools.coco import COCO
from tensorflow.keras.applications import VGG16
from sklearn.utils import compute_sample_weight
folder_path = "D:\\ImageClassification\\face_semantic_segmentation\\dataset"
filenames = os.listdir(folder_path)
images = []
for filename in filenames:
img = cv2.imread(os.path.join(folder_path, filename))
img = cv2.resize(img, (256, 256))
img = np.array(img)
images.append(img)
x_train = np.array(images)
with open("D:\\ImageClassification\\face_semantic_segmentation\\annotations.json") as f:
coco = json.load(f)
annotations = coco['annotations']
masks = {}
for annotation in annotations:
image_id = annotation['image_id']
if image_id not in masks:
masks[image_id] = []
masks[image_id].append(annotation['segmentation'])
resized_masks = []
for image_id, mask in masks.items():
mask_img = np.zeros((720, 1280), dtype=np.uint8)
for segmentation in mask:
poly = np.array(segmentation).reshape((-1, 1, 2)).astype(np.int32)
cv2.fillPoly(mask_img, [poly], 1)
mask_img = cv2.resize(mask_img, (256, 256))
mask_img = np.stack([mask_img] * 3, axis=-1)
resized_masks.append(mask_img)
y_train = np.array(resized_masks)
y_train.shape
import matplotlib.pyplot as plt
import numpy as np
mask = y_train[4]
mask = np.sum(mask, axis=-1)
plt.imshow(mask)
plt.show()
from segmentation_models import Unet
from segmentation_models import get_preprocessing
from segmentation_models.losses import bce_jaccard_loss
from segmentation_models.metrics import iou_score
from tensorflow.keras.models import Model
BACKBONE = 'resnet50'
preprocess_input = get_preprocessing(BACKBONE)
model = Unet(BACKBONE,classes=2,input_shape=(256,256, 3), encoder_weights='imagenet',activation='sigmoid')
x_train = preprocess_input(x_train)
x = model.layers[-1].output
x = Conv2D(3, (1, 1), activation='sigmoid')(x)
model = Model(inputs=model.input, outputs=x)
model.compile(optimizer='Adam', loss='binary_crossentropy', metrics=['binary_accuracy'])
model.fit(x=x_train,y=y_train,batch_size=32,epochs=50)
Related
import cv2 as cv
import numpy as np
from google.colab.patches import cv2_imshow
from tensorflow.keras.models import load_model
img_color = cv.imread('test3.jpg', cv.IMREAD_COLOR)
img_gray = cv.cvtColor(img_color, cv.COLOR_BGR2GRAY)
ret,img_binary = cv.threshold(img_gray, 0, 255, cv.THRESH_BINARY_INV | cv.THRESH_OTSU)
kernel = cv.getStructuringElement( cv.MORPH_RECT, ( 5, 5 ) )
img_binary = cv.morphologyEx(img_binary, cv. MORPH_CLOSE, kernel)
cv2_imshow('digit', img_binary)
cv.waitKey(0)
This is the process of training a model in handwritten and testing the trained model.
I want to load an image using imshow() in colab.
Is there any way to use it without setting the file path?
You can use matplotlib's function for it
import matplotlib.pyplot as plt
%matplotlib inline
fig = plt.gcf()
fig.set_size_inches(18, 10)
plt.axis("off")
plt.rcParams['figure.figsize'] = [20, 10]
plt.imshow(img_binary)
plt.show()
This is my first attempt to solve task on the kaggle. This is page of the task - https://www.kaggle.com/c/bike-sharing-demand.
I wrote this code (I have some excess code lines, because I am not really sure what I need now):
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import keras
import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor
import matplotlib.pyplot as plt
import os
for dirname, _, filenames in os.walk('/kaggle/input'):
for filename in filenames:
print(os.path.join(dirname, filename))
train_data = pd.read_csv('/kaggle/input/bike-sharing-demand/train.csv')
train_targets = train_data[['casual', 'registered', 'count']]
train_datetime_helper = train_data[['datetime']]
dt = pd.DatetimeIndex(train_data['datetime'])
train_data['day'] = dt.day
train_data['month'] = dt.month
train_data['year'] = dt.year
train_data['hour'] = dt.hour
train_data['dow'] = dt.dayofweek
train_data['woy'] = dt.weekofyear
train_data = train_data.drop(['casual', 'registered', 'count', 'datetime'], axis=1)
test_data = pd.read_csv('/kaggle/input/bike-sharing-demand/test.csv')
test_datetime_helper = test_data[['datetime']]
dt = pd.DatetimeIndex(test_data['datetime'])
test_data['day'] = dt.day
test_data['month'] = dt.month
test_data['year'] = dt.year
test_data['hour'] = dt.hour
test_data['dow'] = dt.dayofweek
test_data['woy'] = dt.weekofyear
test_data = test_data.drop(['datetime'], axis=1)
mean = train_data.mean(axis=0)
train_data -= mean
std = train_data.std(axis=0)
train_data /= std
test_data -= mean
test_data /= std
from keras import models
from keras import layers
from keras.layers import Dense, Conv2D, Flatten
def build_model():
model = models.Sequential()
model.add(layers.Dense(64, activation='relu', input_shape=(train_data.shape[1], train_targets.shape[1])))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(1))
model.compile(optimizer='rmsprop', loss='mse', metrics=['mae'])
return model
k = 4
num_val_samples = len(train_data) // k
num_epochs = 100
all_scores = []
for i in range(k):
print('Processing fold #', i)
val_data = train_data[i * num_val_samples: (i + 1) * num_val_samples]
val_targets = train_targets[i * num_val_samples: (i + 1) * num_val_samples]
partial_train_data = np.concatenate(
[train_data[:i * num_val_samples],
train_data[(i + 1) * num_val_samples:]], axis=0)
partial_train_targets = np.concatenate(
[train_targets[:i * num_val_samples],
train_targets[(i + 1) * num_val_samples:]], axis=0)
model = build_model()
model.fit(partial_train_data, partial_train_targets,
epochs=num_epochs, batch_size=1, verbose=0)
val_mse, val_mae = model.evaluate(val_data, val_targets, verbose=0)
all_scores.append(val_mae)
I have got this error. Can you explain how can I solve it enter image description here
you specified wrong the input dimension of your model. try to define your first layer in this way
model.add(layers.Dense(64, activation='relu', input_shape=(train_data.shape[1],)))
PyTorch newbie here. I wrote a script (code below) that performs the following operations: load an image, perform a 2D convolution operation and then display the output and the input.
At present I have the image below, which seems off. How can I plot the feature map correctly?
import numpy as np
import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import matplotlib.pyplot as plt
import imageio
import sys
A = imageio.imread('LiT.png')
# Define how the convolution operation works
conv2 = nn.Conv2d(in_channels=3, out_channels=3, kernel_size=3, stride=1, padding=1)
image_d = torch.FloatTensor(np.asarray(A.reshape(1, 3, A.shape[0] , A.shape[1])))
fc = conv2(image_d)
fc1 = fc.permute(0, 2, 3, 1).reshape([516, 780, 3])
plt.figure(figsize=(16,8))
plt.subplot(1,2,1)
plt.imshow(A)
plt.subplot(1,2,2)
plt.imshow(fc1.data.numpy())
plt.show()
The issue with your code is this line
image_d = torch.FloatTensor(np.asarray(A.reshape(1, 3, A.shape[0] , A.shape[1])))
You can't just reshape the image you need to transpose the channels. As a remark for the future, if you get a stripy result like you did it's most likely some permutation/transposition or reshaping operation that's not correct.
Other than that I also scaled the input image to [0, 1] to show it properly. Below is the working code:
import numpy as np
import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import matplotlib.pyplot as plt
import imageio
import sys
A = imageio.imread('LiT.png')
# Define how the convolution operation works
conv2 = nn.Conv2d(in_channels=3, out_channels=3, kernel_size=3, stride=1, padding=1)
# from [H, W, C] to [C, H, W]
transposed_image = A.transpose((2, 0, 1))
# add batch dim
transposed_image = np.expand_dims(transposed_image, 0)
image_d = torch.FloatTensor(transposed_image)
fc = conv2(image_d)
fc1 = fc.permute(0, 2, 3, 1)[0]
result = fc1.data.numpy()
max_ = np.max(result)
min_ = np.min(result)
result -= min_
result /= max_
plt.figure(figsize=(16,8))
plt.subplot(1,2,1)
plt.imshow(A)
plt.subplot(1,2,2)
plt.imshow(result)
plt.show()
To my understanding, the problem lies in how you are permuting channels position in the image by using reshape. Instead, 'np.transpose or tensor.permute should be used. Using torch for permutation:
image_d = torch.FloatTensor(np.asarray(A)).unsqueeze(0).permute(0,3,1,2)
Or, if we want to handle the permutation part in numpy:
image_d = np.transpose(np.asarray(A), (2,0,1))
image_d = torch.FloatTensor(image_d).unsqueeze(0)
I have plotted few ROC curve to calculate the AUC. I am having ROC curve is actually doesn't plots like a curve. I have attached the images for better understanding. If any one can tell me what is wrong in there. I will be obliged. This is one kind of plot I am getting
This is the another type
However I am not getting a curve like this one.
This is the link to my dataset
https://drive.google.com/open?id=1luj8d863_IOA36cQTo772GEWgUsrXlbJ
I will thankful if anyone can help me understand the problem if any or if my curves are correct then why it is not actually in a curve like structure
import numpy as np
import pandas as pd
from sklearn.pipeline import Pipeline
from sklearn.decomposition import PCA
from keras.layers import Dense, Input
from keras.wrappers.scikit_learn import KerasClassifier
from keras.models import Model,Sequential
from keras.utils import np_utils
from sklearn.model_selection import train_test_split, cross_val_score, KFold
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder, MinMaxScaler, StandardScaler
from itertools import cycle
from sklearn.metrics import roc_curve, auc
from imblearn.over_sampling import SMOTE
seed = 7
np.random.seed(seed)
dataset = pd.read_csv('dataset/prostate.csv')
labels = dataset.values[:,-1]
features_set = dataset.iloc[:,0:12600]
oversampler = SMOTE(random_state=0)
oversampler_feature_set, oversampler_labels = oversampler.fit_sample(features_set,labels)
feature_df = pd.DataFrame(oversampler_feature_set)
labels_df = pd.DataFrame(oversampler_labels)
scalar = MinMaxScaler()
scaled_data = scalar.fit_transform(feature_df)
pca = PCA(n_components=30)
pca_data = pd.DataFrame(pca.fit_transform(scaled_data))
recreated_df = pd.concat([pca_data,labels_df], axis=1)
train, test = train_test_split(recreated_df,test_size=0.2)
X_train = train.values[:,0:30]
Y_train = train.values[:,-1]
X_test = test.values[:,0:30]
y_test = test.values[:,-1]
def my_model():
model = Sequential()
model.add(Dense(20, input_dim=30,activation='sigmoid'))
model.add(Dense(10, activation='sigmoid'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam',metrics=['accuracy'])
return model
estimator = KerasClassifier(build_fn=my_model, epochs=1000, batch_size=10, shuffle=True,verbose=1)
kfold = KFold(n_splits=10, shuffle=True, random_state=seed)
results = cross_val_score(estimator,X_train,Y_train, cv=kfold)
results.mean()
estimator.fit(X_train,Y_train)
y_pred = estimator.predict(X_test).ravel()
sensitivity, specificity, thresholds_keras = roc_curve(y_test,y_pred,pos_label=2)
auc_keras = auc(sensitivity,specificity)
plt.figure(1)
plt.plot([0, 1], [0, 1], 'k--')
plt.plot(sensitivity, specificity, label='Keras (area =:.3f})'.format(auc_keras))
plt.xlabel('Specificity')
plt.ylabel('Sensitivity')
plt.title('Prostate')
plt.legend(loc='best')
plt.show()
Here is my version of an autoencoder written using PyTorch :
import warnings
warnings.filterwarnings('ignore')
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib import pyplot as plt
from sklearn import metrics
import datetime
from sklearn.preprocessing import MultiLabelBinarizer
import seaborn as sns
sns.set_style("darkgrid")
from ast import literal_eval
import numpy as np
from sklearn.preprocessing import scale
import seaborn as sns
sns.set_style("darkgrid")
import torch
%matplotlib inline
f = []
f.append(np.random.uniform(0,10,(1 , 10)).flatten())
f.append(np.random.uniform(10,20,(1 , 10)).flatten())
f.append(np.random.uniform(20,30,(1 , 10)).flatten())
x_data = torch.FloatTensor(np.array(f))
x_data
dimensions_input = 10
hidden_layer_nodes = 5
output_dimension = 10
class Model(torch.nn.Module):
def __init__(self):
super(Model, self).__init__()
self.linear = torch.nn.Linear(dimensions_input,hidden_layer_nodes)
self.sigmoid = torch.nn.Sigmoid()
self.linear2 = torch.nn.Linear(hidden_layer_nodes,output_dimension)
def forward(self, x):
l_out1 = self.linear(x)
l_out2 = self.sigmoid(l_out1)
y_pred = self.linear2(l_out2)
return y_pred
model = Model()
criterion = torch.nn.MSELoss(size_average = False)
optim = torch.optim.SGD(model.parameters(), lr = 0.00001)
def train_model():
y_data = x_data.clone()
for i in range(150000):
y_pred = model(x_data)
loss = criterion(y_pred, y_data)
if i % 5000 == 0:
print(loss)
optim.zero_grad()
loss.backward()
optim.step()
Using x_data.clone() I train the network to learn a feature representation of the input data.
I'm attempting to generate hidden layer weights that match the dimensionality of rows of the input data so that each vector of x_data has a corresponding encoding. But the hidden later is of is a vector of size 5. How to change this network so that a matrix is generated that represents a reduced dimensionality of the input data ?