hgaiser

train_net: "models/apc/ResNet18/faster_rcnn_end2end/train.prototxt"
base_lr: 0.1
lr_policy: "step"
gamma: 0.1
stepsize: 50000
display: 20
average_loss: 100
# iter_size: 1
momentum: 0.9
weight_decay: 0.0005

hgaiser

name: "ResNet50"
layer {
	name: 'input-data'
	type: 'Python'
	top: 'data'
	top: 'im_info'
	top: 'gt_boxes'
	top: 'gt_masks'
	top: 'mask_info'
	python_param {

hgaiser

name: "ResNet50"
layer {
	name: 'input-data'
	type: 'Python'
	top: 'data'
	top: 'im_info'
	top: 'gt_boxes'
	top: 'gt_masks'
	top: 'mask_info'
	python_param {

hgaiser

name: "ResNet50"

input: "data"
input_shape {
	dim: 1
	dim: 3
	dim: 224
	dim: 224
}

hgaiser

name: "SimpleTriNet"

layer {
	name: "data"
	type: "Module"
	top: "anchor"
	top: "negative"
	top: "positive"
	module_param {
		module: "triplet_layers"

hgaiser

name: "fkp_net"
layers {
  name: "data"
  type: MEMORY_DATA
  top: "data"
  top: "label"
  memory_data_param {
    batch_size: 1783 #batch size, so how many prediction youu want to do at once. Best is "1", but higher number get better performance
    channels: 1
    height: 96

hgaiser

def get_session():
	config = tf.ConfigProto()
	config.gpu_options.allow_growth = True
	return tf.Session(config=config)

keras.backend.tensorflow_backend.set_session(get_session())

hgaiser

#!/usr/bin/env python

import tensorflow as tf

from tensorflow.contrib.keras.api import keras
from tensorflow.contrib.keras.api.keras.models import Model, load_model
from tensorflow.contrib.keras.api.keras.layers import Input, Dense, Dropout, Flatten, Conv2D, MaxPooling2D, Activation, Lambda
from tensorflow.contrib.keras.api.keras.datasets import mnist
from tensorflow.contrib.keras.api.keras.utils import to_categorical

hgaiser

hgaiser