chadrick-kwag

import os, torch, datetime, gym
from torch.utils.tensorboard import SummaryWriter




class Actor(torch.nn.Module):

    def __init__(self, state_size, action_size):

chadrick-kwag

import gym, torch, datetime, os
from torch.utils.tensorboard import SummaryWriter
env = gym.make('CartPole-v1')



class Actor(torch.nn.Module):

    def __init__(self, state_size, action_size):

chadrick-kwag

acc_summary = sess.run(acc_summary_op, feed_dict={lazy_acc_score_ph: acc_score})
writer.add_summary(acc_summary, global_step = step)

chadrick-kwag

lazy_acc_score_ph = tf.placeholder(tf.float32, [1])
lazy_acc_score_ts = tf.reduce_sum(lazy_acc_score_ph)

#...

# summary op for recording externally calculated metric(acc_score)
acc_summary_op = tf.summary.scalar("metric/acc", lazy_acc_score_ts)

chadrick-kwag

# calculate accuracy outside of the computational graph

pred_argmax = np.argmax(prediction, axis=1)
label_argmax = np.argmax(test_label, axis=1)

acc_score = accuracy_score(label_argmax, pred_argmax)
acc_score = np.reshape(acc_score,(1,))

chadrick-kwag

for step in range(steps):

    train_summary, loss_val, prediction, _ = sess.run([train_summary_op, loss_ts, prediction_ts, optimizer_op],
                                                        feed_dict={input_ph: train_input, onehot_labels_ph: train_label})
    writer.add_summary(train_summary, global_step = step)
    print("train done for step={}".format(step))

    if step!=0 and step%5==0:
        test_summary = sess.run(test_summary_op, feed_dict={input_ph: test_input, onehot_labels_ph: test_label})
        writer.add_summary(test_summary, global_step = step)

chadrick-kwag

# in training, we want to log loss value, accuracy value
loss_summary = tf.summary.scalar("loss/loss", loss_ts)
train_accuracy_summary = tf.summary.scalar("metric/acc", accuracy_ts)

# will detect loss_summary and train_accuracy_summary
train_summary_op = tf.summary.merge_all()

test_accuracy_summary = tf.summary.scalar("test/acc", accuracy_ts)
test_summary_op = tf.summary.merge([test_accuracy_summary])

chadrick-kwag

import numpy as np
from sklearn.metrics import accuracy_score
import tensorflow as tf
import tensorflow.contrib.slim.nets as nets

# tf version: 1.10.0


def get_random_input_and_label(batch_size, class_size):

chadrick-kwag

import numpy as np
import tensorflow as tf
import tensorflow.contrib.slim.nets as nets

# tf version: 1.10.0


def get_random_input_and_label(batch_size, class_size):

    # for demonstration purpose, I'm going to reuse a random input and label

chadrick-kwag

def calc_prf_single(gt_box_list, pred_box_list):
    """
    prf: precision/recall/f1-score

    when matching, I did not consider conf value at the moment. This policy may change.
    """
    
    gt_assign_map={}

    # for gt_box in gt_box_list: