to extract features from xcption model
I'm working on Image caption generator using cnn and lstm and i shared the code i got from a site. I tried to solve it but when i do changes in code I'm getting error on some other part so can anyone plaese tell me how to solve this
def extract_features(directory):
model = Xception( include_top=False, pooling='avg' )
features = {}
for img in tqdm(os.walk(directory)):
filename = directory + "/" + img
image = Image.open(filename)
image = image.resize((299,299))
image = np.expand_dims(image, axis=0)
#image = preprocess_input(image)
image = image/127.5
image = image - 1.0
feature = model.predict(image)
features[img] = feature
return features
#2048 feature vector
features = extract_features(dataset_images)
dump(features, open("features.p","wb"))
error
TypeError Traceback (most recent call last)
<ipython-input-8-5f1d4e4e3211> in <module>()
16
17 #2048 feature vector
---> 18 features = extract_features(dataset_images)
19 dump(features, open("features.p","wb"))
<ipython-input-8-5f1d4e4e3211> in extract_features(directory)
3 features = {}
4 for img in tqdm(os.walk(directory)):
----> 5 filename = directory + "/" + img
6 image = Image.open(filename)
7 image = image.resize((299,299))
TypeError: can only concatenate str (not "tuple") to str
In your case img in filename = directory + "/" + img is a tuple and directory is a string, so they cannot be concatenated.
So you have loop through img. In that case you might get another error because img includes root directory and sub directories.
def extract_features(directory):
model = Xception( include_top=False, pooling='avg' )
features = {}
for (root,dirs,files) in tqdm(os.walk(directory)):
for img in files:
filename = directory + "/" + img
image = Image.open(filename)
image = image.resize((299,299))
image = np.expand_dims(image, axis=0)
#image = preprocess_input(image)
image = image/127.5
image = image - 1.0
feature = model.predict(image)
features[img] = feature
return features
Related
I'm preparing a set of medical imaging volumes and segmentation masks to be input into a multi-label segmentation neural network for training. I am recieving the following error message when I attempt to load my 5D tensors into a torch TensorDataset:
Traceback (most recent call last):
File (path/project.py), line 122, in <module>
train_dataset = torch.utils.data.TensorDataset(timg, tmask)
File (path/dataset.py), line 365, in __init__
assert all(tensors[0].size(0) == tensor.size(0) for tensor in tensors), "Size mismatch between tensors"
File (path/dataset.py)", line 365, in <genexpr>
assert all(tensors[0].size(0) == tensor.size(0) for tensor in tensors), "Size mismatch between tensors"
TypeError: 'numpy.int32' object is not callable
My original assumption was that the size mismatch was due to the difference in the dimensions of my tensors -- the feature tensor had dimensions 60x128x128x64x1 and the label tensor had dimensions 60x128x128x64x5. However, making the shape and size of these tensors equal has not resolved the issue. My other theory was that the issue was related to this line of code:
def transt(list):
array = np.asarray(list, ->np.int32<-)
changing the dtype did not seem to have an effect. I also tried casting the tensor into different dtypes, again to seemingly no effect on the problem.
Attached is the code. Unsure of how to proceed and any advice would be very appreciated.
import numpy as np
import os
import tensorflow as tf
import nibabel as nib
import matplotlib.pyplot as plt
from VNet import VNet
import Layers
import torchvision
from torchvision.transforms import ToTensor
import torch
from torch.utils.data import TensorDataset, DataLoader
from tensorflow.python.ops.numpy_ops import np_config
np_config.enable_numpy_behavior()
# Setting path
dirname = os.path.dirname(__file__)
path = os.path.join(dirname, 'Liver_MR_Dataset')
# Loading images/masks
img_list = []
gall_list = []
IVC_list = []
kidney_list = []
liver_list = []
rib_list = []
os.chdir(path + '/Image')
image_path = sorted(os.listdir(path + '/Image'))
for image in image_path:
img = nib.load(image).get_fdata()
img_list.append(img)
print(len(img_list))
train_img = img_list[:60]
print(len(train_img))
val_img = img_list[60:]
print(len(val_img))
os.chdir(path + '/Gall')
gall_path = sorted(os.listdir(path + '/Gall'))
for image in gall_path:
mask = nib.load(image).get_fdata()
gall_list.append(mask)
train_gall = gall_list[:60]
val_gall = gall_list[60:]
os.chdir(path + '/IVC')
IVC_path = sorted(os.listdir(path + '/IVC'))
for image in IVC_path:
mask = nib.load(image).get_fdata()
IVC_list.append(mask)
train_IVC = IVC_list[:60]
val_IVC = IVC_list[60:]
os.chdir(path + '/Kidney')
kidney_path = sorted(os.listdir(path + '/Kidney'))
for image in kidney_path:
mask = nib.load(image).get_fdata()
kidney_list.append(mask)
train_kidney = kidney_list[:60]
val_kidney = kidney_list[60:]
os.chdir(path + '/Liver')
liver_path = sorted(os.listdir(path + '/Liver'))
for image in liver_path:
mask = nib.load(image).get_fdata()
liver_list.append(mask)
train_liver = liver_list[:60]
val_liver = liver_list[60:]
os.chdir(path + '/Rib')
rib_path = sorted(os.listdir(path + '/Rib'))
for image in rib_path:
mask = nib.load(image).get_fdata()
rib_list.append(mask)
train_rib = rib_list[:60]
val_rib = rib_list[60:]
os.chdir(path)
# Transformations
def transt(list):
array = np.asarray(list, np.int32)
resize = np.resize(array, [60,128,128,64])
tensor = tf.convert_to_tensor(resize)
return tensor
def transv(list):
array = np.asarray(list, np.int32)
resize = np.resize(array, [7,128,128,64])
tensor = tf.convert_to_tensor(resize)
return tensor
tgall = transt(train_gall)
vgall = transv(val_gall)
tIVC = transt(train_IVC)
vIVC = transv(val_IVC)
tkidney = transt(train_kidney)
vkidney = transv(val_kidney)
tliver = transt(train_liver)
vliver = transv(val_liver)
trib = transt(train_rib)
vrib = transv(val_rib)
timg4d = transt(train_img)
vimg4d = transv(val_img)
timg = tf.stack([timg4d, timg4d, timg4d, timg4d, timg4d], axis=4)
print(timg.shape)
print(timg.size)
vimg = tf.stack([timg4d, timg4d, timg4d, timg4d, timg4d], axis=4)
tmask = tf.stack([tgall, tIVC, tkidney, tliver, trib], axis=4)
print(tmask.shape)
print(tmask.size)
vmask = tf.stack([vgall, vIVC, vkidney, vliver, vrib], axis=4)
# Create Datasets
train_dataset = torch.utils.data.TensorDataset(timg, tmask)
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=60)
#val_dataset = torch.utils.data.TensorDataset(vimg, vmask)
#val_loader = torch.utils.data.DataLoader(val_dataset, batch_size=60)
size is a tuple, all(tensors[0].size[0] == tensor.size[0] for tensor in tensors),
First of all i already load my model to predict inference set that i already prepared, but i got error when to try predict and show the result.
so here my code
def load_img(filename):
img = read_file(filename) # Load Data
img = decode_image(img, channels=3) # convert to RGB
img = resize(img, size=[img_height, img_height])
img = np.array(img)[:,:,1] # Resize image
img = img/255. # Rescale Images
return img
inf1 = load_img(r'ML2\COVID-19\inf_set\covid\covid - 1.jpeg')
inf2 = load_img(r'ML2\COVID-19\inf_set\covid\covid - 2.jpeg')
inf3 = load_img(r'ML2\COVID-19\inf_set\normal\Normal - 1.jpeg')
inf4 = load_img(r'ML2\COVID-19\inf_set\normal\Normal - 2.jpeg')
inf5 = load_img(r'ML2\COVID-19\inf_set\pneumonia\Pneumonia - 1.jpeg')
inf6 = load_img(r'ML2\COVID-19\inf_set\pneumonia\Pneumonia - 2.jpeg')
plt.figure(figsize=(35, 5))
plt.suptitle('Prediction Results', fontsize=15)
counter = 1
for i in [inf1,inf2, inf3, inf4, inf5,inf6]:
plt.subplot(1,6,counter)
res = int(tf.round(model.predict(x=expand_dims(i, axis=0))))
plt.imshow(i)
plt.title(f"Prediction: {label_data[res]}")
plt.axis('off')
counter += 1
plt.show()
And here the error notification
So, i need help to solve this proble, thank you before
You are squashing the image size in this line
img = np.array(img)[:,:,1]
This is why your image becomes size (220,220) instead of (220,220,1), which when you do expand_dims will be of proper input shape (1,220,220,1)
You could change the load_img function, or you could solve this by doing
res = int(tf.round(model.predict(x=expand_dims(i, axis=[0,3]))))
The problem: I am unable to process CNN model for training 8-channel .TIF images.
Expected Output: Map training data (train_ds) via gdal and train model.
data (images):
n = 600
shape = (256, 256, 8)
data structure:
project_photos/
....classes/
......barren/
......agriculture/
......wooded/
import numpy as np
import os
import PIL
import PIL.Image
import tensorflow as tf
import tensorflow_datasets as tfds
import pathlib
>print (tf.__version__)
2.1.0
data_dir = ".\projects\keras\projectA\project_photos\classes")
data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*.tif')))
>print(image_count)
600
list_ds = tf.data.Dataset.list_files(str(data_dir/'*/*'), shuffle=False)
list_ds = list_ds.shuffle(image_count, reshuffle_each_iteration=False)
batch_size = 32
img_height = 256
img_width = 256
>for f in list_ds.take(5):
> print(f.numpy())
b'/home/projects/keras/projectA/project_photos/classes/barren/12345_b0001.tif'
b'/home/projects/keras/projectA/project_photos/classes/wooded//12345_w0001.tif'
b'/home/projects/keras/projectA/project_photos/classes/barren/12345_b0002.tif'
b'/home/projects/keras/projectA/project_photos/classes/agriculture//12345_a0001.tif'
b'/home/projects/keras/projectA/project_photos/classes/wooded/12345_w0002.tif'
# tree structure
>class_names = np.array(sorted([item.name for item in data_dir.glob('*')]))
print(class_names)
['barren' 'agriculture' 'wooded']
# train/validation split
val_size = int(image_count * 0.2)
train_ds = list_ds.skip(val_size)
val_ds = list_ds.take(val_size)
def get_label(file_path):
# convert the path to a list of path components
parts = tf.strings.split(file_path, os.path.sep)
# The second to last is the class-directory
one_hot = parts[-2] == class_names
# Integer encode the label
return tf.argmax(one_hot)
def decode_img(img):
# convert the compressed string to a 3D uint8 tensor
img = tf.image.decode_jpeg(img, channels=3)
# resize the image to the desired size
return tf.image.resize(img, [img_height, img_width])
def process_path(file_path):
label = get_label(file_path)
# load the raw data from the file as a string
img = tf.io.read_file(file_path)
img = decode_img(img)
return img, label
# Set `num_parallel_calls` so multiple images are loaded/processed in parallel.
train_ds = train_ds.map(process_path, num_parallel_calls=AUTOTUNE)
val_ds = val_ds.map(process_path, num_parallel_calls=AUTOTUNE)
I understand that tensorflow has limited support (experimental) for decode_tiff, and even if that did work - I am unable to use the latest version of TF that has that update.
This leaves me with attempting workarounds, the following - which have not succeeded:
"""
Updating decode_img(img) in attempt to process 8-channel .TIF raster
"""
#attempt, adding gdal_Open variable to decode_img
## fails due to image path (train_ds) being stored as byte.
x = gdal.Open(file_path)
Error: Not a string.
#attempt, modifying to extract PATH as str().
def process_path(file_path):
label = get_label(file_path)
# load the raw data from the file as a string
img = ''
for fpath in file_path:
img = fpath.numy()
img = decode_img(img)
return img, label
>train_ds = train_ds.map(process_path, num_parallel_calls=AUTOTUNE)
ValueError: len requires a non-scalar tensor, got one of shape Tensor("Shape:0", shape=(0,), dtype=int32)
#attempt, processing outside of `.map`, works just fine.
imgList = []
for elem in train_ds:
img = elem.numpy()
img = img.decode()
imgList.append(img)
file_path = imgList[0]
raster = gdal.Open(file_path)
bands = [raster.GetRasterBand(k + 1).ReadAsArray() for k in range (raster.RasterCount)]
n_bands = len(bands)
img_array = np.stack(bands,2)
img = tf.convert_to_tensor(img_array, dtype = tf.float32)
img = tf.image.resize(img, [img_height, img_width])
print(type(img))
print(img.numpy().shape)
<class: 'tensorflow.python.framework.ops.EagerTensor'>
(256, 256, 8)
So, any ideas on how I can get this to work within the TF framework - getting TF to process the raster via .map?
I have a Tensorflow input pipeline that reads in two png files (example, label) from disk. I want to tell tensorflow to skip an example/label pair based on a value in the label. Anyone know how to do this?
Here is a simplified example of the input pipeline and with a comment where I want to do the filtering:
import tensorflow as tf
import glob2 as glob
def preprocess_images(impath, labpath):
image = tf.io.read_file(impath)
label = tf.io.read_file(labpath)
image = tf.image.decode_png(image, channels=3)
label = tf.image.decode_png(label, channels=1)
if tf.reduce_sum(label) == 0:
#skip the image and move on to the next, don't include this in the batch
else:
return (image, label)
im_files = glob.glob(impath + '*.png')
lab_files = glob.glob(labpath + '*.png')
files = (im_files, lab_files)
path = tf.data.Dataset.from_tensor_slices(files)
pair = path.map(preprocess_images)
ds = tf.data.Dataset.zip(pair)
ds = ds.batch(64)
The easiest way seems to be to use filter method on your tf.data.Dataset object.
Here I am going to load the label only and filter out the entries with a sum of 0:
def load_label_only(impath, labpath):
label = tf.io.read_file(labpath)
label = tf.image.decode_png(label, channels=1)
return impath, label
# Create the dataset as in your example:
im_files = glob.glob(impath + '*.png')
lab_files = glob.glob(labpath + '*.png')
files = (im_files, lab_files)
ds = tf.data.Dataset.from_tensor_slices(files)
ds = ds.map(load_label_only)
# Here, I am going to keep only non-zero labels:
filtered_ds = ds.filter(lambda image_path, label_map: tf.reduce_sum(label_map) != 0)
# Load the rest of the images...
I am applying augmentation to 493 classes and each class has 1 or 2 or 3 or 4 images (its not known 1 class may have only 1 image other may have 2 images). When I apply augmentation using ImageDataGenerator I get the augmented images but the name of the images are generated randomly , I want the augemnted image name as the original image name.I tried some code:
from keras.preprocessing.image import ImageDataGenerator
from keras.applications.inception_v3 import preprocess_input
import glob,os
path = './newaug'
outpath = './newaug_result5/'
filenames = glob.glob(path + "/**/*.png",recursive=True)
imgnum=50
print (filenames)
for img in filenames:
if "DS_Store" in img: continue
src_fname, ext = os.path.splitext(img)
train_datagen=ImageDataGenerator(
preprocessing_function=preprocess_input,
rotation_range = 10,
width_shift_range=0.05,
height_shift_range=0.05,
fill_mode='constant',cval=0.0)
jf_datagen=ImageDataGenerator(
preprocessing_function=preprocess_input
)
img_name = src_fname.split('/')[-1]
new_dir = os.path.join(outpath, src_fname.split('/')[-1].rsplit('-', 1)[0])
if not os.path.lexists(new_dir):
os.mkdir(new_dir)
#save_fname = os.path.join(new_dir, os.path.basename(img_name))
save_fname = new_dir
i=0
train_generator=train_datagen.flow_from_directory(path,target_size=(224,224),
save_to_dir=save_fname)
for batch in train_generator:
i += 1
if i > imgnum:
break
for batch in jf_datagen.flow_from_directory(path,target_size=(224,224),
save_to_dir=save_fname):
i += 1
if i > imgnum:
break
What I am getting is and images also belong to different classes.
classname1/
|-01_133214.png
|-02_43434.png (This image actually belongs to class 2)
classname2/
|-01_13333214.png(This image actually belongs to class 1)
|-02_4343334.png
|-03_13333214.png(This image actually belongs to class 3)
What I want is , generate the folder same as class and also the augmented images should be save in the same class and name should be same as original image.
classname1/ (Images should belong to same class, for eg 01 signifies classname1)
|classname1-01_2424424.png
|classname1-01_2134242.png
|
|classname1-01_232424.png
classname2/
|classname2-02_323212.png
|classname2-02_321313.png
|
|classname2-02_333339.png
It worked using flow instead of flow_from_directory.
The code is:
import numpy as np
import keras,glob,os
import cv2
from keras.preprocessing.image import ImageDataGenerator, array_to_img,img_to_array, load_img
img_path = './newaug'
outpath = './newaug_result7/'
filenames = glob.glob(img_path + "/**/*.png",recursive=True)
for img in filenames:
if "DS_Store" in img: continue
src_fname, ext = os.path.splitext(img)
datagen = ImageDataGenerator(rotation_range = 10,
width_shift_range=0.05,
height_shift_range=0.05,
fill_mode='constant',cval=0.0)
img = load_img(img)
x = img_to_array(img)
x = x.reshape((1,) + x.shape)
img_name = src_fname.split('/')[-1]
new_dir = os.path.join(outpath, src_fname.split('/')[-1].rsplit('-', 1)[0])
if not os.path.lexists(new_dir):
os.mkdir(new_dir)
#save_fname = os.path.join(new_dir, os.path.basename(img_name))
save_fname = new_dir
i = 0
for batch in datagen.flow (x, batch_size=1, save_to_dir = save_fname,
save_prefix = img_name, save_format='jpg'):
i+=1
if i>51:
break