Recherche avancée

Sur d’autres sites (15699)

• WARN : Tried to pass invalid video frame, marking as broken : Your frame has data type int64, but we require uint8

  5 septembre 2019, par Tavo Diaz

  I am doing some Udemy AI courses and came across with one that "teaches" a bidimensional cheetah how to walk. I was doing the exercises on my computer, but it takes too much time. I decided to use Google Cloud to run the code and see the results some hours after. Nevertheless, when I run the code I get the following error " WARN : Tried to pass
  invalid video frame, marking as broken : Your frame has data type int64, but we require uint8 (i.e. RGB values from 0-255)".

  After the code is executed, I see into the folder and I don’t see any videos (just the meta info).

  Some more info (if it helps) :
  I have a 1 CPU (4g), SSD Ubuntu 16.04 LTS

  I have not tried anything yet to solve it because I don´t know what to try. Im looking for solutions on the web, but nothing I could try.

  This is the code

  import os 
  
  import numpy as np
  
  import gym
  
  from gym import wrappers
  
  import pybullet_envs
  
  
  
  
  
  class Hp():
  
      def __init__(self):
  
          self.nb_steps = 1000
  
          self.episode_lenght =   1000
  
          self.learning_rate = 0.02
  
          self.nb_directions = 32
  
          self.nb_best_directions = 32
  
          assert self.nb_best_directions <= self.nb_directions
  
          self.noise = 0.03
  
          self.seed = 1
  
          self.env_name = 'HalfCheetahBulletEnv-v0'
  
  
  
  
  
  class Normalizer():
  
      def __init__(self, nb_inputs):
  
          self.n = np.zeros(nb_inputs)
  
          self.mean = np.zeros(nb_inputs)
  
          self.mean_diff = np.zeros(nb_inputs)
  
          self.var = np.zeros(nb_inputs)
  
  
  
      def observe(self, x):
  
          self.n += 1.
  
          last_mean = self.mean.copy()
  
          self.mean += (x - self.mean) / self.n
  
          #abajo es el online numerator update
  
          self.mean_diff += (x - last_mean) * (x - self.mean)
  
          #abajo online computation de la varianza
  
          self.var = (self.mean_diff / self.n).clip(min = 1e-2)  
  
  
  
      def normalize(self, inputs):
  
          obs_mean = self.mean
  
          obs_std = np.sqrt(self.var)
  
          return (inputs - obs_mean) / obs_std
  
  
  
  class Policy():
  
      def __init__(self, input_size, output_size):
  
          self.theta = np.zeros((output_size, input_size))
  
  
  
      def evaluate(self, input, delta = None, direction = None):
  
          if direction is None:
  
              return self.theta.dot(input)
  
          elif direction == 'positive':
  
              return (self.theta + hp.noise * delta).dot(input)
  
          else:
  
              return (self.theta - hp.noise * delta).dot(input)
  
  
  
      def sample_deltas(self):
  
          return [np.random.randn(*self.theta.shape) for _ in range(hp.nb_directions)]
  
  
  
      def update (self, rollouts, sigma_r):
  
          step = np.zeros(self.theta.shape)
  
          for r_pos, r_neg, d in rollouts:
  
              step += (r_pos - r_neg) * d
  
          self.theta += hp.learning_rate / (hp.nb_best_directions * sigma_r) * step
  
  
  
  
  
  def explore(env, normalizer, policy, direction = None, delta = None):
  
      state = env.reset()
  
      done = False
  
      num_plays = 0.
  
      #abajo puede ser promedio de las rewards
  
      sum_rewards = 0
  
      while not done and num_plays < hp.episode_lenght:
  
          normalizer.observe(state)
  
          state = normalizer.normalize(state)
  
          action = policy.evaluate(state, delta, direction)
  
          state, reward, done, _ = env.step(action)
  
          reward = max(min(reward, 1), -1)
  
          #abajo sería poner un promedio
  
          sum_rewards += reward
  
          num_plays += 1
  
      return sum_rewards
  
  
  
  def train (env, policy, normalizer, hp):
  
      for step in range(hp.nb_steps):
  
          #iniciar las perturbaciones deltas y los rewards positivos/negativos
  
          deltas = policy.sample_deltas()
  
          positive_rewards = [0] * hp.nb_directions
  
          negative_rewards = [0] * hp.nb_directions
  
          #sacar las rewards en la dirección positiva
  
          for k in range(hp.nb_directions):
  
              positive_rewards[k] = explore(env, normalizer, policy, direction = 'positive', delta = deltas[k])
  
          #sacar las rewards en dirección negativo
  
          for k in range(hp.nb_directions):
  
              negative_rewards[k] = explore(env, normalizer, policy, direction = 'negative', delta = deltas[k])
  
          #sacar todas las rewards para sacar la desvest
  
          all_rewards = np.array(positive_rewards + negative_rewards)
  
          sigma_r = all_rewards.std()
  
          #acomodar los rollauts por el max (r_pos, r_neg) y seleccionar la mejor dirección
  
          scores = {k:max(r_pos, r_neg) for k, (r_pos, r_neg) in enumerate(zip(positive_rewards, negative_rewards))}
  
          order = sorted(scores.keys(), key = lambda x:scores[x])[:hp.nb_best_directions]
  
          rollouts = [(positive_rewards[k], negative_rewards[k], deltas[k]) for k in order]
  
          #actualizar policy
  
          policy.update (rollouts, sigma_r)
  
          #poner el final reward del policy luego del update
  
          reward_evaluation = explore (env, normalizer, policy)
  
          print('Paso: ', step, 'Lejania: ', reward_evaluation)
  
  
  
  def mkdir(base, name):
  
      path = os.path.join(base, name)
  
      if not os.path.exists(path):
  
          os.makedirs(path)
  
      return path
  
  work_dir = mkdir('exp', 'brs')
  
  monitor_dir = mkdir(work_dir, 'monitor')
  
  
  
  hp = Hp()
  
  np.random.seed(hp.seed)
  
  env = gym.make(hp.env_name)
  
  env = wrappers.Monitor(env, monitor_dir, force = True)
  
  nb_inputs = env.observation_space.shape[0]
  
  nb_outputs = env.action_space.shape[0]
  
  policy = Policy(nb_inputs, nb_outputs)
  
  normalizer = Normalizer(nb_inputs)
  
  train(env, policy, normalizer, hp)

• Unable to play RTSP URL with ffplay but able to play it with VLC

  15 février 2018, par Dims

  I am trying to see my IP camera with VLC and see it with VLC with address

  rtsp://192.168.1.168

  Unfortunately, when I enter the same address into ffplay

  ffplay rtsp://192.168.1.168

  I get multiple errors like

  UDP timeout, retrying with TCP 0B f=0/0
  
  method PAUSE failed: 455 Method Not Valid In This State

  why and how to overcome ?

• x86 : checkasm : check for or handle missing cleanup after MMX instructions

  11 décembre 2015, par Janne Grunau

  x86 : checkasm : check for or handle missing cleanup after MMX instructions
  Not every asm routine is expected clear the MMX state after returning.
  
  It is however a requisite for testing floating point code in checkasm.
  
  Annotate functions requiring cleanup with declare_func_emms() and issue
  
  emms after the call. The remaining functions are checked for having  a
  
  cleared MMX state after return.
  

  • [DBH] tests/checkasm/checkasm.h
  • [DBH] tests/checkasm/h264pred.c
  • [DBH] tests/checkasm/h264qpel.c
  • [DBH] tests/checkasm/x86/checkasm.asm