mjamroz

taskname: '+ MobileViTv2-2.0 plant'
common:
  enable_coreml_compatible_module: true
  results_loc: "conv"
  run_label: "finetune_mobilevit_plants"
  mixed_precision: true
  conversion:
    input_image_path: "/home/nme/WORK/plants_and_shrooms/plants_images/6541/a177a8d425913fac10075c76bc8332a0ad83d04eDsc_0063.jpg"
dataset:
  category: "classification"

mjamroz

import functools
import inspect


def run_job_in_background(func, args, kwargs):
    print(f"RUN {func} background")
    func()


def background(func=None, *, commit=False):

mjamroz

tags = [
        {"p": 1, "fav":False},
        {"p": 2, "fav":False},
        {"p": 5, "fav":False},
        {"p": 5.5, "fav":True},
        {"p": 5.6, "fav":True},
        {"p": 6, "fav":False},
        ]

# after changing position in frontend, we applying this function to update tags positions in db:

mjamroz

[[source]]
url = "https://pypi.org/simple"
verify_ssl = true
name = "pypi"

[packages]
tensorflow = "==1.15.0"
mxnet-mkl  = "==1.6.0"
numpy      = "==1.18.2"
tensorflowjs = "==1.7.2"

mjamroz

from mxnet import metric, nd


class BinarySelectedStatistics(metric._BinaryClassificationMetrics):
    def __init__(self):
        super().__init__()
        self.positive = 1 # default
        self.num_inst = 0
        self.sum_metric = 0.0

mjamroz

import mxnet as mx
import argparse, os
from matplotlib import pyplot as plt
from gluoncv.model_zoo import get_model
#mx.random.seed(42)
# CLI
def parse_args():
    parser = argparse.ArgumentParser(description='Train a model for image classification.')
    parser.add_argument('--classes', type=str, default=1000,
                        help='number of classes')

mjamroz

#!/usr/bin/env python3
from mxnet.gluon import data, SymbolBlock, utils
from gluoncv.model_zoo import get_model
from mxnet import nd, cpu, gpu, io, metric
from multiprocessing import cpu_count
import argparse

classes = ['Cl1', 'lass2', 'ass3', 'ss4']

parser = argparse.ArgumentParser(description='Batch prediction')

mjamroz

import argparse, time, logging, os,math

import numpy as np
import mxnet as mx
import gluoncv as gcv
from mxnet import gluon, nd
from mxnet import autograd as ag
from mxnet.gluon import nn
from mxnet.gluon.data.vision import transforms

mjamroz

from mxnet.gluon import nn
from gluoncv.model_zoo import get_model
from mxnet import image, cpu, init
from gluoncv.data.transforms.presets.imagenet import transform_eval

context = [cpu()]

net = get_model("network_prefix", ctx=context, pretrained=True)
with net.name_scope():
    net.output = nn.Dense(4)

mjamroz

davs://[email protected]/webdav/someFolder