def main():
st.title("Semantic Segmentation App for Images")
st.text("Built with gluoncv and Streamlit")
st.markdown(
"""### [Semantic Segmentation](https://towardsdatascience.com/semantic-segmentation-with-deep-learning-a-guide-and-code-e52fc8958823)\
` `[PSPNet](https://towardsdatascience.com/review-pspnet-winner-in-ilsvrc-2016-semantic-segmentation-scene-parsing-e089e5df177d) \
` `[[Paper]](https://arxiv.org/abs/1612.01105)\
` `[](https://github.com/Hardly-Human/Semantic-Segmentation-of-Images)\
` `[](https://lbesson.mit-license.org/)"""
)
image_file = st.file_uploader("Upload Image", type=['jpg', 'png', 'jpeg'])
if image_file is None:
st.warning(
"Upload Image and Run Model (Use Image size <300 KB for faster inference)"
)
if image_file is not None:
image1 = Image.open(image_file)
rgb_im = image1.convert('RGB')
image2 = rgb_im.save("saved_image.jpg")
image_path = "saved_image.jpg"
st.image(image1, width=500, height=500)
if st.button("Run Model"):
st.warning("Loading Model..🤞")
model = load_model('psp_resnet101_ade')
img = image.imread(image_path)
img = test_transform(img, ctx)
st.success("Loaded Model Succesfully!!🤩👍")
plot_image(model, img)
def process_frame(self, frame, frame_count, frameWidth, frameHeight):
fcx = frame_width // 2
fcy = frame_height // 2
percent = 0.2
rightcx = int(fcx + percent * frame_width)
leftcx = int(fcx - percent * frame_width)
signal = Signal.NoPipe
# cropped based on 240
frm = cv2.resize(frame, (224, 224))
img = mx.nd.array(frm, ctx=self.ctx)
img = test_transform(img, ctx=self.ctx)
output = self.model.predict(img)
argx = mx.nd.topk(output, 1)
predict = np.squeeze(argx).asnumpy()
if (frame_count > 1):
predict = self.etha * predict + (1 - self.etha) * self.previous
self.previous = copy.copy(predict)
ret, mask = cv2.threshold(predict.astype(float), .5, 255,
cv2.THRESH_BINARY)
if cv2.countNonZero(mask) > 0:
mask = cv2.resize(mask, (frameWidth, frameHeight))
im2, contours, h = cv2.findContours(mask.astype(np.uint8),
cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
if (len(contours) > 0):
contourMask = max(contours, key=cv2.contourArea)
# Centroid
M = cv2.moments(contourMask)
if M['m00'] != 0:
cx = int(M['m10'] / M['m00'])
cy = int(M['m01'] / M['m00'])
self.kalman.correct(
np.array([[np.float32(cx)], [np.float32(cy)]],
np.float32))
cent = self.kalman.predict()
if frame_count >= 25:
cx = np.int(cent[0][0])
cy = np.int(cent[1][0])
signal = self.find_signal(cx, leftcx, rightcx)
# Centroid
cv2.circle(frame, (cx, cy), 0, (0, 255, 255), 5)
# rectangle
rect = cv2.minAreaRect(contourMask)
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(frame, [box], 0, (255, 255, 255), 1)
return frame, cx, cy, signal.value
return frame, 0, 0, Signal.NoPipe.value
def getSeg(self, np_img, saved_name=''):
np_img = np.array(np_img)
np_img = mx.ndarray.array(np_img)
img = test_transform(np_img, self.ctx)
# print(img)
output = self.model.predict(img)
predict = mx.nd.squeeze(mx.nd.argmax(output, 1)).asnumpy()
predict = predict.astype(numpy.uint8)
if saved_name != '':
try:
io.imsave(saved_name, predict, check_contrast=False)
except Exception as e:
print("Error in saving file in getSeg():", e, saved_name)
return predict
import mxnet as mx
from mxnet import image
from mxnet.gluon.data.vision import transforms
import gluoncv
import cv2
# using cpu
ctx = mx.cpu(0)
filename= '71.jpeg'
# load the image
img = image.imread(filename)
from matplotlib import pyplot as plt
#plt.imshow(img.asnumpy())
#plt.show()
from gluoncv.data.transforms.presets.segmentation import test_transform
img = test_transform(img, ctx)
# get pre-trained model
model = gluoncv.model_zoo.get_model('fcn_resnet101_voc', pretrained=True)
output = model.predict(img)
predict = mx.nd.squeeze(mx.nd.argmax(output, 1)).asnumpy()
from gluoncv.utils.viz import get_color_pallete
import matplotlib.image as mpimg
mask = get_color_pallete(predict, 'pascal_voc')
mask.save('output.png')
def main():
start = timer()
print('Processing Start time: %.1f' % (start))
print("current time", datetime.now())
gauth = GoogleAuth()
gauth.LocalWebserverAuth()
drive = GoogleDrive(gauth)
# Auto-iterate through all files that matches this query
file_list = drive.ListFile({'q': "'root' in parents"}).GetList()
for file in file_list:
# print('title: {}, id: {}'.format(file1['title'], file1['id']))
file_id = None
if file['title'] == "semanticsegmentation":
print('Folder Found')
file_id = file['id']
break
if file_id is not None:
classes = ["wall","building;edifice","sky","floor;flooring","tree","ceiling","road;route","bed","windowpane;window","grass","cabinet","sidewalk;pavement","person;individual;someone;somebody;mortal;soul","earth;ground","door;double;door","table","mountain;mount","plant;flora;plant;life","curtain;drape;drapery;mantle;pall","chair","car;auto;automobile;machine;motorcar","water","painting;picture","sofa;couch;lounge","shelf","house","sea","mirror","rug;carpet;carpeting","field","armchair","seat","fence;fencing","desk","rock;stone","wardrobe;closet;press","lamp","bathtub;bathing;tub;bath;tub","railing;rail","cushion","base;pedestal;stand","box","column;pillar","signboard;sign","chest;of;drawers;chest;bureau;dresser","counter","sand","sink","skyscraper","fireplace;hearth;open;fireplace","refrigerator;icebox","grandstand;covered;stand","path","stairs;steps","runway","case;display;case;showcase;vitrine","pool;table;billiard;table;snooker;table","pillow","screen;door;screen","stairway;staircase","river","bridge;span","bookcase","blind;screen","coffee;table;cocktail;table","toilet;can;commode;crapper;pot;potty;stool;throne","flower","book","hill","bench","countertop","stove;kitchen;stove;range;kitchen;range;cooking;stove","palm;palm;tree","kitchen;island","computer;computing;machine;computing;device;data;processor;electronic;computer;information;processing;system","swivel;chair","boat","bar","arcade;machine","hovel;hut;hutch;shack;shanty","bus;autobus;coach;charabanc;double-decker;jitney;motorbus;motorcoach;omnibus;passenger;vehicle","towel","light;light;source","truck;motortruck","tower","chandelier;pendant;pendent","awning;sunshade;sunblind","streetlight;street;lamp","booth;cubicle;stall;kiosk","television;television;receiver;television;set;tv;tv;set;idiot;box;boob;tube;telly;goggle;box","airplane;aeroplane;plane","dirt;track","apparel;wearing;apparel;dress;clothes","pole","land;ground;soil","bannister;banister;balustrade;balusters;handrail","escalator;moving;staircase;moving;stairway","ottoman;pouf;pouffe;puff;hassock","bottle","buffet;counter;sideboard","poster;posting;placard;notice;bill;card","stage","van","ship","fountain","conveyer;belt;conveyor;belt;conveyer;conveyor;transporter","canopy","washer;automatic;washer;washing;machine","plaything;toy","swimming;pool;swimming;bath;natatorium","stool","barrel;cask","basket;handbasket","waterfall;falls","tent;collapsible;shelter","bag","minibike;motorbike","cradle","oven","ball","food;solid;food","step;stair","tank;storage;tank","trade;name;brand;name;brand;marque","microwave;microwave;oven","pot;flowerpot","animal;animate;being;beast;brute;creature;fauna","bicycle;bike;wheel;cycle","lake","dishwasher;dish;washer;dishwashing;machine","screen;silver;screen;projection;screen","blanket;cover","sculpture","hood;exhaust;hood","sconce","vase","traffic;light;traffic;signal;stoplight","tray","ashcan;trash;can;garbage;can;wastebin;ash;bin;ash-bin;ashbin;dustbin;trash;barrel;trash;bin","fan","pier;wharf;wharfage;dock","crt;screen","plate","monitor;monitoring;device","bulletin;board;notice;board","shower","radiator","glass;drinking;glass","clock","flag"]
files = glob.glob(r'/Users/divyachandana/Documents/NJIT/work/summertasks/jun1-jun5/atlanta/*.jpg')
print("Total Files",len(files))
columns = ['filename','class','total_pixel','individual_pixel','ratio','timestamp']
# ---------- drive code -----
with open('semantic_results_atlanta.csv','a') as csvfile:
csvwriter = csv.writer(csvfile,lineterminator='\n')
# csvwriter.writerow(columns)
# i=0
for f in files:
file_check_query = "select count(*) from {} where filename like '%{}%'".format('semantic_results_atlanta', os.path.basename(f))
# print(file_check_query)
# i += 1
# print(i)
count = dbms.get_count_result(file_check_query)
# print(count)
if count > 0: continue
# print('resuming',f)
try:
img = image.imread(f)
img = image.resize_short(img, 1024)
# img = image.resize_short(img, 100)
# print("filename: ", f)
# ctx = mx.gpu(0)
img = test_transform(img, ctx)
# print("img: ", img)
output = model.predict(img)
# print("output: ", output)
predict = mx.nd.squeeze(mx.nd.argmax(output, 1)).asnumpy()
# print("predict: ", predict)
mask = get_color_pallete(predict, 'ade20k')
# predict.save('predict.png')
# mmask = mpimg.imread('output.png')
predict = predict.astype(numpy.uint8)
convert_single_array = numpy.array(predict)
unique_numbers = numpy.unique(convert_single_array)
# print(unique_numbers)
new_basename = os.path.basename(f).replace(".jpg", ".png")
new_name = os.path.join('output/', new_basename)
mask.save(new_name)
# color_img = image.imread(new_name)
# colors, counts = numpy.unique(color_img.reshape(-1, 3), return_counts=True, axis=0)
total_pixel = numpy.sum(predict)
d_file = drive.CreateFile({'parents': [{'id': file_id}], 'title': os.path.basename(new_name)})
d_file.SetContentFile(new_name)
d_file.Upload()
# print('Created file %s with mimeType %s' % (d_file['title'], d_file['mimeType']))
combile_all_csv_data = []
combine_sql_srting_format = []
for i in unique_numbers:
individual_count = numpy.sum(predict == i)
# print(individual_count)
csv_data = []
csv_data.append(os.path.basename(f))
csv_data.append(classes[i])
csv_data.append(total_pixel)
csv_data.append(individual_count)
csv_data.append(round((individual_count/total_pixel),6))
time_stamp = datetime.now()
csv_data.append(time_stamp)
# csv_data = [filename,predict,colors,counts,total_pixel]
# print(csv_data)
combile_all_csv_data.append(csv_data)
sql_srting = ["NULL" if val == None else "'"+str(val)+"'" for val in csv_data]
sql_srting_format = ",".join([str(val) for val in sql_srting])
combine_sql_srting_format.append(sql_srting_format)
csvwriter.writerows(combile_all_csv_data)
dbms.insertmany_sqlite3('semantic_results_atlanta',','.join(columns),combine_sql_srting_format)
os.remove(new_name)
# if idx % 10 == 0:
# print("Processed: ", idx)
except Exception as e:
print("Error in :", ' ' + f, e)
continue
print('Finished')
end = timer()
print('Processing time: %.1f' % (end - start))
def process_frame(self, frame, frame_count, frameWidth, frameHeight):
# cropped based on 240
frm = cv2.resize(frame, (224, 224))
img = mx.nd.array(frm, ctx=self.ctx)
img = test_transform(img, ctx=self.ctx)
# img = img.astype('float32')
output = self.model.predict(img)
#argx = mx.nd.argmax(output, 1)
argx = mx.nd.topk(output, 1)
#argx = np.argmax(output, axis=1)
# Wait to read actually waits for calculation
# argx.wait_to_read()
# or
# np.squeeze(argx).wait_to_read()
# tic = time.perf_counter()
# tic = time.time()
predict = np.squeeze(argx).asnumpy()
# toc = time.time()
# print("Proccesed in {}".format(toc-tic))
# predict = predict.astype(np.uint8)
# current = cv2.fastNlMeansDenoising(predict,None,10,7,21)
if (frame_count > 1):
predict = self.etha * predict + (1 - self.etha) * self.previous
# current = current.astype(np.uint8)
self.previous = copy.copy(predict)
ret, mask = cv2.threshold(predict.astype(float), .5, 255,
cv2.THRESH_BINARY)
if cv2.countNonZero(mask) > 0:
mask = cv2.resize(mask, (frameWidth, frameHeight))
# contourMask = self.get_rough_contour(mask)
im2, contours, h = cv2.findContours(mask.astype(np.uint8),
cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
if (len(contours) > 0):
contourMask = max(contours, key=cv2.contourArea)
# Centroid
M = cv2.moments(contourMask)
if M['m00'] != 0:
cx = int(M['m10'] / M['m00'])
cy = int(M['m01'] / M['m00'])
self.kalman.correct(
np.array([[np.float32(cx)], [np.float32(cy)]],
np.float32))
cent = self.kalman.predict()
if frame_count >= 25:
cx = np.int(cent[0][0])
cy = np.int(cent[1][0])
# Centroid
cv2.circle(frame, (cx, cy), 0, (0, 255, 255), 5)
# rectangle
rect = cv2.minAreaRect(contourMask)
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(frame, [box], 0, (255, 255, 255), 1)
# Line
# rows,cols = mask.shape[:2]
# [vx,vy,x,y] = cv2.fitLine(contourMask, cv2.DIST_L2,0,0.01,0.01)
# lefty = int((-x*vy/vx) + y)
# righty = int(((cols-x)*vy/vx)+y)
# img = cv2.line(frame,(cols-1,righty),(0,lefty),(255,255,255),1)
return frame, cx, cy
return frame, 0, 0