def compare_callback(exe, benchmark, elapsed):
for report_name in args.compare_to:
v = model.get_result(report_name, benchmark)
if v is None:
print "(no %s)" % report_name,
else:
print "%s: %.2f (%+0.1f%%)" % (report_name, v, (elapsed - v) / v * 100),
def compare_callback(exe, benchmark, elapsed, size):
for report_name in args.compare_to:
v = model.get_result(report_name, benchmark)
if v is None:
print "(no %s)" % report_name,
else:
print "%s: %.2fs (%s%%)" % (
report_name, v[0], "{:5.1f}".format(
(elapsed - v[0]) / v[0] * 100)),
def predict():
# whenever the predict method is called, we're going
# to input the user drawn character as an image into the model
# perform inference, and return the classification
# get the raw data format of the image
imgData = request.get_data()
convertImage(imgData)
keras.backend.clear_session()
my_model = mod.get_mnist_model()
res = mod.get_result('output.png', my_model)
print(np.round(res*100,2)) # probabilites of all other digits
return str(np.argmax(res))
def create_widget(self):
self.target_mlb = MultiListbox(self, (('mRNAname', 20),('score',20)), height=25)
self.function_mlb = MultiListbox(self, (('target family', 20),('function',20)), height=25)
self.RNA_in_input = SearchInput(self, text='输入microRNA名字:',
textvariable=self.search_string,
button_function=lambda:get_result(self.search_string, self.target_select_value, self.target_mlb, self.function_mlb))
self.split_frame = Frame(self, height=1, width=680, bg='black')
self.split_frame_2 = Frame(self, height=1, width=680, bg='black')
self.query_target_label = Label(self, text='查询target')
self.query_function_label = Label(self, text='查询功能')
self.target_select_radiobutton = []
self.target_select_radiobutton.append(Radiobutton(self,
variable = self.target_select_value,
value = 'targetscan', text = 'targetscan'))
self.target_select_radiobutton.append(Radiobutton(self,
variable = self.target_select_value,
value = 'miRanda', text = 'miRanda'))
self.target_select_radiobutton.append(Radiobutton(self,
variable = self.target_select_value,
value = 'picTar', text = 'picTar'))
for radiobutton in self.target_select_radiobutton:
radiobutton['width'] = 6
def repeated_filter(exe, benchmark):
v = model.get_result(skip_report_name(exe), benchmark)
if v:
return v
return False
def save_report_callback(exe, benchmark, elapsed, size):
old_val = model.get_result(args.save_report, benchmark)
model.save_result(args.save_report, benchmark, elapsed, size)
if old_val is not None and args.take_min:
print "(prev min: %.2fs / %2.1fMB)" % (old_val[0], old_val[1]),
def view_filter(exe, benchmark):
v = model.get_result(args.view, benchmark)
if v is not None:
return v
return True
def repeated_filter(exe, benchmark):
v = model.get_result(skip_report_name(exe), benchmark)
if v:
return v
return False
def save_report_callback(exe, benchmark, elapsed):
old_val = model.get_result(args.save_report, benchmark)
model.save_result(args.save_report, benchmark, elapsed)
if old_val is not None and args.take_min:
print "(prev min: %.2fs)" % (old_val,),
def view_filter(exe, benchmark):
v = model.get_result(args.view, benchmark)
if v is not None:
return v
return True
import os
from utils import getFiles, plot_confusion_matrix
from model import HMM_Model, get_result, train, load_models, evaluate
from dataloader import Dataloader, single_loader
import numpy as np
genre_list = [
'blues', 'classical', 'jazz', 'country', 'pop', 'rock', 'metal', 'disco',
'hiphop', 'reggae'
]
# dl = Dataloader(genre_list, root='genres')
# train(dl)
models = load_models(genre_list)
# Evaluate method 1:
cm, real, pred = evaluate('genres_small', genre_list, models)
plot_confusion_matrix(cm, genre_list, True) # get plot
print(classification_report(real, pred, target_names=genre_list)) # get report
# Evaluate method 2:
fl = getFiles('genres_small')
for f in fl:
X = single_loader(f, is_print_info=False, is_vision=False)
print('Truth:{}, predict:{}'.format(f, get_result(X, models)))
# Single test:
X = single_loader('blues.00000.wav')
result = get_result(X, models)
print(result)
