def pre_screen(img, display_img):
"""
Performs inference and displays target image with result.
Args:
- img -> type:Image -> fastai wrapper for pixel image.
- display_img -> type:str -> location of static image being analyzed.
"""
with st.spinner('Wait for it...'):
time.sleep(3)
model = load_learner('models/', file="e-covidnet.pkl")
if torch.cuda.is_available():
model.model.load_state_dict(torch.load('models/e-covidnet.pth'))
else:
model.model.load_state_dict(
torch.load('models/e-covidnet.pth',
map_location=torch.device("cpu")))
pred_class = model.predict(img)[0]
pred_prob = round(torch.max(model.predict(img)[2]).item() * 100)
if str(pred_class) == 'COVID-19':
st.success("COVID-19 with the probability of " + str(pred_prob) + '%.')
st.image(display_img, width=300)
elif str(pred_class) == 'pneumonia':
result = st.success("Viral Pneumonia with the probability of " +
str(pred_prob) + '%.')
st.image(display_img, width=300)
elif str(pred_class) == 'normal':
st.success("Normal with the probability of " + str(pred_prob) + '%.')
st.image(display_img, width=300)
def predict(img):
with st.spinner('Please wait..'):
time.sleep(3)
model = load_learner('.')
pred_class,pred_idx,outputs = model.predict(img)
pred_prob = round(torch.max(model.predict(img)[2]).item()*100)
st.write('## This is ',str(pred_class).capitalize(),' with probablity of ',pred_prob,'%')
def predict(img, display_img):
# Display the test image
st.image(display_img, use_column_width=True)
# Temporarily displays a message while executing
with st.spinner('Using model 1...'):
time.sleep(3)
# Load model and make prediction
model = load_learner('models/', 'export.pkl')
pred_class = model.predict(img)[0] # get the predicted class
pred_prob = round(torch.max(model.predict(img)[2]).item() *
100) # get the max probability
# Display the prediction
if str(pred_class) == '0-4':
st.success("You are 0-4 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '5-9':
st.success("You are 5-9 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '10-14':
st.success("You are 10-14 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '15-19':
st.success("You are 15-19 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '20-24':
st.success("You are 20-24 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '25-29':
st.success("You are 25-29 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '30-34':
st.success("You are 30-34 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '35-39':
st.success("You are 35-39 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '40-44':
st.success("You are 40-44 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '45-49':
st.success("You are 45-49 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '50-54':
st.success("You are 50-54 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '55-59':
st.success("You are 55-59 with the probability of " + str(pred_prob) +
'%.')
elif str(pred_class) == '60-64':
st.success("You are 60-64 with the probability of " + str(pred_prob) +
'%.')
else:
st.success("You are 65+ with the probability of " + str(pred_prob) +
'%.')
def predict(img, display_img):
st.image(display_img, use_column_width=True)
with st.spinner('Wait for it...'):
time.sleep(5)
model = load_learner('model/images/')
pred_class = model.predict(img)[0]
pred_prob = (torch.max(model.predict(img)[2]).item() * 100)
if str(pred_class) == 'poorichole':
st.success("This is Poori Chole. Probability -> " + str(pred_prob) +
'%.')
else:
st.success("This is Samosa. Probability -> " + str(pred_prob) + '%.')
def predict(img, display_img):
# Display the test image
st.image(display_img, use_column_width=True)
# Temporarily displays a message while executing
with st.spinner('Wait for it...'):
time.sleep(3)
# Load model and make prediction
model = load_learner('model/data/train/')
pred_class = model.predict(img)[0]
pred_prob = round(torch.max(model.predict(img)[2]).item() * 100)
# Display the prediction
if str(pred_class) == 'mtp':
st.success("This is Son Tung M-TP with the probability of " +
str(pred_prob) + '%.')
else:
st.success("This is G-Dragon with the probability of " +
str(pred_prob) + '%.')
def get_prediction(image_tensor):
hasil = model.predict(image_tensor)
return str(hasil[0]), torch.max(hasil[2]).item() * 100
def predict(img, display_img):
# display test image
st.image(display_img, use_column_width=True)
# temporary message
with st.spinner('Thinking...'):
time.sleep(3)
# load trained model
model = load_learner('models/', 'WatchProj_classifier.pkl')
# prediction
pred_class = model.predict(img)[0]
# confidence percentage
pred_prob = round(torch.max(model.predict(img)[2]).item() * 100)
if str(pred_class) == 'rolex':
st.success("I am " + str(pred_prob) + '%'
" confident this is a Rolex.")
if str(pred_class) == 'audemarspiguet':
st.success("I am " + str(pred_prob) + '%'
" confident this is an Audemars Piguet.")
if str(pred_class) == 'breitling':
st.success("I am " + str(pred_prob) + '%'
" confident this is an Breitling.")
if str(pred_class) == 'iwc':
st.success("I am " + str(pred_prob) + '%' " confident this is an IWC.")
if str(pred_class) == 'jaegerlecoultre':
st.success("I am " + str(pred_prob) + '%'
" confident this is a Jaegerlecoultre.")
if str(pred_class) == 'omega':
st.success("I am " + str(pred_prob) + '%'
" confident this is an Omega.")
if str(pred_class) == 'panerai':
st.success("I am " + str(pred_prob) + '%'
" confident this is a Panerai.")
if str(pred_class) == 'patekphilippe':
st.success("I am " + str(pred_prob) + '%'
" confident this is a Patek Philippe.")
if str(pred_class) == 'cartier':
st.success("I am " + str(pred_prob) + '%'
" confident this is a Cartier.")
if str(pred_class) == 'gucci':
st.success("I am " + str(pred_prob) + '%'
" confident this is a Gucci.")
if str(pred_class) == 'seiko':
st.success("I am " + str(pred_prob) + '%'
" confident this is a Seiko.")
if str(pred_class) == 'movado':
st.success("I am " + str(pred_prob) + '%'
" confident this is a Movado.")
if str(pred_class) == 'zenith':
st.success("I am " + str(pred_prob) + '%'
" confident this is an Zenith.")
from utils import get_databunch
from make_vgg_resnet import VGG_ResNet
if __name__ == "__main__":
datasetdir = os.path.join(os.path.dirname(__file__), './kuzu_mnist')
datasetdir = os.path.abspath(datasetdir)
# Load dataset
databunch = get_databunch(datasetdir)
# Create VGG + ResNet model
learn = Learner(databunch, VGG_ResNet(), metrics=accuracy)
# Load
learn.load('vgg_resnet_model_with_norm')
# Validate
loss, acc = learn.validate()
print('val_loss: {}, val_acc: {}'.format(loss, acc))
mat = np.zeros((10, 10))
for data in databunch.valid_ds:
images, labels = data
images = images.reshape((1, 1, 28, 28))
outputs = learn.model(images)
_, predicted = torch.max(outputs, 1)
predicted = int(predicted)
mat[labels][predicted] += 1
print(mat)