def main():
#if len(sys.argv) < 2:
# print("usage: python %prog <torrent> [options]")
# return
opts = optparse.OptionParser(\
usage = "usage: python console.py <torrent> [options]")
opts.add_option('-s', '--store', action = 'store_true', \
dest = 'store', help = 'files are written to disk')
opts.add_option('-p', '--path', default = 'downloads', dest = 'path',\
metavar = 'DIR', help = 'in which dir to store/retrieve the files')
opts.add_option('-a', '--accept', action = 'store_true', \
dest = 'accept', help = 'starts listening for incoming connections')
options, args = opts.parse_args()
if len(args) != 1:
opts.error('incorrect number of arguments')
peer_id = b'a0b1c2d3e4f5g6h7i8j9'
env = environment.initialize(args[0], peer_id, \
options.store, options.path)
console = code.InteractiveConsole(env)
console.interact(
"Python interactive console %s.\nBitTorrent chat client using bitless."
% sys.version)
environment.shutdown()
print("Finished...")
def main():
#if len(sys.argv) < 2:
# print("usage: python %prog <torrent> [options]")
# return
opts = optparse.OptionParser(\
usage = "usage: python console.py <torrent> [options]")
opts.add_option('-s', '--store', action = 'store_true', \
dest = 'store', help = 'files are written to disk')
opts.add_option('-p', '--path', default = 'downloads', dest = 'path',\
metavar = 'DIR', help = 'in which dir to store/retrieve the files')
opts.add_option('-a', '--accept', action = 'store_true', \
dest = 'accept', help = 'starts listening for incoming connections')
options, args = opts.parse_args()
if len(args) != 1:
opts.error('incorrect number of arguments')
peer_id = b'a0b1c2d3e4f5g6h7i8j9'
env = environment.initialize(args[0], peer_id, \
options.store, options.path)
console = code.InteractiveConsole(env)
console.interact("Python interactive console %s.\nBitTorrent chat client using bitless." % sys.version)
environment.shutdown()
print("Finished...")
//= Sola丶小克 //===== Current Version: ===================================== //= 1.0 //===== Description: ========================================= //= 此脚本用于编译复兴前和复兴后 Release 版本的 Pandas 模拟器 //= 符号文件的储存和上传工作, 将由其他脚本来实现 //===== Additional Comments: ================================= //= 1.0 首个版本. [Sola丶小克] //============================================================ ''' # -*- coding: utf-8 -*- import environment environment.initialize() import os import platform import re import shutil import time import winreg import git from dotenv import load_dotenv from libs import Common, Inputer, Message # 切换工作目录为脚本所在目录 os.chdir(os.path.split(os.path.realpath(__file__))[0])
def cxr_predict(hmp_dims=None,
dcm_file=None,
cuda='0',
fl_gradcam=True,
Nens=3,
th_gradcam=0.7,
input_type='dicom'):
print(
"\n-------------------------------------------------------------------"
)
print(
"| |")
print(
"| |")
print(
"| v1.0 MGH Age, View, Gender, Vendor, Abnormal Detection |")
print(
"| (Copyright (c) 2021-2022, MGH LMIC. All rights reserved.) |")
print(
"| |")
print(
"| |")
print(
"-------------------------------------------------------------------\n"
)
param_cuda = cuda
param_labels = [
'ap', 'pa', 'female', 'male', 'varian', 'agfa', 'ge',
'Foreign body>.>.', 'Hilar/mediastinum>Cardiomegaly>.',
'Lung density>Increased lung density>Atelectasis',
'Lung density>Increased lung density>Pulmonary edema',
'Lung density>Increased lung density>pneumonia',
'Pleura>Pleural effusion>.', 'abnormal', 'PatientAge'
]
param_path = None
param_runDir = ''
param_type = 0
param_preModel = 'multitask_model'
param_gradcam = fl_gradcam
param_arch = None
param_task = 2
param_clsGcam = param_labels[-8:-2]
param_Nens = Nens
fl_ensemble = False if param_Nens == 1 else True
runtime_path, device = initialize(param_runDir, param_cuda)
# image preprocessing
d = DcmToPng(
param_labels,
dcm_path=runtime_path.joinpath('input_dir/DICOM').resolve(),
png_path=runtime_path.joinpath('input_dir/IMAGEFILE').resolve(),
ds=dcm_file,
localOp=True,
input_type=input_type)
#d = DcmToPng(param_labels, dcm_path=runtime_path.joinpath('dicoms').resolve(), png_path=runtime_path.joinpath('pngs').resolve(), ds=dcm_file)
if input_type == 'dicom':
d.dcm2png()
# start network inference
env = DemoEnvironment(device,
runtime_path,
mtype=param_type,
name_labels=param_labels,
name_paths=param_path,
name_model=param_arch,
task_type=param_task)
t = Demo(env,
pt_runtime=runtime_path,
fn_net=param_preModel,
fl_gradcam=param_gradcam,
cls_gradcam=param_clsGcam,
th_gradcam=th_gradcam,
fl_ensemble=fl_ensemble)
if (fl_ensemble):
result = t.demo_cxr_ensemble_evaluation(hmp_dims=hmp_dims,
n_ens=param_Nens)
else:
result = t.demo_cxr_evaluation(hmp_dims=hmp_dims)
df_prob = pd.DataFrame(result['prob'], columns=print_label_name)
df_pred = pd.DataFrame(result['pred'], columns=print_label_name)
df_file = pd.read_csv(
runtime_path.joinpath('input_dir/IMAGEFILE/images.csv'))
df_prob['file'] = df_file['PATH']
df_pred['file'] = df_file['PATH']
runtime_path.joinpath('output_dir/Classification').mkdir(parents=True,
exist_ok=True)
df_prob.to_csv(
runtime_path.joinpath('output_dir/Classification/probability.txt'),
header=True,
index=True,
sep=',',
mode='w')
df_pred.to_csv(
runtime_path.joinpath('output_dir/Classification/prediction.txt'),
header=True,
index=True,
sep=',',
mode='w')
#print(result)
return result