gabrielgarza

class InferenceConfig(config.__class__):
        # Run detection on one image at a time
        GPU_COUNT = 1
        IMAGES_PER_GPU = 1
        DETECTION_MIN_CONFIDENCE = 0.95
        DETECTION_NMS_THRESHOLD = 0.0
        IMAGE_MIN_DIM = 768
        IMAGE_MAX_DIM = 768
        RPN_ANCHOR_SCALES = (64, 96, 128, 256, 512)
        DETECTION_MAX_INSTANCES = 20

gabrielgarza

FROM nvidia/cuda:9.0-cudnn7-devel-ubuntu16.04
MAINTAINER Gabriel Garza <[email protected]>

# Essentials: developer tools, build tools, OpenBLAS
RUN apt-get update && apt-get install -y --no-install-recommends \
    apt-utils git curl vim unzip openssh-client wget \
    build-essential cmake \
    libopenblas-dev

#

gabrielgarza

def rle_decode(self, mask_rle, shape=(768, 768)):
    '''
    mask_rle: run-length as string formated (start length)
    shape: (height,width) of array to return
    Returns numpy array, 1 - mask, 0 - background

    '''
    if not isinstance(mask_rle, str):
        img = np.zeros(shape[0]*shape[1], dtype=np.uint8)
        return img.reshape(shape).T

gabrielgarza

train_ship_segmentations_df = pd.read_csv(os.path.join("./datasets/train_val/train_ship_segmentations.csv"))

msk = np.random.rand(len(train_ship_segmentations_df)) < 0.8

train = train_ship_segmentations_df[msk]
test = train_ship_segmentations_df[~msk]

#  Move train set
for index, row in train.iterrows():
    image_id = row["ImageId"]

gabrielgarza

def build_network(self):
        # Create placeholders
        with tf.name_scope('inputs'):
            self.X = tf.placeholder(tf.float32, shape=(self.n_x, None), name="X")
            self.Y = tf.placeholder(tf.float32, shape=(self.n_y, None), name="Y")
            self.discounted_episode_rewards_norm = tf.placeholder(tf.float32, [None, ], name="actions_value")
# Initialize parameters
        units_layer_1 = 10
        units_layer_2 = 10
        units_output_layer = self.n_y

gabrielgarza

import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import random

class Individual(object):

    def __init__(self, numbers=None, mutate_prob=0.01):
        if numbers is None:
            self.numbers = np.random.randint(101, size=10)

gabrielgarza

import gym
from gym import wrappers
import random
import numpy as np
import tensorflow as tf
import tflearn
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
from statistics import mean, median
from collections import Counter