Image edge detection Keras model loss not improving

Question

I have a video of droplets. I have taken the first frame and manually marked the edges. I split up the image into smaller images. I then tried to train a keras model of the small unmarked images against the small marked images.

I've tried using "dense" layers. The model trains, but the loss does not improve. When I try using the model, it just gives me a black image output.

Marked split images

Input image (frame 1)

Model summary

#################### IMPORT AND SPLIT

from cam_img_split import cam_img_split
import cv2

img_tr_in=cv2.imread('frame 1.png')
img_tr_out=cv2.imread('frame 1 so far.png')
seg_shape=[32,32]

tr_in=cam_img_split(img_tr_in,seg_shape)
tr_out=cam_img_split(img_tr_out,seg_shape)

pl=[4,20] #images selected for training

##################### NEURAL NETWORK

import tensorflow as tf
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import adam

b_sha=np.prod(tr_in.shape[2:5]) #batch shape

model = Sequential()
model.add(Dense(b_sha, activation='relu'))
model.add(Dense(3072, activation='softmax'))
model.add(Dense(3072, activation='softmax'))
model.add(Dense(3072, activation='softmax'))
model.add(Dense(np.prod(tr_out.shape[2:5]), activation='softmax'))
model.compile(optimizer=adam(lr=0.1), loss='mean_squared_error', metrics=['accuracy'])

tr_in_sel=tr_in[0:pl[0],0:pl[1],:,:,:]
tr_out_sel=tr_out[0:pl[0],0:pl[1],:,:,:]

tr_in_sel_flat=tr_in_sel.reshape([np.prod(pl),b_sha])   #Flattening
tr_out_sel_flat=tr_in_sel.reshape([np.prod(pl),b_sha])

tr_in_sel_flat_norm=tr_in_sel_flat/255
tr_out_sel_flat_norm=tr_out_sel_flat/255

model.fit(tr_in_sel_flat_norm, tr_out_sel_flat_norm, epochs=10, batch_size=pl[0])

I expected an output matching the images with the marked edges. Instead I got a black image output.

Answer 1

I solved this problem by using 7x7 sections of the image to classify the central pixel of that section as either oil or water (1 or 0). I then used the binary_crossentropy loss function to train the model.

By having a 7x7 section moving one pixel at a time across the main image, I can have a lot more training data than just segmenting the main image.

I previously tried to get a 7x7 image from another 7x7 image, which made the problem more difficult.

#IMPORT AND SPLIT

from cam_img_split import cam_img_split
from cam_pad import cam_pad
from cam_img_bow import cam_img_bow
import cv2
import numpy as np

img_tr_in=cv2.imread('frame 1.png',0)[0:767,0:767]/255
img_tr_out=cv2.imread('frame 1 so far bnw 2.png',0)[0:767,0:767]/255
img_tr_out=(cam_img_bow(img_tr_out,0.5)).astype(np.uint8)

seg_shape=[15,15] #needs to be odd and equal to each other

pl_max=img_tr_in.shape[0:2]
pl=np.array([0.15*pl_max[0],pl_max[1]]).astype(np.uint32)

pad_in=int(np.floor(seg_shape[0]/2))

img_tr_in_pad=cam_pad(img_tr_in,pad_in)

tr_in=np.zeros([pl[0],pl[1],seg_shape[0],seg_shape[1]])

for n1 in range(0,pl[0]):
        for n2 in range(0,pl[1]):
                tr_in[n1,n2]=img_tr_in_pad[n1:n1+seg_shape[0],n2:n2+seg_shape[1]]


##################### NEURAL NETWORK

import tensorflow as tf
from keras.models import Sequential
from keras.layers import Dense,Dropout,Conv2D, MaxPooling2D, Flatten
from keras.optimizers import adam
from keras.utils import to_categorical
import matplotlib.pyplot as plt

pad=4

input_shape=(seg_shape[0]+2*pad,seg_shape[1]+2*pad,1)
output_shape=(1,1,1)

model = Sequential()
model.add(Conv2D(32, (3, 3),input_shape=input_shape, activation='relu'))
model.add(Conv2D(64,(3, 3), activation='relu'))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(units=2, activation='softmax'))

model.compile(optimizer=adam(lr=0.001), loss='binary_crossentropy', metrics=['accuracy'])


##################### FITTING THE MODEL

tr_in_flat=tr_in.reshape([pl[0]*pl[1],seg_shape[0],seg_shape[1],1])
tr_out_flat=img_tr_out.reshape([pl_max[0]*pl_max[1]])

tr_in_flat_pad=np.zeros(tr_in_flat.shape+np.array([0,2*pad,2*pad,0]))

for n3 in range(0,tr_in_flat.shape[0]):
        tr_in_flat_pad[n3,:,:,0]=cam_pad(tr_in_flat[n3,:,:,0], pad)

model.fit(tr_in_flat_pad, to_categorical(tr_out_flat[0:pl[0]*pl[1]]), epochs=5, batch_size=int(16*pl[0]),shuffle=True)


##################### PLOTTING PREDICTIONS

tr_in_full=np.zeros([pl_max[0],pl_max[1],seg_shape[0]+2*pad,seg_shape[1]+2*pad])

for n1 in range(0,pl_max[0]):
        for n2 in range(0,pl_max[1]):
                tr_in_full[n1,n2]=cam_pad(img_tr_in_pad[n1:n1+seg_shape[0],n2:n2+seg_shape[1]],pad)


tr_in_full_flat=tr_in_full.reshape([pl_max[0]*pl_max[1],seg_shape[0]+2*pad,seg_shape[1]+2*pad,1])

pred = model.predict(tr_in_full_flat)

pred_img=np.zeros(pred.shape[0])

for n1 in range(0,pred.shape[0]):
        pred_img[n1]=round(pred[n1,0])

pred_img_out=(pred_img.reshape([pl_max[0],pl_max[1]]))

plt.subplot(1,2,1)
plt.imshow(pred_img_out)

plt.subplot(1,2,2)
plt.imshow(img_tr_in)

plt.show()