def tower_loss(scope): images, labels = read_and_decode() if net == 'vgg_16': with slim.arg_scope(vgg.vgg_arg_scope()): logits, end_points = vgg.vgg_16(images, num_classes=FLAGS.num_classes) elif net == 'vgg_19': with slim.arg_scope(vgg.vgg_arg_scope()): logits, end_points = vgg.vgg_19(images, num_classes=FLAGS.num_classes) elif net == 'resnet_v1_101': with slim.arg_scope(resnet_v1.resnet_arg_scope()): logits, end_points = resnet_v1.resnet_v1_101(images, num_classes=FLAGS.num_classes) logits = tf.reshape(logits, [FLAGS.batch_size, FLAGS.num_classes]) elif net == 'resnet_v1_50': with slim.arg_scope(resnet_v1.resnet_arg_scope()): logits, end_points = resnet_v1.resnet_v1_50(images, num_classes=FLAGS.num_classes) logits = tf.reshape(logits, [FLAGS.batch_size, FLAGS.num_classes]) elif net == 'resnet_v2_50': with slim.arg_scope(resnet_v2.resnet_arg_scope()): logits, end_points = resnet_v2.resnet_v2_50(images, num_classes=FLAGS.num_classes) logits = tf.reshape(logits, [FLAGS.batch_size, FLAGS.num_classes]) else: raise Exception('No network matched with net %s.' % net) assert logits.shape == (FLAGS.batch_size, FLAGS.num_classes) _ = cal_loss(logits, labels) losses = tf.get_collection('losses', scope) total_loss = tf.add_n(losses, name='total_loss') for l in losses + [total_loss]: loss_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', l.op.name) tf.summary.scalar(loss_name, l) return total_loss
def top_feature_net(input, anchors, inds_inside, num_bases): stride=8 # arg_scope = resnet_v1.resnet_arg_scope(weight_decay=0.0) # with slim.arg_scope(arg_scope) : with slim.arg_scope(vgg.vgg_arg_scope()): # net, end_points = resnet_v1.resnet_v1_50(input, None, global_pool=False, output_stride=8) block5, end_points = vgg.vgg_16(input) block3 = end_points['conv3/conv3_3'] # block = conv2d_bn_relu(block, num_kernels=512, kernel_size=(1,1), stride=[1,1,1,1], padding='SAME', name='2') tf.summary.histogram('rpn_top_block', block) # tf.summary.histogram('rpn_top_block_weights', tf.get_collection('2/conv_weight')[0]) with tf.variable_scope('top') as scope: #up = upsample2d(block, factor = 2, has_bias=True, trainable=True, name='1') #up = block up = conv2d_bn_relu(block, num_kernels=128, kernel_size=(3,3), stride=[1,1,1,1], padding='SAME', name='2') scores = conv2d(up, num_kernels=2*num_bases, kernel_size=(1,1), stride=[1,1,1,1], padding='SAME', name='score') probs = tf.nn.softmax( tf.reshape(scores,[-1,2]), name='prob') deltas = conv2d(up, num_kernels=4*num_bases, kernel_size=(1,1), stride=[1,1,1,1], padding='SAME', name='delta') #<todo> flip to train and test mode nms (e.g. different nms_pre_topn values): use tf.cond with tf.variable_scope('top-nms') as scope: #non-max batch_size, img_height, img_width, img_channel = input.get_shape().as_list() img_scale = 1 # pdb.set_trace() rois, roi_scores = tf_rpn_nms( probs, deltas, anchors, inds_inside, stride, img_width, img_height, img_scale, nms_thresh=0.7, min_size=stride, nms_pre_topn=nms_pre_topn_, nms_post_topn=nms_post_topn_, name ='nms') #<todo> feature = upsample2d(block, factor = 4, ...) feature = block
def __call__(self, image_batch): if self.model == vgg16: with slim.arg_scope(vgg.vgg_arg_scope()): features, _ = self.model(inputs=image_batch) if self.model == resnet101: with slim.arg_scope(resnet.resnet_arg_scope()): features, _ = self.model(inputs=image_batch, num_classes=None) return features
def VGG_16(input_image): arg_scope = vgg.vgg_arg_scope() with slim.arg_scope(arg_scope): features, _ = vgg.vgg_16(input_image) # feature flatten features = tf.reshape(features, shape=[1, -1]) features = tf.squeeze(features) return features
def encoder_vgg(x, enc_final_size, reuse=False, scope_prefix='', hparams=None, is_training=True): """VGG network to use as encoder without the top few layers. Can be pretrained. Args: x: The image to encode. In the range 0 to 1. enc_final_size: The desired size of the encoding. reuse: To reuse in variable scope or not. scope_prefix: The prefix before the scope name. hparams: The python hparams. is_training: boolean value indicating if training is happening. Returns: The generated image. """ with tf.variable_scope(scope_prefix + 'encoder', reuse=reuse): # Preprocess input x *= 256 x = x - COLOR_NORMALIZATION_VECTOR with arg_scope(vgg.vgg_arg_scope()): # Padding because vgg_16 accepts images of size at least VGG_IMAGE_SIZE. x = tf.pad(x, [[0, 0], [0, VGG_IMAGE_SIZE - IMG_WIDTH], [0, VGG_IMAGE_SIZE - IMG_HEIGHT], [0, 0]]) _, end_points = vgg.vgg_16(x, num_classes=enc_final_size, is_training=is_training) pool5_key = [key for key in end_points.keys() if 'pool5' in key] assert len(pool5_key) == 1 enc = end_points[pool5_key[0]] # Undoing padding. enc = tf.slice(enc, [0, 0, 0, 0], [-1, 2, 2, -1]) enc_shape = enc.get_shape().as_list() enc_shape[0] = -1 enc_size = enc_shape[1] * enc_shape[2] * enc_shape[3] enc_flat = tf.reshape(enc, (-1, enc_size)) enc_flat = tf.nn.dropout(enc_flat, hparams.enc_keep_prob) enc_flat = tf.layers.dense( enc_flat, enc_final_size, kernel_initializer=tf.truncated_normal_initializer(stddev=1e-4, )) if hparams.enc_pred_use_l2norm: enc_flat = tf.nn.l2_normalize(enc_flat, 1) return enc_flat
def encoder_vgg(x, enc_final_size, reuse=False, scope_prefix='', hparams=None, is_training=True): """VGG network to use as encoder without the top few layers. Can be pretrained. Args: x: The image to encode. In the range 0 to 1. enc_final_size: The desired size of the encoding. reuse: To reuse in variable scope or not. scope_prefix: The prefix before the scope name. hparams: The python hparams. is_training: boolean value indicating if training is happening. Returns: The generated image. """ with tf.variable_scope(scope_prefix + 'encoder', reuse=reuse): # Preprocess input x *= 256 x = x - COLOR_NORMALIZATION_VECTOR with arg_scope(vgg.vgg_arg_scope()): # Padding because vgg_16 accepts images of size at least VGG_IMAGE_SIZE. x = tf.pad(x, [[0, 0], [0, VGG_IMAGE_SIZE - IMG_WIDTH], [0, VGG_IMAGE_SIZE - IMG_HEIGHT], [0, 0]]) _, end_points = vgg.vgg_16( x, num_classes=enc_final_size, is_training=is_training) pool5_key = [key for key in end_points.keys() if 'pool5' in key] assert len(pool5_key) == 1 enc = end_points[pool5_key[0]] # Undoing padding. enc = tf.slice(enc, [0, 0, 0, 0], [-1, 2, 2, -1]) enc_shape = enc.get_shape().as_list() enc_shape[0] = -1 enc_size = enc_shape[1] * enc_shape[2] * enc_shape[3] enc_flat = tf.reshape(enc, (-1, enc_size)) enc_flat = tf.nn.dropout(enc_flat, hparams.enc_keep_prob) enc_flat = tf.layers.dense( enc_flat, enc_final_size, kernel_initializer=tf.truncated_normal_initializer(stddev=1e-4,)) if hparams.enc_pred_use_l2norm: enc_flat = tf.nn.l2_normalize(enc_flat, 1) return enc_flat
def rgb_feature_net(input): # with tf.variable_scope("rgb_base"): # arg_scope = resnet_v1.resnet_arg_scope(weight_decay=0.0) # with slim.arg_scope(arg_scope): with slim.arg_scope(vgg.vgg_arg_scope()): # net, end_points = resnet_v1.resnet_v1_50(input, None, global_pool=False, output_stride=8) # block=end_points['resnet_v1_50/block4'] # block = conv2d_bn_relu(block, num_kernels=512, kernel_size=(1,1), stride=[1,1,1,1], padding='SAME', name='2') block, _ = vgg.vgg_16(input) #<todo> feature = upsample2d(block, factor = 4, ...) tf.summary.histogram('rgb_top_block', block) feature = block return feature
def get_logits_prob(self, batch_input): """ Prediction from the model on a single batch. :param batch_input: the input batch. Must be from size [?, 224, 224, 3] :return: the logits and probabilities for the batch """ with slim.arg_scope(vgg.vgg_arg_scope()): logits, _ = vgg.vgg_16(batch_input, num_classes=1000, is_training=False) probs = tf.squeeze(tf.nn.softmax(logits))[1:] return logits, probs
def __init__(self, tensor, keep_prob=1.0, num_classes=1000, retrain_layer=[], weights_path='./weights/vgg_16.ckpt'): # Call the parent class Model.__init__(self, tensor, keep_prob, num_classes, retrain_layer, weights_path) # TODO This implementation has a problem while validation (is still set to training) is_training = True if retrain_layer else False with slim.arg_scope(vgg_arg_scope()): self.final, self.endpoints = vgg_16(self.tensor, num_classes=self.num_classes, is_training=is_training, dropout_keep_prob=keep_prob)
def build(self): # Input self.input = tf.placeholder( dtype=tf.float32, shape=[None, self.img_size[0], self.img_size[1], self.img_size[2]]) self.input_mean = tfutils.mean_value(self.input, self.img_mean) if self.base_net == 'vgg16': with slim.arg_scope(vgg.vgg_arg_scope()): outputs, end_points = vgg.vgg_16(self.input_mean, self.num_classes) self.prob = tf.nn.softmax(outputs, -1) self.logits = outputs elif self.base_net == 'res50': with slim.arg_scope(resnet_v1.resnet_arg_scope()): net, end_points = resnet_v1.resnet_v1_50( self.input_mean, self.num_classes, is_training=self.is_train) self.prob = tf.nn.softmax(net[:, 0, 0, :], -1) self.logits = net[:, 0, 0, :] elif self.base_net == 'res101': with slim.arg_scope(resnet_v1.resnet_arg_scope()): net, end_points = resnet_v1.resnet_v1_101( self.input_mean, self.num_classes, is_training=self.is_train) self.prob = tf.nn.softmax(net[:, 0, 0, :], -1) self.logits = net[:, 0, 0, :] elif self.base_net == 'res152': with slim.arg_scope(resnet_v1.resnet_arg_scope()): net, end_points = resnet_v1.resnet_v1_152( self.input_mean, self.num_classes, is_training=self.is_train) self.prob = tf.nn.softmax(net[:, 0, 0, :], -1) self.logits = net[:, 0, 0, :] else: raise ValueError( 'base network should be vgg16, res50, -101, -152...') self.gt = tf.placeholder(dtype=tf.int32, shape=[None]) # self.var_list = tf.trainable_variables() if self.is_train: self.loss()
def build_model(self): is_train = self.FLAGS.is_train dropout_keep_prob = 1.0 if is_train: dropout_keep_prob = 0.5 images_placeholder = tf.image.resize_images(self.input_placeholder, (224, 224)) with slim.arg_scope(vgg.vgg_arg_scope()): logits, end_points = vgg.vgg_16(images_placeholder, is_training=is_train, dropout_keep_prob=dropout_keep_prob) image_features = end_points['vgg_16/fc8'] scene_logits = slim.fully_connected(image_features, 100, activation_fn=None, scope='scene_pred', trainable=True) multi_hot_logits = slim.fully_connected(image_features, 175, activation_fn=None, scope='multi_hot_logits', trainable=True) word_embedding_logits = slim.fully_connected(image_features, 300, activation_fn=None, scope='word_embedding_pred', trainable=True) obj_embedding_size = 40 object_embedding_logits = slim.fully_connected(image_features, obj_embedding_size, activation_fn=None, scope='object_embedding_pred', trainable=True) outputs = [scene_logits, multi_hot_logits, word_embedding_logits, object_embedding_logits] return outputs
def run_training(): config = tf.ConfigProto(allow_soft_placement=True) sess = tf.Session(config=config) # sess = tf.Session() # config=tf.ConfigProto(log_device_placement=True)) # create input path and labels np.array from csv annotations df_annos = pd.read_csv(ANNOS_CSV, index_col=0) df_annos = df_annos.sample(frac=1).reset_index( drop=True) # shuffle the whole datasets if DATA == 'l8': path_col = ['l8_vis_jpg'] elif DATA == 's1': path_col = ['s1_vis_jpg'] elif DATA == 'l8s1': path_col = ['l8_vis_jpg', 's1_vis_jpg'] input_files_train = JPG_DIR + df_annos.loc[df_annos.partition == 'train', path_col].values input_labels_train = df_annos.loc[df_annos.partition == 'train', 'pop_density_log2'].values input_files_val = JPG_DIR + df_annos.loc[df_annos.partition == 'val', path_col].values input_labels_val = df_annos.loc[df_annos.partition == 'val', 'pop_density_log2'].values input_id_train = df_annos.loc[df_annos.partition == 'train', 'village_id'].values input_id_val = df_annos.loc[df_annos.partition == 'val', 'village_id'].values print('input_files_train shape:', input_files_train.shape) train_set_size = len(input_labels_train) # data input with tf.device('/cpu:0'): train_images_batch, train_labels_batch, _ = \ dataset.input_batches(FLAGS.batch_size, FLAGS.output_size, input_files_train, input_labels_train, input_id_train, IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNEL, regression=True, augmentation=True, normalization=True) val_images_batch, val_labels_batch, _ = \ dataset.input_batches(FLAGS.batch_size, FLAGS.output_size, input_files_val, input_labels_val, input_id_val, IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNEL, regression=True, augmentation=False, normalization=True) images_placeholder = tf.placeholder( tf.float32, shape=[None, IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNEL]) labels_placeholder = tf.placeholder(tf.float32, shape=[ None, ]) print('finish data input') TRAIN_BATCHES_PER_EPOCH = int( train_set_size / FLAGS.batch_size) # number of training batches/steps in each epoch MAX_STEPS = TRAIN_BATCHES_PER_EPOCH * FLAGS.max_epoch # total number of training batches/steps # CNN forward reference if MODEL == 'vgg': with slim.arg_scope( vgg.vgg_arg_scope(weight_decay=FLAGS.weight_decay)): outputs, _ = vgg.vgg_16(images_placeholder, num_classes=FLAGS.output_size, dropout_keep_prob=FLAGS.dropout_keep, is_training=True) outputs = tf.squeeze( outputs ) # change shape from (B,1) to (B,), same as label input if MODEL == 'resnet': with slim.arg_scope(resnet_v1.resnet_arg_scope()): outputs, _ = resnet_v1.resnet_v1_152(images_placeholder, num_classes=FLAGS.output_size, is_training=True) outputs = tf.squeeze( outputs ) # change shape from (B,1) to (B,), same as label input # loss labels_real = tf.pow(2.0, labels_placeholder) outputs_real = tf.pow(2.0, outputs) # only loss_log2_mse are used for gradient calculate, model minimize this value loss_log2_mse = tf.reduce_mean(tf.squared_difference( labels_placeholder, outputs), name='loss_log2_mse') loss_real_rmse = tf.sqrt(tf.reduce_mean( tf.squared_difference(labels_real, outputs_real)), name='loss_real_rmse') loss_real_mae = tf.losses.absolute_difference(labels_real, outputs_real) tf.summary.scalar('loss_log2_mse', loss_log2_mse) tf.summary.scalar('loss_real_rmse', loss_real_rmse) tf.summary.scalar('loss_real_mae', loss_real_mae) # accuracy (R2) def r_sqaured(labels, outputs): sst = tf.reduce_sum( tf.squared_difference(labels, tf.reduce_mean(labels))) sse = tf.reduce_sum(tf.squared_difference(labels, outputs)) return (1.0 - tf.div(sse, sst)) r2_log2 = r_sqaured(labels_placeholder, outputs) r2_real = r_sqaured(labels_real, outputs_real) tf.summary.scalar('r2_log2', r2_log2) tf.summary.scalar('r2_real', r2_real) # determine the model vairables to restore from pre-trained checkpoint if MODEL == 'vgg': if DATA == 'l8s1': model_variables = slim.get_variables_to_restore( exclude=['vgg_16/fc8', 'vgg_16/conv1']) else: model_variables = slim.get_variables_to_restore( exclude=['vgg_16/fc8']) if MODEL == 'resnet': model_variables = slim.get_variables_to_restore( exclude=['resnet_v1_152/logits', 'resnet_v1_152/conv1']) # training step and learning rate global_step = tf.Variable(0, name='global_step', trainable=False) #, dtype=tf.int64) learning_rate = tf.train.exponential_decay( FLAGS.learning_rate, # initial learning rate global_step=global_step, # current step decay_steps=MAX_STEPS, # total numbers step to decay decay_rate=FLAGS.lr_decay_rate ) # final learning rate = FLAGS.learning_rate * decay_rate tf.summary.scalar('learning_rate', learning_rate) optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate) # optimizer = tf.train.RMSPropOptimizer(learning_rate=learning_rate) # optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate) # to only update gradient in first and last layer # vars_update = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, 'vgg_16/(conv1|fc8)') # print('variables to update in traing: ', vars_update) train_op = optimizer.minimize( loss_log2_mse, global_step=global_step) #, var_list = vars_update) # summary output in tensorboard summary = tf.summary.merge_all() summary_writer_train = tf.summary.FileWriter( os.path.join(LOG_DIR, 'log_train'), sess.graph) summary_writer_val = tf.summary.FileWriter( os.path.join(LOG_DIR, 'log_val'), sess.graph) # variable initialize init = tf.global_variables_initializer() sess.run(init) # restore the model from pre-trained checkpoint restorer = tf.train.Saver(model_variables) restorer.restore(sess, PRETRAIN_WEIGHTS) print('loaded pre-trained weights: ', PRETRAIN_WEIGHTS) # saver object to save checkpoint during training saver = tf.train.Saver(tf.global_variables(), max_to_keep=10) print('start training...') epoch = 0 best_r2 = -float('inf') for step in xrange(MAX_STEPS): if step % TRAIN_BATCHES_PER_EPOCH == 0: epoch += 1 start_time = time.time() # record the time used for each batch images_out, labels_out = sess.run( [train_images_batch, train_labels_batch]) # inputs of this batch, numpy array format duration_batch = time.time() - start_time if step == 0: print("finished reading batch data") print("images_out shape:", images_out.shape) feed_dict = { images_placeholder: images_out, labels_placeholder: labels_out } _, train_loss, train_accuracy, train_outputs, lr = \ sess.run([train_op, loss_log2_mse, r2_log2, outputs, learning_rate], feed_dict=feed_dict) duration = time.time() - start_time if step % 10 == 0 or ( step + 1) == MAX_STEPS: # print traing loss every 10 batches print('Step %d epoch %d lr %.3e: log2 MSE loss = %.4f log2 R2 = %.4f (%.3f sec, %.3f sec(each batch))' \ % (step, epoch, lr, train_loss, train_accuracy, duration*10, duration_batch)) summary_str = sess.run(summary, feed_dict=feed_dict) summary_writer_train.add_summary(summary_str, step) summary_writer_train.flush() if step % 50 == 0 or ( step + 1 ) == MAX_STEPS: # calculate and print validation loss every 50 batches images_out, labels_out = sess.run( [val_images_batch, val_labels_batch]) feed_dict = { images_placeholder: images_out, labels_placeholder: labels_out } val_loss, val_accuracy = sess.run([loss_log2_mse, r2_log2], feed_dict=feed_dict) print('Step %d epoch %d: val log2 MSE = %.4f val log2 R2 = %.4f ' % (step, epoch, val_loss, val_accuracy)) summary_str = sess.run(summary, feed_dict=feed_dict) summary_writer_val.add_summary(summary_str, step) summary_writer_val.flush() # in each epoch, if the validation R2 is higher than best R2, save the checkpoint if step % (TRAIN_BATCHES_PER_EPOCH - TRAIN_BATCHES_PER_EPOCH % 50) == 0: if val_accuracy > best_r2: best_r2 = val_accuracy checkpoint_file = os.path.join(LOG_DIR, 'model.ckpt') saver.save(sess, checkpoint_file, global_step=step, write_state=True)
def main(argv=None): # 加载处理好的数据 processed_data = np.load(INPUT_DATA) training_images = processed_data[0] n_training_examples = len(training_images) training_labels = processed_data[1] validation_images = processed_data[2] validation_labels = processed_data[3] testing_images = processed_data[4] testing_labels = processed_data[5] print('%d training, %d validation, %d testing' % (n_training_examples, len(validation_labels), len(testing_labels))) # 定义vgg16的输入 images = tf.placeholder(tf.float32, [None, 224, 224, 3], name='input_image') labels = tf.placeholder(tf.int64, [None], name='labels') # 定义vgg16模型 with slim.arg_scope(vgg.vgg_arg_scope()): logits, _ = vgg.vgg_16(images, num_classes=N_CLASSES) # 损失函数 loss_fun = tf.losses.softmax_cross_entropy(tf.one_hot(labels, N_CLASSES), logits) # 训练 # train_step = tf.train.RMSPropOptimizer(LEARNING_RATE).minimize(tf.losses.get_total_loss()) # 只训练最后一层 train_step = tf.train.RMSPropOptimizer(LEARNING_RATE).minimize( tf.losses.get_total_loss(), var_list=get_trainable_variables()) # 正确率 with tf.variable_scope('evaluation'): correct_prediction = tf.equal(tf.argmax(logits, 1), labels) evaluation_step = tf.reduce_mean( tf.cast(correct_prediction, tf.float32)) ckpt = tf.train.get_checkpoint_state(SAVE_PATH) if ckpt and ckpt.model_checkpoint_path: # 加载之前训练的参数继续训练 variables_to_restore = slim.get_model_variables() print('continue training from %s' % ckpt) step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1] step = int(step) ckpt = ckpt.model_checkpoint_path else: # 没有训练数据,就先迁移一部分训练好的 ckpt = TRAINED_CKPT_FILE variables_to_restore = get_tuned_variable() print('loading tuned variables from %s' % TRAINED_CKPT_FILE) step = 0 load_fn = slim.assign_from_checkpoint_fn(ckpt, variables_to_restore, ignore_missing_vars=True) # 开启会话训练 saver = tf.train.Saver() with tf.Session() as sess: # 初始化所有参数 init = tf.global_variables_initializer() sess.run(init) load_fn(sess) start = 0 end = BATCH for i in range(step + 1, step + 1 + STEPS): start_time = time.time() # 运行训练,不会更新所有参数 _, loss_val = sess.run( [train_step, loss_fun], feed_dict={ images: training_images[start:end], labels: training_labels[start:end] }) duration = time.time() - start_time #print('current train step duration %.3f' % duration) if i % 10 == 0: print('after %d train step, loss value is: %.4f' % (i, loss_val)) # 输出日志 if i % 100 == 0: saver.save(sess, TRAIN_FILE, global_step=i) validation_accuracy = sess.run(evaluation_step, feed_dict={ images: validation_images, labels: validation_labels }) print('Step %d Validation accuracy = %.1f%%' % (i, validation_accuracy * 100.0)) start = end if start == n_training_examples: start = 0 end = start + BATCH if end > n_training_examples: end = n_training_examples # 在测试集上测试正确率 test_accuracy = sess.run(evaluation_step, feed_dict={ images: testing_images, labels: testing_labels }) print('Final test accuracy = %.1f%%' % (test_accuracy * 100.0))
def __call__(self, inputs, training=False): with slim.arg_scope(vgg_arg_scope()): return slim_vgg_16(inputs, is_training=training)[0]
def run_testing(): with tf.Graph().as_default(): with slim.arg_scope(vgg.vgg_arg_scope()): images, labels, filenames = inputs(FLAGS.batch_size, FLAGS.num_epochs) images = tf.reshape(images, [-1, gd.INPUT_SIZE, gd.INPUT_SIZE, 3]) logits, end_points = alexnet.alexnet_v2(images, num_classes=gd.NUM_CLASSES, is_training=False) print(labels) print(logits) eps = tf.constant(value=1e-10) flat_logits = logits + eps softmax = tf.nn.softmax(flat_logits) probability = tf.reduce_max(softmax, axis=1) ll = tf.argmax(logits, axis=1) print(ll) variables_to_restore = slim.get_variables_to_restore() saver = tf.train.Saver(variables_to_restore) eval_correct = evaluation(logits, labels) config = tf.ConfigProto() config.gpu_options.allow_growth = True with tf.Session(config=config) as sess: saver.restore(sess, checkpoint_file) coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) step = 0 if not os.path.exists(gd.DIR_DESCRIPTION): os.makedirs(gd.DIR_DESCRIPTION) csvfile = open( gd.DIR_DESCRIPTION + "/12cls_2017-11-16_alexnet_sensi_color_change_wrongprediction.csv", "a") writer = csv.writer(csvfile) writer.writerow(['labels', 'prediction', 'filename']) file_name2 = "/detail_result.csv" csvfile2 = open(gd.DIR_DESCRIPTION + file_name2, "wb") writer2 = csv.writer(csvfile2) writer2.writerow(['labels', 'prediction', 'probability']) for step in range(gd.TOTAL): #while not coord.should_stop(): #accuracy=do_eval(sess,eval_correct,log_name) labels_out, prediction_out, filename, softmax_out, probability_max = sess.run( [labels, ll, filenames, softmax, probability]) print("%d : %d ,%d ,max_probability: %f" % (step, labels_out[0], prediction_out[0], probability_max[0])) writer2.writerow( [labels_out[0], prediction_out[0], probability_max[0]]) #print(labels_out[0]) #print(prediction_out[0]) count_label[labels_out[0]] += 1 if labels_out[0] == prediction_out[0]: count_prediction[prediction_out[0]] += 1 else: writer.writerow( [labels_out[0], prediction_out[0], filename[0]]) confusion_matrix[labels_out[0]][prediction_out[0]] += 1 #details_accuray(labels_out,prediction_out,gd.NUM_CLASSES) csvfile.close() print(count_label) print(count_prediction) print(confusion_matrix) print('\n') for i in range(num_of_class): print(confusion_matrix[i]) precision_result = [0 for i in range(num_of_class)] recall_result = [0 for i in range(num_of_class)] #for i in range(num_of_class): # precision_result[i]=confusion_matrix[i][i]/ precision_sum = map(sum, zip(*confusion_matrix)) print("precision_sum:") print(precision_sum) for i in range(num_of_class): precision_result[i] = confusion_matrix[i][i] / precision_sum[i] print("average_precision:") print(precision_result) print("mean_average_precision:") print(sum(precision_result) / num_of_class) print("recall_sum:") recall_sum = map(sum, confusion_matrix) print(recall_sum) for i in range(num_of_class): recall_result[i] = confusion_matrix[i][i] / recall_sum[i] print("recall:") print(recall_result) print("mean_recall:") print(sum(recall_result) / num_of_class) print("accuracy:%d/%d" % (sum(count_prediction), sum(count_label))) #print(sum(count_prediction)) #print(count_prediction) #print(sum(count_label)) print(sum(count_prediction) / sum(count_label))
"First_Student_IC_school_bus_202076.jpg") image_string = urllib2.urlopen(url).read() image = tf.image.decode_jpeg(image_string, channels=3) # Convert image to float32 before subtracting the # mean pixel value image_float = tf.to_float(image, name='ToFloat') # Subtract the mean pixel value from each pixel processed_image = _mean_image_subtraction(image_float, [_R_MEAN, _G_MEAN, _B_MEAN]) input_image = tf.expand_dims(processed_image, 0) with slim.arg_scope(vgg.vgg_arg_scope()): # spatial_squeeze option enables to use network in a fully # convolutional manner logits, _ = vgg.vgg_16(input_image, num_classes=1000, is_training=False, spatial_squeeze=False) # For each pixel we get predictions for each class # out of 1000. We need to pick the one with the highest # probability. To be more precise, these are not probabilities, # because we didn't apply softmax. But if we pick a class # with the highest value it will be equivalent to picking # the highest value after applying softmax pred = tf.argmax(logits, dimension=3)