I am trying to print a stylemix encoder image however my printed images are too small, I am not sure where am I doing wrong.
my latent space
jon = np.load('latent_representations/example0.npy')
drogo = np.load('latent_representations/example1.npy')
# Loading already learned latent directions
smile_direction = np.load('ffhq_dataset/latent_directions/smile.npy')
gender_direction = np.load('ffhq_dataset/latent_directions/gender.npy')
age_direction = np.load('ffhq_dataset/latent_directions/age.npy'
)
my draw style mix loop
def draw_style_mixing_figure(png, Gs, w, h, src_dlatents, dst_dlatents, style_ranges):
print(png)
#src_dlatents = Gs.components.mapping.run(src_latents, None) # [seed, layer, component]
#dst_dlatents = Gs.components.mapping.run(dst_latents, None)
src_images = Gs.components.synthesis.run(src_dlatents, randomize_noise=False, **synthesis_kwargs)
dst_images = Gs.components.synthesis.run(dst_dlatents, randomize_noise=False, **synthesis_kwargs)
canvas = PIL.Image.new('RGB', (w * (len(src_dlatents) + 1), h * (len(dst_dlatents) + 1)), 'white')
for col, src_image in enumerate(list(src_images)):
canvas.paste(PIL.Image.fromarray(src_image, 'RGB'), ((col + 1) * w, 0))
for row, dst_image in enumerate(list(dst_images)):
canvas.paste(PIL.Image.fromarray(dst_image, 'RGB'), (0, (row + 1) * h))
row_dlatents = np.stack([dst_dlatents[row]] * len(src_dlatents))
row_dlatents[:, style_ranges[row]] = src_dlatents[:, style_ranges[row]]
row_images = Gs.components.synthesis.run(row_dlatents, randomize_noise=False, **synthesis_kwargs)
for col, image in enumerate(list(row_images)):
canvas.paste(PIL.Image.fromarray(image, 'RGB'), ((col + 1) * w, (row + 1) * h))
canvas.save(png)
return canvas.resize((512,512))
my printing image order
tflib.init_tf()
synthesis_kwargs = dict(output_transform=dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True), minibatch_size=1)
_Gs_cache = dict()
draw_style_mixing_figure(os.path.join(config.result_dir, 'style-mixing.png'), Gs, w=1024, h=1024, src_dlatents=jon.reshape((1, 12, 512)), dst_dlatents=drogo.reshape((1, 12, 512)), style_ranges=[range(1,1)]),
But resulting pictures are too small
any idea how to make them bigger?
Related
I am using Connected components(NN) method to detect and correct the skew document.I have an image of skew document.I have done the following steps :
1.document image preprocessing.
2.elegible connected components
def imshow(image1):
plt.figure(figsize=(20,10)
plt.imshow(image1)
output = cv2.connectedComponentsWithStats(invr_binary, connectivity, cv2.CV_32S)
(numLabels, labels, stats, centroids) = output
## non text removal
w_avg=stats[1:, cv2.CC_STAT_WIDTH].mean()
h_avg=stats[1: , cv2.CC_STAT_HEIGHT].mean()
B_max=(w_avg * h_avg) * 4
B_min=(w_avg * h_avg) * 0.25
result = np.zeros((labels.shape), np.uint8)
output1=image.copy()
a, b=0.6, 2
for i in range(0, numLabels - 1):
area=stats[i, cv2.CC_STAT_AREA]
if area>B_min and area<B_max: ## non text removal
result[labels == i + 1] = 255
x = stats[i, cv2.CC_STAT_LEFT]
y = stats[i, cv2.CC_STAT_TOP]
w = stats[i, cv2.CC_STAT_WIDTH]
h = stats[i, cv2.CC_STAT_HEIGHT]
area = stats[i, cv2.CC_STAT_AREA]
(cX, cY) = centroids[i]
c=w/h
if a<c and c<b: ## A and C type filtering
result[labels == i + 1] = 255
cv2.rectangle(output1, (x, y), (x + w, y + h), (0, 255, 0), 1)
cv2.circle(output1, (int(cX), int(cY)), 1, (0, 0, 255), -1)
imshow(output1)
input image :
output image :
After finding the center points of the text which is shown in the output image.Now is the next step skew slop calculation. But I could not understand that how to calculate that.I am using that research papers link :3.3(page no. 7)
https://www.mdpi.com/2079-9292/9/1/55/pdf
I am trying to implement a custom dataset loader. Firstly I resize the images and labels with the same ratio between (0.98, 1,1) then I randomly crop both images and labels with same parameters so that I can feed them into NN. However, I am getting an error from PyTorch functional. Here is my code:
class RandomCrop(object):
def __init__(self, size, padding=None, pad_if_needed=True, fill=0, padding_mode='constant'):
self.size = size
self.padding = padding
self.pad_if_needed = pad_if_needed
self.fill = fill
self.padding_mode = padding_mode
#staticmethod
def get_params(img, output_size):
w, h = img.size
th, tw = output_size
if w == tw and h == th:
return 0, 0, h, w
i = random.randint(0, h - th)
j = random.randint(0, w - tw)
return i, j, th, tw
def __call__(self, data):
img,mask = data["image"],data["mask"]
# pad the width if needed
if self.pad_if_needed and img.size[0] < self.size[1]:
img = F.pad(img, (self.size[1] - img.size[0], 0), self.fill, self.padding_mode)
mask = F.pad(mask, (self.size[1] - mask.size[0], 0), self.fill, self.padding_mode)
# pad the height if needed
if self.pad_if_needed and img.size[1] < self.size[0]:
img = F.pad(img, (0, self.size[0] - img.size[1]), self.fill, self.padding_mode)
mask = F.pad(mask, (0, self.size[0] - mask.size[1]), self.fill, self.padding_mode)
i, j, h, w = self.get_params(img, self.size)
crop_image = transforms.functional.crop(img, i, j, h, w)
crop_mask = transforms.functional.crop(mask, i, j, h, w)
return{"image": crop_image, "mask": crop_mask }
Here is the error:
AttributeError: 'Image' object has no attribute 'dim'
Mistakenly I imported nn.functional.pad instead of the transforms.functional.pad. After changing it everything went smoothly
This is my Code of Mask Detection using YOLOV3 weights created by me. Whenever I run my Program, I experience a delay in my output Video of detection. This is the code please have a look.
import cv2
import numpy as np
net = cv2.dnn.readNet("yolov3_custom_final.weights", "yolov3_custom.cfg")
with open("obj.name", "r") as f:
classes = f.read().splitlines()
cap = cv2.VideoCapture(0 + cv2.CAP_DSHOW)
while True:
ret, img = cap.read()
height, weight, _ = img.shape
blob = cv2.dnn.blobFromImage(img, 1 / 255, (416, 416), (0, 0, 0), swapRB=True, crop=False)
net.setInput(blob)
output = net.getUnconnectedOutLayersNames()
layers = net.forward(output)
box = []
confidences = []
class_ids = []
for out in layers:
for detection in out:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.3:
centre_x = int(detection[0] * weight)
centre_y = int(detection[1] * height)
w = int(detection[2] * weight)
h = int(detection[3] * height)
x = int(centre_x - w / 2)
y = int(centre_y - h / 2)
box.append([x, y, w, h])
confidences.append(float(confidence))
class_ids.append(class_id)
indexes = np.array(cv2.dnn.NMSBoxes(box, confidences, 0.5, 0.4))
font = cv2.FONT_HERSHEY_PLAIN
colors = np.random.uniform(0, 255, size=(len(box), 3))
for i in indexes.flatten():
x, y, w, h = box[i]
label = str(classes[class_ids[i]])
confidence = str(round(confidences[i], 2))
color = colors[i]
cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
cv2.putText(img, label + "I" + confidence, (x, y + 20), font, 2, (255, 255, 255), 2)
cv2.imshow("Final", img)
if cv2.waitKey(1) & 0xff == ord("q"):
break
cap.release()
cv2.destroyAllWindows()
Can someone Please help me in this Issue or suggest a way to reduce the Lag in my Output videostream ?
As I have done some research over the Time, I have a found a Possible answer to this question. As I'm running my YOLO model in my local system which has no GPU, This is the factor that is causing a delay in the Output as it Processes a frame and takes another frame after completion.
I am trying to implement Floyd-Steinberg dithering in Python after using KMeans. I realised, that after dithering I receive colours which are not included in the reduced palette, so I modify the image again with KMeans. However, when trying with this picture, I see no dithering at all. I got stucked, I got tired - please, help me. My ideas become almost extinct.
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
k = 16
im = Image.open('Image.png').convert('RGB') #Image converted to RGB
pic = np.array(im, dtype = np.float)/255 #Enables imshow()
im.close()
def kmeans(pic): #Prepares algorithmic data
v, c, s = pic.shape
repic = np.resize(pic, (c*v, 3))
kme = KMeans(n_clusters = k).fit(repic)
cl = kme.cluster_centers_
return kme, cl, repic, v, c
kme, cl, repic, v, c = kmeans(pic)
pred = kme.predict(repic)
def picture(v, c, cl, pred): #Creates a picture with reduced colors
image = np.ones((v, c, 3))
ind = 0
for i in range(v):
for j in range(c):
image[i][j] = cl[pred[ind]]
ind+=1
return image
image = picture(v, c, cl, pred)
def dither(pic, image): #Floyd-Steinberg dithering
v, c, s = pic.shape
Floyd = np.copy(image)
for i in range(1, v-1):
for j in range(1, c-1):
quan = pic[i][j] - image[i][j]
Floyd[i][j + 1] = quan * (np.float(7 / 16)) + pic[i][j + 1]
Floyd[i + 1][j - 1] = quan * (np.float(5 / 16)) + pic[i + 1][j - 1]
Floyd[i + 1][j] = quan * (np.float(3 / 16)) + pic[i + 1][j]
Floyd[i + 1][j + 1] = quan * (np.float(1 / 16)) + pic[i + 1][j + 1]
return Floyd
fld = dither(pic, image)
a1, a2, reim, a3, a4 = kmeans(fld)
lab = kme.predict(reim)
Floyd = picture(v, c, cl, lab)
plt.imshow(Floyd)
plt.show()
I'm really hoping for some help on this as it has me absolutely stumped. I have the code working on its own as per below:
from tkinter import *
from PIL import ImageTk
dam_level = [75]
c = Canvas(width = 200, height = 235, relief = "sunken", borderwidth = 2)
c.grid(row = 11, rowspan = 8, column = 4, columnspan = 2)
c_width = 200
c_height = 250
y_stretch = 1.9
y_gap = 35
x_stretch = 15
x_width = 90
x_gap = 30
for x, y in enumerate(dam_level):
x0 = x * x_stretch + x * x_width + x_gap
y0 = c_height - (y * y_stretch + y_gap)
x1 = x * x_stretch + x * x_width + x_width + x_gap
y1 = c_height - y_gap
c.create_rectangle(x0, y0, x1, y1, fill = "#008ae8")
y = (str(y))
c.create_text(x0 + 10, y0, anchor = SW, text = (y, "%"))
c.create_text(x0 + 60, y1 + 5, anchor = N, text = "Catchment")
photo = ImageTk.PhotoImage(file =
"/Users/Name/Desktop/python3.4/water.png")
c.create_image(10, 10, image = photo, anchor = NW)
mainloop()
However when I put it in my main application in its own function (with the rest of my code), the image won't display. The graph and canvas displays, just not the water.png image. There's no error log or anything. The only change I make when I put this in my app is adding 'self' to this line. (And I remove the 'mainloop()' of course).
c = Canvas(self, width = 200, height = 235, relief = "sunken", borderwidth = 2)
Any suggestions would be greatly appreciated.
Thanks Bryan, for pointing me in the right direction.
Fixed with:
c.image = photo