zhreshold

# use ImageMagick convert
# the order is important. the density argument applies to input.pdf and resize and rotate to output.pdf
convert -density 90 input.pdf -rotate 0.5 -attenuate 0.2 +noise Multiplicative -colorspace Gray output.pdf

zhreshold

Platform	Download link
Linux(cpu, openblas)1
Linux(gpu, cuda9.0)13
Linux(gpu, cuda9.2)13
Windows x64(cpu, openblas)
Windows x64(gpu, cuda9.2)3
Mac OS(cpu, appleblas)2	x

1: use LD_LIBRARY_PATH=$LD_LIBRARY_PATH:. gluoncv-detect in case you are using the supplied shared libraries under the same directory. You can add export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/path/to/prebuilt-package to ~/.bashrc to permanently add library into search path.

zhreshold

How to finetune detection models in GluonCV

How to modify pre-trained network from VOC/COCO to custom classes

# python3 train_ssd.py --finetune ssd_300_vgg16_atrous_coco --dataset customxx
import gluoncv as gcv
# download pretrained from coco
net = gcv.model_zoo.get_model('ssd_300_vgg16_atrous_coco', pretrained=True)
# modify network to fit the new classes, say ['a', 'b', 'c']

zhreshold

import argparse
import os
import time
import mxnet as mx
import gluoncv as gcv
from gluoncv.data.transforms import presets

def parse_args():
    parser = argparse.ArgumentParser(description='Benchmark GluonCV SSD networks.')
    parser.add_argument('--network', type=str, default='ssd_300_vgg16_atrous_voc',

zhreshold

class Darknet(gluon.HybridBlock):
  def __init__(self, spec, classes=1000, batch_norm=True, **kwargs):
    super(Darknet, self).__init__(**kwargs)
    filters = spec['filters']
    kernels = spec['kernels']
    with self.name_scope():
      self.features = nn.HybridSequential()
      first_stage = True
      for sf, sk in zip(filters, kernels):
        if not first_stage:

zhreshold

import mxnet as mx
from mxnet import nd

data = mx.nd.array([1,2,3], ctx=mx.Context('cpu_shared', 0))

pid, fd, shape, dtype = data._to_shared_mem()

new_data = mx.nd.NDArray(nd.ndarray._new_from_shared_mem(pid, fd, shape, dtype))

print(new_data)

zhreshold

from gluoncv.data import imagenet
from mxnet.gluon.data.vision import transforms
from mxnet import gluon
import mxnet as mx
import time
import logging
logging.basicConfig(level=logging.DEBUG)

batch_size = 128
num_workers = 2

zhreshold

name: "ResNet-18"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 224
input_dim: 224

layer {
	bottom: "data"
	top: "conv1"

zhreshold

name: "Parallel18_6x_CIFAR10"
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param {
    shape {
      dim: 1
      dim: 3
      dim: 32

zhreshold

mkdir -p n01440764	
mkdir -p n01443537	
mkdir -p n01484850	
mkdir -p n01491361	
mkdir -p n01494475	
mkdir -p n01496331	
mkdir -p n01498041	
mkdir -p n01514668	
mkdir -p n01514859	
mkdir -p n01518878