Python facenet.FLIP屬性代碼示例

# 需要導入模塊: import facenet [as 別名]
# 或者: from facenet import FLIP [as 別名]
def feature_encode(sess, image_paths, batch_size):

    # Run forward pass to calculate embeddings
    #print('Runnning forward pass on LFW images')

    use_flipped_images = False
    use_fixed_image_standardization = False
    use_random_rotate = False
    use_radnom_crop = False
    # Enqueue one epoch of image paths and labels
    nrof_embeddings = len(image_paths)  # nrof_pairs * nrof_images_per_pair
    nrof_flips = 2 if use_flipped_images else 1
    nrof_images = nrof_embeddings * nrof_flips
    labels_array = np.expand_dims(np.arange(0,nrof_images),1)
    image_paths_array = np.expand_dims(np.repeat(np.array(image_paths),nrof_flips),1)
    control_array = np.zeros_like(labels_array, np.int32)

    if use_fixed_image_standardization:
        control_array += np.ones_like(labels_array)*facenet.FIXED_STANDARDIZATION
    if use_flipped_images:
        # Flip every second image
        control_array += (labels_array % 2)*facenet.FLIP
    if use_random_rotate:
        control_array += facenet.RANDOM_ROTATE
    if use_radnom_crop:
        control_array += facenet.RANDOM_CROP

    sess.run(eval_enqueue_op, {image_paths_placeholder: image_paths_array, 
                      labels_placeholder: labels_array, control_placeholder: control_array})

    embedding_size = int(embeddings.get_shape()[1])
    assert nrof_images % batch_size == 0, 'The number of LFW images must be an integer multiple of the LFW batch size'
    nrof_batches = nrof_images // batch_size
    emb_array = np.zeros((nrof_images, embedding_size))
    lab_array = np.zeros((nrof_images,))
    for i in range(nrof_batches):
        feed_dict = {phase_train_placeholder:False, batch_size_placeholder:batch_size}
        emb, lab = sess.run([embeddings, label_batch], feed_dict=feed_dict)
        lab_array[lab] = lab
        emb_array[lab, :] = emb
        if i % 10 == 9:
            print('.', end='')
            sys.stdout.flush()
    #import pdb; pdb.set_trace()
    #np.savetxt("emb_array.csv", emb_array, delimiter=",")
    return emb_array 

# 需要導入模塊: import facenet [as 別名]
# 或者: from facenet import FLIP [as 別名]
def feature_encode(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, 
                   batch_size_placeholder, control_placeholder, embeddings, labels, image_paths, 
                   batch_size, distance_metric):

    # Run forward pass to calculate embeddings
    #print('Runnning forward pass on LFW images')

    use_flipped_images = False
    use_fixed_image_standardization = False
    use_random_rotate = False
    use_radnom_crop = False
    # Enqueue one epoch of image paths and labels
    nrof_embeddings = len(image_paths)  # nrof_pairs * nrof_images_per_pair
    nrof_flips = 2 if use_flipped_images else 1
    nrof_images = nrof_embeddings * nrof_flips
    labels_array = np.expand_dims(np.arange(0,nrof_images),1)
    image_paths_array = np.expand_dims(np.repeat(np.array(image_paths),nrof_flips),1)
    control_array = np.zeros_like(labels_array, np.int32)

    if use_fixed_image_standardization:
        control_array += np.ones_like(labels_array)*facenet.FIXED_STANDARDIZATION
    if use_flipped_images:
        # Flip every second image
        control_array += (labels_array % 2)*facenet.FLIP
    if use_random_rotate:
        control_array += facenet.RANDOM_ROTATE
    if use_radnom_crop:
        control_array += facenet.RANDOM_CROP

    sess.run(enqueue_op, {image_paths_placeholder: image_paths_array, 
                      labels_placeholder: labels_array, control_placeholder: control_array})

    embedding_size = int(embeddings.get_shape()[1])
    assert nrof_images % batch_size == 0, 'The number of LFW images must be an integer multiple of the LFW batch size'
    nrof_batches = nrof_images // batch_size
    emb_array = np.zeros((nrof_images, embedding_size))
    lab_array = np.zeros((nrof_images,))
    for i in range(nrof_batches):
        feed_dict = {phase_train_placeholder:False, batch_size_placeholder:batch_size}
        emb, lab = sess.run([embeddings, labels], feed_dict=feed_dict)
        lab_array[lab] = lab
        emb_array[lab, :] = emb
        if i % 10 == 9:
            print('.', end='')
            sys.stdout.flush()
    #import pdb; pdb.set_trace()
    #np.savetxt("emb_array.csv", emb_array, delimiter=",")
    return emb_array 

# 需要導入模塊: import facenet [as 別名]
# 或者: from facenet import FLIP [as 別名]
def feature_encode(sess, image_paths, batch_size):

    # Run forward pass to calculate embeddings
    #print('Runnning forward pass on LFW images')

    use_flipped_images = False
    use_fixed_image_standardization = False
    use_random_rotate = False
    use_radnom_crop = False
    # Enqueue one epoch of image paths and labels
    nrof_embeddings = len(image_paths)  # nrof_pairs * nrof_images_per_pair
    nrof_flips = 2 if use_flipped_images else 1
    nrof_images = nrof_embeddings * nrof_flips
    labels_array = np.expand_dims(np.arange(0,nrof_images),1)
    image_paths_array = np.expand_dims(np.repeat(np.array(image_paths),nrof_flips),1)
    control_array = np.zeros_like(labels_array, np.int32)

    if use_fixed_image_standardization:
        control_array += np.ones_like(labels_array)*facenet.FIXED_STANDARDIZATION
    if use_flipped_images:
        # Flip every second image
        control_array += (labels_array % 2)*facenet.FLIP
    if use_random_rotate:
        control_array += facenet.RANDOM_ROTATE
    if use_radnom_crop:
        control_array += facenet.RANDOM_CROP

    sess.run(eval_enqueue_op, {image_paths_placeholder: image_paths_array, 
                      labels_placeholder: labels_array, control_placeholder: control_array})

    embedding_size = int(embeddings.get_shape()[1])
    assert nrof_images % batch_size == 0, 'The number of LFW images must be an integer multiple of the LFW batch size'
    nrof_batches = nrof_images // batch_size
    emb_array = np.zeros((nrof_images, embedding_size))
    lab_array = np.zeros((nrof_images,))
    for i in range(nrof_batches):
        feed_dict = {phase_train_placeholder:False, batch_size_placeholder:batch_size}
        emb, lab = sess.run([embeddings, label_batch], feed_dict=feed_dict)
        lab_array[lab] = lab
        emb_array[lab, :] = emb
        if i % 10 == 9:
            # print('.', end='')
            sys.stdout.flush()
    #import pdb; pdb.set_trace()
    #np.savetxt("emb_array.csv", emb_array, delimiter=",")
    return emb_array 

# 需要導入模塊: import facenet [as 別名]
# 或者: from facenet import FLIP [as 別名]
def evaluate(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder,
        embeddings, labels, image_paths, actual_issame, batch_size, nrof_folds, distance_metric, subtract_mean, use_flipped_images, use_fixed_image_standardization):
    # Run forward pass to calculate embeddings
    print('Runnning forward pass on LFW images')
    
    # Enqueue one epoch of image paths and labels
    nrof_embeddings = len(actual_issame)*2  # nrof_pairs * nrof_images_per_pair
    nrof_flips = 2 if use_flipped_images else 1
    nrof_images = nrof_embeddings * nrof_flips
    labels_array = np.expand_dims(np.arange(0,nrof_images),1)
    image_paths_array = np.expand_dims(np.repeat(np.array(image_paths),nrof_flips),1)
    control_array = np.zeros_like(labels_array, np.int32)
    if use_fixed_image_standardization:
        control_array += np.ones_like(labels_array)*facenet.FIXED_STANDARDIZATION
    if use_flipped_images:
        # Flip every second image
        control_array += (labels_array % 2)*facenet.FLIP
    sess.run(enqueue_op, {image_paths_placeholder: image_paths_array, labels_placeholder: labels_array, control_placeholder: control_array})
    
    embedding_size = int(embeddings.get_shape()[1])
    assert nrof_images % batch_size == 0, 'The number of LFW images must be an integer multiple of the LFW batch size'
    nrof_batches = nrof_images // batch_size
    emb_array = np.zeros((nrof_images, embedding_size))
    lab_array = np.zeros((nrof_images,))
    for i in range(nrof_batches):
        feed_dict = {phase_train_placeholder:False, batch_size_placeholder:batch_size}
        emb, lab = sess.run([embeddings, labels], feed_dict=feed_dict)
        lab_array[lab] = lab
        emb_array[lab, :] = emb
        if i % 10 == 9:
            print('.', end='')
            sys.stdout.flush()
        #import pdb; pdb.set_trace()
    print('')
    
    embeddings = np.zeros((nrof_embeddings, embedding_size*nrof_flips))
    if use_flipped_images:
        # Concatenate embeddings for flipped and non flipped version of the images
        embeddings[:,:embedding_size] = emb_array[0::2,:]
        embeddings[:,embedding_size:] = emb_array[1::2,:]
    else:
        embeddings = emb_array

    assert np.array_equal(lab_array, np.arange(nrof_images))==True, 'Wrong labels used for evaluation, possibly caused by training examples left in the input pipeline'
    tpr, fpr, accuracy, val, val_std, far = lfw.evaluate(embeddings, actual_issame, nrof_folds=nrof_folds, distance_metric=distance_metric, subtract_mean=subtract_mean)
    
    print('Accuracy: %2.5f+-%2.5f' % (np.mean(accuracy), np.std(accuracy)))
    print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
    
    auc = metrics.auc(fpr, tpr)
    print('Area Under Curve (AUC): %1.3f' % auc)
    eer = brentq(lambda x: 1. - x - interpolate.interp1d(fpr, tpr)(x), 0., 1.)
    print('Equal Error Rate (EER): %1.3f' % eer) 

# 需要導入模塊: import facenet [as 別名]
# 或者: from facenet import FLIP [as 別名]
def evaluate(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder,
        embeddings, labels, image_paths, batch_size, distance_metric):
    # Run forward pass to calculate embeddings
    #print('Runnning forward pass on LFW images')
    
    use_flipped_images = False
    use_fixed_image_standardization = False
    use_random_rotate = True
    use_radnom_crop = True
    # Enqueue one epoch of image paths and labels
    nrof_embeddings = len(image_paths)  # nrof_pairs * nrof_images_per_pair
    nrof_flips = 2 if use_flipped_images else 1
    nrof_images = nrof_embeddings * nrof_flips
    labels_array = np.expand_dims(np.arange(0,nrof_images),1)
    image_paths_array = np.expand_dims(np.repeat(np.array(image_paths),nrof_flips),1)
    control_array = np.zeros_like(labels_array, np.int32)
    
    if use_fixed_image_standardization:
        control_array += np.ones_like(labels_array)*facenet.FIXED_STANDARDIZATION
    if use_flipped_images:
        # Flip every second image
        control_array += (labels_array % 2)*facenet.FLIP
    if use_random_rotate:
        control_array += facenet.RANDOM_ROTATE
    if use_radnom_crop:
        control_array += facenet.RANDOM_CROP
        
    sess.run(enqueue_op, {image_paths_placeholder: image_paths_array, labels_placeholder: labels_array, control_placeholder: control_array})
    
    embedding_size = int(embeddings.get_shape()[1])
    assert nrof_images % batch_size == 0, 'The number of LFW images must be an integer multiple of the LFW batch size'
    nrof_batches = nrof_images // batch_size
    emb_array = np.zeros((nrof_images, embedding_size))
    lab_array = np.zeros((nrof_images,))
    for i in range(nrof_batches):
        feed_dict = {phase_train_placeholder:False, batch_size_placeholder:batch_size}
        emb, lab = sess.run([embeddings, labels], feed_dict=feed_dict)
        lab_array[lab] = lab
        emb_array[lab, :] = emb
        if i % 10 == 9:
            print('.', end='')
            sys.stdout.flush()
    #import pdb; pdb.set_trace()
    #np.savetxt("emb_array.csv", emb_array, delimiter=",")
    return emb_array 

# 需要導入模塊: import facenet [as 別名]
# 或者: from facenet import FLIP [as 別名]
def evaluate(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder,
        embeddings, labels, image_paths, batch_size, distance_metric):
    # Run forward pass to calculate embeddings
    #print('Runnning forward pass on LFW images')
    
    use_flipped_images = False
    use_fixed_image_standardization = False
    use_random_rotate = False
    use_radnom_crop = False
    # Enqueue one epoch of image paths and labels
    nrof_embeddings = len(image_paths)  # nrof_pairs * nrof_images_per_pair
    nrof_flips = 2 if use_flipped_images else 1
    nrof_images = nrof_embeddings * nrof_flips
    labels_array = np.expand_dims(np.arange(0,nrof_images),1)
    image_paths_array = np.expand_dims(np.repeat(np.array(image_paths),nrof_flips),1)
    control_array = np.zeros_like(labels_array, np.int32)
    
    if use_fixed_image_standardization:
        control_array += np.ones_like(labels_array)*facenet.FIXED_STANDARDIZATION
    if use_flipped_images:
        # Flip every second image
        control_array += (labels_array % 2)*facenet.FLIP
    if use_random_rotate:
        control_array += facenet.RANDOM_ROTATE
    if use_radnom_crop:
        control_array += facenet.RANDOM_CROP
        
    sess.run(enqueue_op, {image_paths_placeholder: image_paths_array, labels_placeholder: labels_array, control_placeholder: control_array})
    
    embedding_size = int(embeddings.get_shape()[1])
    assert nrof_images % batch_size == 0, 'The number of LFW images must be an integer multiple of the LFW batch size'
    nrof_batches = nrof_images // batch_size
    emb_array = np.zeros((nrof_images, embedding_size))
    lab_array = np.zeros((nrof_images,))
    for i in range(nrof_batches):
        feed_dict = {phase_train_placeholder:False, batch_size_placeholder:batch_size}
        emb, lab = sess.run([embeddings, labels], feed_dict=feed_dict)
        lab_array[lab] = lab
        emb_array[lab, :] = emb
        if i % 10 == 9:
            print('.', end='')
            sys.stdout.flush()
    #import pdb; pdb.set_trace()
    #np.savetxt("emb_array.csv", emb_array, delimiter=",")
    return emb_array 

# 需要導入模塊: import facenet [as 別名]
# 或者: from facenet import FLIP [as 別名]
def evaluate(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder, 
        embeddings, labels, image_paths, actual_issame, batch_size, nrof_folds, log_dir, step, summary_writer, stat, epoch, distance_metric, subtract_mean, use_flipped_images, use_fixed_image_standardization):
    start_time = time.time()
    # Run forward pass to calculate embeddings
    print('Runnning forward pass on LFW images')
    
    # Enqueue one epoch of image paths and labels
    nrof_embeddings = len(actual_issame)*2  # nrof_pairs * nrof_images_per_pair
    nrof_flips = 2 if use_flipped_images else 1
    nrof_images = nrof_embeddings * nrof_flips
    labels_array = np.expand_dims(np.arange(0,nrof_images),1)
    image_paths_array = np.expand_dims(np.repeat(np.array(image_paths),nrof_flips),1)
    control_array = np.zeros_like(labels_array, np.int32)
    if use_fixed_image_standardization:
        control_array += np.ones_like(labels_array)*facenet.FIXED_STANDARDIZATION
    if use_flipped_images:
        # Flip every second image
        control_array += (labels_array % 2)*facenet.FLIP
    sess.run(enqueue_op, {image_paths_placeholder: image_paths_array, labels_placeholder: labels_array, control_placeholder: control_array})
    
    embedding_size = int(embeddings.get_shape()[1])
    assert nrof_images % batch_size == 0, 'The number of LFW images must be an integer multiple of the LFW batch size'
    nrof_batches = nrof_images // batch_size
    emb_array = np.zeros((nrof_images, embedding_size))
    lab_array = np.zeros((nrof_images,))
    for i in range(nrof_batches):
        feed_dict = {phase_train_placeholder:False, batch_size_placeholder:batch_size}
        emb, lab = sess.run([embeddings, labels], feed_dict=feed_dict)
        lab_array[lab] = lab
        emb_array[lab, :] = emb
        if i % 10 == 9:
            print('.', end='')
            sys.stdout.flush()
    print('')
    embeddings = np.zeros((nrof_embeddings, embedding_size*nrof_flips))
    if use_flipped_images:
        # Concatenate embeddings for flipped and non flipped version of the images
        embeddings[:,:embedding_size] = emb_array[0::2,:]
        embeddings[:,embedding_size:] = emb_array[1::2,:]
    else:
        embeddings = emb_array

    assert np.array_equal(lab_array, np.arange(nrof_images))==True, 'Wrong labels used for evaluation, possibly caused by training examples left in the input pipeline'
    _, _, accuracy, val, val_std, far = lfw.evaluate(embeddings, actual_issame, nrof_folds=nrof_folds, distance_metric=distance_metric, subtract_mean=subtract_mean)
    
    print('Accuracy: %2.5f+-%2.5f' % (np.mean(accuracy), np.std(accuracy)))
    print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
    lfw_time = time.time() - start_time
    # Add validation loss and accuracy to summary
    summary = tf.Summary()
    #pylint: disable=maybe-no-member
    summary.value.add(tag='lfw/accuracy', simple_value=np.mean(accuracy))
    summary.value.add(tag='lfw/val_rate', simple_value=val)
    summary.value.add(tag='time/lfw', simple_value=lfw_time)
    summary_writer.add_summary(summary, step)
    with open(os.path.join(log_dir,'lfw_result.txt'),'at') as f:
        f.write('%d\t%.5f\t%.5f\n' % (step, np.mean(accuracy), val))
    stat['lfw_accuracy'][epoch-1] = np.mean(accuracy)
    stat['lfw_valrate'][epoch-1] = val 

# 需要導入模塊: import facenet [as 別名]
# 或者: from facenet import FLIP [as 別名]
def evaluate(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder,
        embeddings, labels, image_paths, actual_issame, batch_size, nrof_folds, distance_metric, subtract_mean, use_flipped_images, use_fixed_image_standardization):
    # Run forward pass to calculate embeddings
    print('Runnning forward pass on LFW images')
    
    # Enqueue one epoch of image paths and labels
    nrof_embeddings = len(actual_issame)*2  # nrof_pairs * nrof_images_per_pair
    nrof_flips = 2 if use_flipped_images else 1
    nrof_images = nrof_embeddings * nrof_flips
    labels_array = np.expand_dims(np.arange(0,nrof_images),1)
    image_paths_array = np.expand_dims(np.repeat(np.array(image_paths),nrof_flips),1)
    control_array = np.zeros_like(labels_array, np.int32)
    if use_fixed_image_standardization:
        control_array += np.ones_like(labels_array)*facenet.FIXED_STANDARDIZATION
    if use_flipped_images:
        # Flip every second image
        control_array += (labels_array % 2)*facenet.FLIP
    sess.run(enqueue_op, {image_paths_placeholder: image_paths_array, labels_placeholder: labels_array, control_placeholder: control_array})
    
    embedding_size = int(embeddings.get_shape()[1])
    assert nrof_images % batch_size == 0, 'The number of LFW images must be an integer multiple of the LFW batch size'
    nrof_batches = nrof_images // batch_size
    emb_array = np.zeros((nrof_images, embedding_size))
    lab_array = np.zeros((nrof_images,))
    for i in range(nrof_batches):
        feed_dict = {phase_train_placeholder:False, batch_size_placeholder:batch_size}
        emb, lab = sess.run([embeddings, labels], feed_dict=feed_dict)
        lab_array[lab] = lab
        emb_array[lab, :] = emb
        if i % 10 == 9:
            print('.', end='')
            sys.stdout.flush()
    print('')
    embeddings = np.zeros((nrof_embeddings, embedding_size*nrof_flips))
    if use_flipped_images:
        # Concatenate embeddings for flipped and non flipped version of the images
        embeddings[:,:embedding_size] = emb_array[0::2,:]
        embeddings[:,embedding_size:] = emb_array[1::2,:]
    else:
        embeddings = emb_array

    assert np.array_equal(lab_array, np.arange(nrof_images))==True, 'Wrong labels used for evaluation, possibly caused by training examples left in the input pipeline'
    tpr, fpr, accuracy, val, val_std, far = lfw.evaluate(embeddings, actual_issame, nrof_folds=nrof_folds, distance_metric=distance_metric, subtract_mean=subtract_mean)
    
    print('Accuracy: %2.5f+-%2.5f' % (np.mean(accuracy), np.std(accuracy)))
    print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
    
    auc = metrics.auc(fpr, tpr)
    print('Area Under Curve (AUC): %1.3f' % auc)
    eer = brentq(lambda x: 1. - x - interpolate.interp1d(fpr, tpr)(x), 0., 1.)
    print('Equal Error Rate (EER): %1.3f' % eer)