AttributeError: 'module' object has no attribute 'text_format'
来源:互联网 发布:夏普比率算法 编辑:程序博客网 时间:2024/06/05 07:25
請注意,本類僅僅是記錄開發過程中遇到對問題,可能會亂貼代碼,亂貼圖,亂貼報錯信息,不保證能解決問題,以及有優美的排版,後面有時間我會重新整理的。
解決方法
sudo pip install protobuf==2.6.0
注意:參考的文章請點這裏
簡略報錯信息
./experiments/scripts/faster_rcnn_alt_opt.sh 0 ZF pascal_vocProcess Process-1:Traceback (most recent call last): File "/usr/lib/python2.7/multiprocessing/process.py", line 258, in _bootstrap self.run() File "/usr/lib/python2.7/multiprocessing/process.py", line 114, in run self._target(*self._args, **self._kwargs) File "./tools/train_faster_rcnn_alt_opt.py", line 129, in train_rpn max_iters=max_iters) File "/home/pikachu/dev/py-faster-rcnn/tools/../lib/fast_rcnn/train.py", line 157, in train_net pretrained_model=pretrained_model) File "/home/pikachu/dev/py-faster-rcnn/tools/../lib/fast_rcnn/train.py", line 51, in __init__ pb2.text_format.Merge(f.read(), self.solver_param)AttributeError: 'module' object has no attribute 'text_format'
詳細的報錯信息
pikachu@pikachu-Aspire-VN7-591G:~/dev/py-faster-rcnn$ ./experiments/scripts/faster_rcnn_alt_opt.sh 0 ZF pascal_voc+ set -e+ export PYTHONUNBUFFERED=True+ PYTHONUNBUFFERED=True+ GPU_ID=0+ NET=ZF+ NET_lc=zf+ DATASET=pascal_voc+ array=($@)+ len=3+ EXTRA_ARGS=+ EXTRA_ARGS_SLUG=+ case $DATASET in+ TRAIN_IMDB=voc_2007_trainval+ TEST_IMDB=voc_2007_test+ PT_DIR=pascal_voc+ ITERS=40000++ date +%Y-%m-%d_%H-%M-%S+ LOG=experiments/logs/faster_rcnn_alt_opt_ZF_.txt.2017-07-07_10-46-59+ exec++ tee -a experiments/logs/faster_rcnn_alt_opt_ZF_.txt.2017-07-07_10-46-59+ echo Logging output to experiments/logs/faster_rcnn_alt_opt_ZF_.txt.2017-07-07_10-46-59Logging output to experiments/logs/faster_rcnn_alt_opt_ZF_.txt.2017-07-07_10-46-59+ ./tools/train_faster_rcnn_alt_opt.py --gpu 0 --net_name ZF --weights data/imagenet_models/ZF.v2.caffemodel --imdb voc_2007_trainval --cfg experiments/cfgs/faster_rcnn_alt_opt.ymlCalled with args:Namespace(cfg_file='experiments/cfgs/faster_rcnn_alt_opt.yml', gpu_id=0, imdb_name='voc_2007_trainval', net_name='ZF', pretrained_model='data/imagenet_models/ZF.v2.caffemodel', set_cfgs=None)~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~Stage 1 RPN, init from ImageNet model~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~Init model: data/imagenet_models/ZF.v2.caffemodelUsing config:{'DATA_DIR': '/home/pikachu/dev/py-faster-rcnn/data', 'DEDUP_BOXES': 0.0625, 'EPS': 1e-14, 'EXP_DIR': 'faster_rcnn_alt_opt', 'GPU_ID': 0, 'MATLAB': 'matlab', 'MODELS_DIR': '/home/pikachu/dev/py-faster-rcnn/models/pascal_voc', 'PIXEL_MEANS': array([[[ 102.9801, 115.9465, 122.7717]]]), 'RNG_SEED': 3, 'ROOT_DIR': '/home/pikachu/dev/py-faster-rcnn', 'TEST': {'BBOX_REG': True, 'HAS_RPN': True, 'MAX_SIZE': 1000, 'NMS': 0.3, 'PROPOSAL_METHOD': 'selective_search', 'RPN_MIN_SIZE': 16, 'RPN_NMS_THRESH': 0.7, 'RPN_POST_NMS_TOP_N': 300, 'RPN_PRE_NMS_TOP_N': 6000, 'SCALES': [600], 'SVM': False}, 'TRAIN': {'ASPECT_GROUPING': True, 'BATCH_SIZE': 128, 'BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0], 'BBOX_NORMALIZE_MEANS': [0.0, 0.0, 0.0, 0.0], 'BBOX_NORMALIZE_STDS': [0.1, 0.1, 0.2, 0.2], 'BBOX_NORMALIZE_TARGETS': True, 'BBOX_NORMALIZE_TARGETS_PRECOMPUTED': False, 'BBOX_REG': False, 'BBOX_THRESH': 0.5, 'BG_THRESH_HI': 0.5, 'BG_THRESH_LO': 0.0, 'FG_FRACTION': 0.25, 'FG_THRESH': 0.5, 'HAS_RPN': True, 'IMS_PER_BATCH': 1, 'MAX_SIZE': 1000, 'PROPOSAL_METHOD': 'gt', 'RPN_BATCHSIZE': 256, 'RPN_BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0], 'RPN_CLOBBER_POSITIVES': False, 'RPN_FG_FRACTION': 0.5, 'RPN_MIN_SIZE': 16, 'RPN_NEGATIVE_OVERLAP': 0.3, 'RPN_NMS_THRESH': 0.7, 'RPN_POSITIVE_OVERLAP': 0.7, 'RPN_POSITIVE_WEIGHT': -1.0, 'RPN_POST_NMS_TOP_N': 2000, 'RPN_PRE_NMS_TOP_N': 12000, 'SCALES': [600], 'SNAPSHOT_INFIX': 'stage1', 'SNAPSHOT_ITERS': 10000, 'USE_FLIPPED': True, 'USE_PREFETCH': False}, 'USE_GPU_NMS': True}Loaded dataset `voc_2007_trainval` for trainingSet proposal method: gtAppending horizontally-flipped training examples...wrote gt roidb to /home/pikachu/dev/py-faster-rcnn/data/cache/voc_2007_trainval_gt_roidb.pkldonePreparing training data...doneroidb len: 10022Output will be saved to `/home/pikachu/dev/py-faster-rcnn/output/faster_rcnn_alt_opt/voc_2007_trainval`Filtered 0 roidb entries: 10022 -> 10022WARNING: Logging before InitGoogleLogging() is written to STDERRI0707 10:47:17.331874 3142 solver.cpp:44] Initializing solver from parameters: train_net: "models/pascal_voc/ZF/faster_rcnn_alt_opt/stage1_rpn_train.pt"base_lr: 0.001display: 20lr_policy: "step"gamma: 0.1momentum: 0.9weight_decay: 0.0005stepsize: 60000snapshot: 0snapshot_prefix: "zf_rpn"average_loss: 100I0707 10:47:17.331914 3142 solver.cpp:77] Creating training net from train_net file: models/pascal_voc/ZF/faster_rcnn_alt_opt/stage1_rpn_train.ptI0707 10:47:17.332700 3142 net.cpp:51] Initializing net from parameters: name: "ZF"state { phase: TRAIN}layer { name: "input-data" type: "Python" top: "data" top: "im_info" top: "gt_boxes" python_param { module: "roi_data_layer.layer" layer: "RoIDataLayer" param_str: "\'num_classes\': 21" }}layer { name: "conv1" type: "Convolution" bottom: "data" top: "conv1" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 96 pad: 3 kernel_size: 7 stride: 2 }}layer { name: "relu1" type: "ReLU" bottom: "conv1" top: "conv1"}layer { name: "norm1" type: "LRN" bottom: "conv1" top: "norm1" lrn_param { local_size: 3 alpha: 5e-05 beta: 0.75 norm_region: WITHIN_CHANNEL engine: CAFFE }}layer { name: "pool1" type: "Pooling" bottom: "norm1" top: "pool1" pooling_param { pool: MAX kernel_size: 3 stride: 2 pad: 1 }}layer { name: "conv2" type: "Convolution" bottom: "pool1" top: "conv2" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 256 pad: 2 kernel_size: 5 stride: 2 }}layer { name: "relu2" type: "ReLU" bottom: "conv2" top: "conv2"}layer { name: "norm2" type: "LRN" bottom: "conv2" top: "norm2" lrn_param { local_size: 3 alpha: 5e-05 beta: 0.75 norm_region: WITHIN_CHANNEL engine: CAFFE }}layer { name: "pool2" type: "Pooling" bottom: "norm2" top: "pool2" pooling_param { pool: MAX kernel_size: 3 stride: 2 pad: 1 }}layer { name: "conv3" type: "Convolution" bottom: "pool2" top: "conv3" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 384 pad: 1 kernel_size: 3 stride: 1 }}layer { name: "relu3" type: "ReLU" bottom: "conv3" top: "conv3"}layer { name: "conv4" type: "Convolution" bottom: "conv3" top: "conv4" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 384 pad: 1 kernel_size: 3 stride: 1 }}layer { name: "relu4" type: "ReLU" bottom: "conv4" top: "conv4"}layer { name: "conv5" type: "Convolution" bottom: "conv4" top: "conv5" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 256 pad: 1 kernel_size: 3 stride: 1 }}layer { name: "relu5" type: "ReLU" bottom: "conv5" top: "conv5"}layer { name: "rpn_conv1" type: "Convolution" bottom: "conv5" top: "rpn_conv1" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 256 pad: 1 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "rpn_relu1" type: "ReLU" bottom: "rpn_conv1" top: "rpn_conv1"}layer { name: "rpn_cls_score" type: "Convolution" bottom: "rpn_conv1" top: "rpn_cls_score" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 18 pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "rpn_bbox_pred" type: "Convolution" bottom: "rpn_conv1" top: "rpn_bbox_pred" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 36 pad: 0 kernel_size: 1 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "rpn_cls_score_reshape" type: "Reshape" bottom: "rpn_cls_score" top: "rpn_cls_score_reshape" reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }}layer { name: "rpn-data" type: "Python" bottom: "rpn_cls_score" bottom: "gt_boxes" bottom: "im_info" bottom: "data" top: "rpn_labels" top: "rpn_bbox_targets" top: "rpn_bbox_inside_weights" top: "rpn_bbox_outside_weights" python_param { module: "rpn.anchor_target_layer" layer: "AnchorTargetLayer" param_str: "\'feat_stride\': 16" }}layer { name: "rpn_loss_cls" type: "SoftmaxWithLoss" bottom: "rpn_cls_score_reshape" bottom: "rpn_labels" top: "rpn_cls_loss" loss_weight: 1 propagate_down: true propagate_down: false loss_param { ignore_label: -1 normalize: true }}layer { name: "rpn_loss_bbox" type: "SmoothL1Loss" bottom: "rpn_bbox_pred" bottom: "rpn_bbox_targets" bottom: "rpn_bbox_inside_weights" bottom: "rpn_bbox_outside_weights" top: "rpn_loss_bbox" loss_weight: 1 smooth_l1_loss_param { sigma: 3 }}layer { name: "dummy_roi_pool_conv5" type: "DummyData" top: "dummy_roi_pool_conv5" dummy_data_param { data_filler { type: "gaussian" std: 0.01 } shape { dim: 1 dim: 9216 } }}layer { name: "fc6" type: "InnerProduct" bottom: "dummy_roi_pool_conv5" top: "fc6" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } inner_product_param { num_output: 4096 }}layer { name: "relu6" type: "ReLU" bottom: "fc6" top: "fc6"}layer { name: "fc7" type: "InnerProduct" bottom: "fc6" top: "fc7" param { lr_mult: 0 decay_mult: 0 } param { lr_mult: 0 decay_mult: 0 } inner_product_param { num_output: 4096 }}layer { name: "silence_fc7" type: "Silence" bottom: "fc7"}I0707 10:47:17.332875 3142 layer_factory.hpp:77] Creating layer input-dataI0707 10:47:17.363018 3142 net.cpp:84] Creating Layer input-dataI0707 10:47:17.363045 3142 net.cpp:380] input-data -> dataI0707 10:47:17.374701 3142 net.cpp:380] input-data -> im_infoI0707 10:47:17.374732 3142 net.cpp:380] input-data -> gt_boxesRoiDataLayer: name_to_top: {'gt_boxes': 2, 'data': 0, 'im_info': 1}I0707 10:47:17.401430 3142 net.cpp:122] Setting up input-dataI0707 10:47:17.401459 3142 net.cpp:129] Top shape: 1 3 600 1000 (1800000)I0707 10:47:17.401475 3142 net.cpp:129] Top shape: 1 3 (3)I0707 10:47:17.401480 3142 net.cpp:129] Top shape: 1 4 (4)I0707 10:47:17.401484 3142 net.cpp:137] Memory required for data: 7200028I0707 10:47:17.401494 3142 layer_factory.hpp:77] Creating layer data_input-data_0_splitI0707 10:47:17.401506 3142 net.cpp:84] Creating Layer data_input-data_0_splitI0707 10:47:17.401511 3142 net.cpp:406] data_input-data_0_split <- dataI0707 10:47:17.401522 3142 net.cpp:380] data_input-data_0_split -> data_input-data_0_split_0I0707 10:47:17.401533 3142 net.cpp:380] data_input-data_0_split -> data_input-data_0_split_1I0707 10:47:17.401567 3142 net.cpp:122] Setting up data_input-data_0_splitI0707 10:47:17.401576 3142 net.cpp:129] Top shape: 1 3 600 1000 (1800000)I0707 10:47:17.401584 3142 net.cpp:129] Top shape: 1 3 600 1000 (1800000)I0707 10:47:17.401587 3142 net.cpp:137] Memory required for data: 21600028I0707 10:47:17.401590 3142 layer_factory.hpp:77] Creating layer conv1I0707 10:47:17.401612 3142 net.cpp:84] Creating Layer conv1I0707 10:47:17.401617 3142 net.cpp:406] conv1 <- data_input-data_0_split_0I0707 10:47:17.401621 3142 net.cpp:380] conv1 -> conv1I0707 10:47:21.584990 3142 net.cpp:122] Setting up conv1I0707 10:47:21.585019 3142 net.cpp:129] Top shape: 1 96 300 500 (14400000)I0707 10:47:21.585022 3142 net.cpp:137] Memory required for data: 79200028I0707 10:47:21.585036 3142 layer_factory.hpp:77] Creating layer relu1I0707 10:47:21.585047 3142 net.cpp:84] Creating Layer relu1I0707 10:47:21.585049 3142 net.cpp:406] relu1 <- conv1I0707 10:47:21.585054 3142 net.cpp:367] relu1 -> conv1 (in-place)I0707 10:47:21.585517 3142 net.cpp:122] Setting up relu1I0707 10:47:21.585530 3142 net.cpp:129] Top shape: 1 96 300 500 (14400000)I0707 10:47:21.585531 3142 net.cpp:137] Memory required for data: 136800028I0707 10:47:21.585535 3142 layer_factory.hpp:77] Creating layer norm1I0707 10:47:21.585546 3142 net.cpp:84] Creating Layer norm1I0707 10:47:21.585549 3142 net.cpp:406] norm1 <- conv1I0707 10:47:21.585553 3142 net.cpp:380] norm1 -> norm1I0707 10:47:21.585670 3142 net.cpp:122] Setting up norm1I0707 10:47:21.585677 3142 net.cpp:129] Top shape: 1 96 300 500 (14400000)I0707 10:47:21.585680 3142 net.cpp:137] Memory required for data: 194400028I0707 10:47:21.585681 3142 layer_factory.hpp:77] Creating layer pool1I0707 10:47:21.585686 3142 net.cpp:84] Creating Layer pool1I0707 10:47:21.585688 3142 net.cpp:406] pool1 <- norm1I0707 10:47:21.585692 3142 net.cpp:380] pool1 -> pool1I0707 10:47:21.585722 3142 net.cpp:122] Setting up pool1I0707 10:47:21.585727 3142 net.cpp:129] Top shape: 1 96 151 251 (3638496)I0707 10:47:21.585729 3142 net.cpp:137] Memory required for data: 208954012I0707 10:47:21.585731 3142 layer_factory.hpp:77] Creating layer conv2I0707 10:47:21.585739 3142 net.cpp:84] Creating Layer conv2I0707 10:47:21.585746 3142 net.cpp:406] conv2 <- pool1I0707 10:47:21.585749 3142 net.cpp:380] conv2 -> conv2I0707 10:47:21.600478 3142 net.cpp:122] Setting up conv2I0707 10:47:21.600505 3142 net.cpp:129] Top shape: 1 256 76 126 (2451456)I0707 10:47:21.600509 3142 net.cpp:137] Memory required for data: 218759836I0707 10:47:21.600523 3142 layer_factory.hpp:77] Creating layer relu2I0707 10:47:21.600533 3142 net.cpp:84] Creating Layer relu2I0707 10:47:21.600543 3142 net.cpp:406] relu2 <- conv2I0707 10:47:21.600548 3142 net.cpp:367] relu2 -> conv2 (in-place)I0707 10:47:21.600803 3142 net.cpp:122] Setting up relu2I0707 10:47:21.600814 3142 net.cpp:129] Top shape: 1 256 76 126 (2451456)I0707 10:47:21.600817 3142 net.cpp:137] Memory required for data: 228565660I0707 10:47:21.600819 3142 layer_factory.hpp:77] Creating layer norm2I0707 10:47:21.600828 3142 net.cpp:84] Creating Layer norm2I0707 10:47:21.600831 3142 net.cpp:406] norm2 <- conv2I0707 10:47:21.600836 3142 net.cpp:380] norm2 -> norm2I0707 10:47:21.600947 3142 net.cpp:122] Setting up norm2I0707 10:47:21.600955 3142 net.cpp:129] Top shape: 1 256 76 126 (2451456)I0707 10:47:21.600957 3142 net.cpp:137] Memory required for data: 238371484I0707 10:47:21.600960 3142 layer_factory.hpp:77] Creating layer pool2I0707 10:47:21.600965 3142 net.cpp:84] Creating Layer pool2I0707 10:47:21.600966 3142 net.cpp:406] pool2 <- norm2I0707 10:47:21.600970 3142 net.cpp:380] pool2 -> pool2I0707 10:47:21.601002 3142 net.cpp:122] Setting up pool2I0707 10:47:21.601007 3142 net.cpp:129] Top shape: 1 256 39 64 (638976)I0707 10:47:21.601011 3142 net.cpp:137] Memory required for data: 240927388I0707 10:47:21.601012 3142 layer_factory.hpp:77] Creating layer conv3I0707 10:47:21.601019 3142 net.cpp:84] Creating Layer conv3I0707 10:47:21.601023 3142 net.cpp:406] conv3 <- pool2I0707 10:47:21.601027 3142 net.cpp:380] conv3 -> conv3I0707 10:47:21.615322 3142 net.cpp:122] Setting up conv3I0707 10:47:21.615350 3142 net.cpp:129] Top shape: 1 384 39 64 (958464)I0707 10:47:21.615352 3142 net.cpp:137] Memory required for data: 244761244I0707 10:47:21.615366 3142 layer_factory.hpp:77] Creating layer relu3I0707 10:47:21.615375 3142 net.cpp:84] Creating Layer relu3I0707 10:47:21.615378 3142 net.cpp:406] relu3 <- conv3I0707 10:47:21.615386 3142 net.cpp:367] relu3 -> conv3 (in-place)I0707 10:47:21.615893 3142 net.cpp:122] Setting up relu3I0707 10:47:21.615907 3142 net.cpp:129] Top shape: 1 384 39 64 (958464)I0707 10:47:21.615911 3142 net.cpp:137] Memory required for data: 248595100I0707 10:47:21.615913 3142 layer_factory.hpp:77] Creating layer conv4I0707 10:47:21.615923 3142 net.cpp:84] Creating Layer conv4I0707 10:47:21.615926 3142 net.cpp:406] conv4 <- conv3I0707 10:47:21.615932 3142 net.cpp:380] conv4 -> conv4I0707 10:47:21.620095 3142 net.cpp:122] Setting up conv4I0707 10:47:21.620124 3142 net.cpp:129] Top shape: 1 384 39 64 (958464)I0707 10:47:21.620127 3142 net.cpp:137] Memory required for data: 252428956I0707 10:47:21.620136 3142 layer_factory.hpp:77] Creating layer relu4I0707 10:47:21.620146 3142 net.cpp:84] Creating Layer relu4I0707 10:47:21.620149 3142 net.cpp:406] relu4 <- conv4I0707 10:47:21.620154 3142 net.cpp:367] relu4 -> conv4 (in-place)I0707 10:47:21.620321 3142 net.cpp:122] Setting up relu4I0707 10:47:21.620329 3142 net.cpp:129] Top shape: 1 384 39 64 (958464)I0707 10:47:21.620332 3142 net.cpp:137] Memory required for data: 256262812I0707 10:47:21.620333 3142 layer_factory.hpp:77] Creating layer conv5I0707 10:47:21.620340 3142 net.cpp:84] Creating Layer conv5I0707 10:47:21.620343 3142 net.cpp:406] conv5 <- conv4I0707 10:47:21.620348 3142 net.cpp:380] conv5 -> conv5I0707 10:47:21.623618 3142 net.cpp:122] Setting up conv5I0707 10:47:21.623647 3142 net.cpp:129] Top shape: 1 256 39 64 (638976)I0707 10:47:21.623651 3142 net.cpp:137] Memory required for data: 258818716I0707 10:47:21.623662 3142 layer_factory.hpp:77] Creating layer relu5I0707 10:47:21.623670 3142 net.cpp:84] Creating Layer relu5I0707 10:47:21.623673 3142 net.cpp:406] relu5 <- conv5I0707 10:47:21.623690 3142 net.cpp:367] relu5 -> conv5 (in-place)I0707 10:47:21.624076 3142 net.cpp:122] Setting up relu5I0707 10:47:21.624089 3142 net.cpp:129] Top shape: 1 256 39 64 (638976)I0707 10:47:21.624092 3142 net.cpp:137] Memory required for data: 261374620I0707 10:47:21.624095 3142 layer_factory.hpp:77] Creating layer rpn_conv1I0707 10:47:21.624114 3142 net.cpp:84] Creating Layer rpn_conv1I0707 10:47:21.624120 3142 net.cpp:406] rpn_conv1 <- conv5I0707 10:47:21.624130 3142 net.cpp:380] rpn_conv1 -> rpn_conv1I0707 10:47:21.631552 3142 net.cpp:122] Setting up rpn_conv1I0707 10:47:21.631582 3142 net.cpp:129] Top shape: 1 256 39 64 (638976)I0707 10:47:21.631585 3142 net.cpp:137] Memory required for data: 263930524I0707 10:47:21.631597 3142 layer_factory.hpp:77] Creating layer rpn_relu1I0707 10:47:21.631608 3142 net.cpp:84] Creating Layer rpn_relu1I0707 10:47:21.631614 3142 net.cpp:406] rpn_relu1 <- rpn_conv1I0707 10:47:21.631623 3142 net.cpp:367] rpn_relu1 -> rpn_conv1 (in-place)I0707 10:47:21.632009 3142 net.cpp:122] Setting up rpn_relu1I0707 10:47:21.632019 3142 net.cpp:129] Top shape: 1 256 39 64 (638976)I0707 10:47:21.632024 3142 net.cpp:137] Memory required for data: 266486428I0707 10:47:21.632027 3142 layer_factory.hpp:77] Creating layer rpn_conv1_rpn_relu1_0_splitI0707 10:47:21.632035 3142 net.cpp:84] Creating Layer rpn_conv1_rpn_relu1_0_splitI0707 10:47:21.632040 3142 net.cpp:406] rpn_conv1_rpn_relu1_0_split <- rpn_conv1I0707 10:47:21.632048 3142 net.cpp:380] rpn_conv1_rpn_relu1_0_split -> rpn_conv1_rpn_relu1_0_split_0I0707 10:47:21.632058 3142 net.cpp:380] rpn_conv1_rpn_relu1_0_split -> rpn_conv1_rpn_relu1_0_split_1I0707 10:47:21.632105 3142 net.cpp:122] Setting up rpn_conv1_rpn_relu1_0_splitI0707 10:47:21.632112 3142 net.cpp:129] Top shape: 1 256 39 64 (638976)I0707 10:47:21.632118 3142 net.cpp:129] Top shape: 1 256 39 64 (638976)I0707 10:47:21.632122 3142 net.cpp:137] Memory required for data: 271598236I0707 10:47:21.632127 3142 layer_factory.hpp:77] Creating layer rpn_cls_scoreI0707 10:47:21.632139 3142 net.cpp:84] Creating Layer rpn_cls_scoreI0707 10:47:21.632143 3142 net.cpp:406] rpn_cls_score <- rpn_conv1_rpn_relu1_0_split_0I0707 10:47:21.632151 3142 net.cpp:380] rpn_cls_score -> rpn_cls_scoreI0707 10:47:21.633322 3142 net.cpp:122] Setting up rpn_cls_scoreI0707 10:47:21.633334 3142 net.cpp:129] Top shape: 1 18 39 64 (44928)I0707 10:47:21.633338 3142 net.cpp:137] Memory required for data: 271777948I0707 10:47:21.633345 3142 layer_factory.hpp:77] Creating layer rpn_cls_score_rpn_cls_score_0_splitI0707 10:47:21.633355 3142 net.cpp:84] Creating Layer rpn_cls_score_rpn_cls_score_0_splitI0707 10:47:21.633360 3142 net.cpp:406] rpn_cls_score_rpn_cls_score_0_split <- rpn_cls_scoreI0707 10:47:21.633368 3142 net.cpp:380] rpn_cls_score_rpn_cls_score_0_split -> rpn_cls_score_rpn_cls_score_0_split_0I0707 10:47:21.633378 3142 net.cpp:380] rpn_cls_score_rpn_cls_score_0_split -> rpn_cls_score_rpn_cls_score_0_split_1I0707 10:47:21.633417 3142 net.cpp:122] Setting up rpn_cls_score_rpn_cls_score_0_splitI0707 10:47:21.633424 3142 net.cpp:129] Top shape: 1 18 39 64 (44928)I0707 10:47:21.633426 3142 net.cpp:129] Top shape: 1 18 39 64 (44928)I0707 10:47:21.633429 3142 net.cpp:137] Memory required for data: 272137372I0707 10:47:21.633430 3142 layer_factory.hpp:77] Creating layer rpn_bbox_predI0707 10:47:21.633437 3142 net.cpp:84] Creating Layer rpn_bbox_predI0707 10:47:21.633441 3142 net.cpp:406] rpn_bbox_pred <- rpn_conv1_rpn_relu1_0_split_1I0707 10:47:21.633445 3142 net.cpp:380] rpn_bbox_pred -> rpn_bbox_predI0707 10:47:21.634851 3142 net.cpp:122] Setting up rpn_bbox_predI0707 10:47:21.634863 3142 net.cpp:129] Top shape: 1 36 39 64 (89856)I0707 10:47:21.634866 3142 net.cpp:137] Memory required for data: 272496796I0707 10:47:21.634891 3142 layer_factory.hpp:77] Creating layer rpn_cls_score_reshapeI0707 10:47:21.634905 3142 net.cpp:84] Creating Layer rpn_cls_score_reshapeI0707 10:47:21.634912 3142 net.cpp:406] rpn_cls_score_reshape <- rpn_cls_score_rpn_cls_score_0_split_0I0707 10:47:21.634922 3142 net.cpp:380] rpn_cls_score_reshape -> rpn_cls_score_reshapeI0707 10:47:21.634954 3142 net.cpp:122] Setting up rpn_cls_score_reshapeI0707 10:47:21.634959 3142 net.cpp:129] Top shape: 1 2 351 64 (44928)I0707 10:47:21.634964 3142 net.cpp:137] Memory required for data: 272676508I0707 10:47:21.634968 3142 layer_factory.hpp:77] Creating layer rpn-dataI0707 10:47:21.660670 3142 net.cpp:84] Creating Layer rpn-dataI0707 10:47:21.660693 3142 net.cpp:406] rpn-data <- rpn_cls_score_rpn_cls_score_0_split_1I0707 10:47:21.660701 3142 net.cpp:406] rpn-data <- gt_boxesI0707 10:47:21.660704 3142 net.cpp:406] rpn-data <- im_infoI0707 10:47:21.660707 3142 net.cpp:406] rpn-data <- data_input-data_0_split_1I0707 10:47:21.660712 3142 net.cpp:380] rpn-data -> rpn_labelsI0707 10:47:21.660722 3142 net.cpp:380] rpn-data -> rpn_bbox_targetsI0707 10:47:21.660732 3142 net.cpp:380] rpn-data -> rpn_bbox_inside_weightsI0707 10:47:21.660744 3142 net.cpp:380] rpn-data -> rpn_bbox_outside_weightsI0707 10:47:21.661968 3142 net.cpp:122] Setting up rpn-dataI0707 10:47:21.661985 3142 net.cpp:129] Top shape: 1 1 351 64 (22464)I0707 10:47:21.661988 3142 net.cpp:129] Top shape: 1 36 39 64 (89856)I0707 10:47:21.661991 3142 net.cpp:129] Top shape: 1 36 39 64 (89856)I0707 10:47:21.661993 3142 net.cpp:129] Top shape: 1 36 39 64 (89856)I0707 10:47:21.661995 3142 net.cpp:137] Memory required for data: 273844636I0707 10:47:21.661999 3142 layer_factory.hpp:77] Creating layer rpn_loss_clsI0707 10:47:21.662017 3142 net.cpp:84] Creating Layer rpn_loss_clsI0707 10:47:21.662022 3142 net.cpp:406] rpn_loss_cls <- rpn_cls_score_reshapeI0707 10:47:21.662026 3142 net.cpp:406] rpn_loss_cls <- rpn_labelsI0707 10:47:21.662032 3142 net.cpp:380] rpn_loss_cls -> rpn_cls_lossI0707 10:47:21.662044 3142 layer_factory.hpp:77] Creating layer rpn_loss_clsI0707 10:47:21.662364 3142 net.cpp:122] Setting up rpn_loss_clsI0707 10:47:21.662371 3142 net.cpp:129] Top shape: (1)I0707 10:47:21.662374 3142 net.cpp:132] with loss weight 1I0707 10:47:21.662381 3142 net.cpp:137] Memory required for data: 273844640I0707 10:47:21.662384 3142 layer_factory.hpp:77] Creating layer rpn_loss_bboxI0707 10:47:21.662395 3142 net.cpp:84] Creating Layer rpn_loss_bboxI0707 10:47:21.662401 3142 net.cpp:406] rpn_loss_bbox <- rpn_bbox_predI0707 10:47:21.662405 3142 net.cpp:406] rpn_loss_bbox <- rpn_bbox_targetsI0707 10:47:21.662410 3142 net.cpp:406] rpn_loss_bbox <- rpn_bbox_inside_weightsI0707 10:47:21.662415 3142 net.cpp:406] rpn_loss_bbox <- rpn_bbox_outside_weightsI0707 10:47:21.662421 3142 net.cpp:380] rpn_loss_bbox -> rpn_loss_bboxI0707 10:47:21.663342 3142 net.cpp:122] Setting up rpn_loss_bboxI0707 10:47:21.663352 3142 net.cpp:129] Top shape: (1)I0707 10:47:21.663353 3142 net.cpp:132] with loss weight 1I0707 10:47:21.663359 3142 net.cpp:137] Memory required for data: 273844644I0707 10:47:21.663363 3142 layer_factory.hpp:77] Creating layer dummy_roi_pool_conv5I0707 10:47:21.663373 3142 net.cpp:84] Creating Layer dummy_roi_pool_conv5I0707 10:47:21.663380 3142 net.cpp:380] dummy_roi_pool_conv5 -> dummy_roi_pool_conv5I0707 10:47:21.663417 3142 net.cpp:122] Setting up dummy_roi_pool_conv5I0707 10:47:21.663424 3142 net.cpp:129] Top shape: 1 9216 (9216)I0707 10:47:21.663426 3142 net.cpp:137] Memory required for data: 273881508I0707 10:47:21.663429 3142 layer_factory.hpp:77] Creating layer fc6I0707 10:47:21.663437 3142 net.cpp:84] Creating Layer fc6I0707 10:47:21.663439 3142 net.cpp:406] fc6 <- dummy_roi_pool_conv5I0707 10:47:21.663444 3142 net.cpp:380] fc6 -> fc6I0707 10:47:21.735376 3142 net.cpp:122] Setting up fc6I0707 10:47:21.735415 3142 net.cpp:129] Top shape: 1 4096 (4096)I0707 10:47:21.735419 3142 net.cpp:137] Memory required for data: 273897892I0707 10:47:21.735437 3142 layer_factory.hpp:77] Creating layer relu6I0707 10:47:21.735448 3142 net.cpp:84] Creating Layer relu6I0707 10:47:21.735456 3142 net.cpp:406] relu6 <- fc6I0707 10:47:21.735463 3142 net.cpp:367] relu6 -> fc6 (in-place)I0707 10:47:21.736017 3142 net.cpp:122] Setting up relu6I0707 10:47:21.736039 3142 net.cpp:129] Top shape: 1 4096 (4096)I0707 10:47:21.736042 3142 net.cpp:137] Memory required for data: 273914276I0707 10:47:21.736044 3142 layer_factory.hpp:77] Creating layer fc7I0707 10:47:21.736052 3142 net.cpp:84] Creating Layer fc7I0707 10:47:21.736054 3142 net.cpp:406] fc7 <- fc6I0707 10:47:21.736058 3142 net.cpp:380] fc7 -> fc7I0707 10:47:21.766991 3142 net.cpp:122] Setting up fc7I0707 10:47:21.767033 3142 net.cpp:129] Top shape: 1 4096 (4096)I0707 10:47:21.767038 3142 net.cpp:137] Memory required for data: 273930660I0707 10:47:21.767050 3142 layer_factory.hpp:77] Creating layer silence_fc7I0707 10:47:21.767062 3142 net.cpp:84] Creating Layer silence_fc7I0707 10:47:21.767067 3142 net.cpp:406] silence_fc7 <- fc7I0707 10:47:21.767074 3142 net.cpp:122] Setting up silence_fc7I0707 10:47:21.767076 3142 net.cpp:137] Memory required for data: 273930660I0707 10:47:21.767079 3142 net.cpp:200] silence_fc7 does not need backward computation.I0707 10:47:21.767088 3142 net.cpp:200] fc7 does not need backward computation.I0707 10:47:21.767092 3142 net.cpp:200] relu6 does not need backward computation.I0707 10:47:21.767097 3142 net.cpp:200] fc6 does not need backward computation.I0707 10:47:21.767102 3142 net.cpp:200] dummy_roi_pool_conv5 does not need backward computation.I0707 10:47:21.767105 3142 net.cpp:198] rpn_loss_bbox needs backward computation.I0707 10:47:21.767110 3142 net.cpp:198] rpn_loss_cls needs backward computation.I0707 10:47:21.767114 3142 net.cpp:198] rpn-data needs backward computation.I0707 10:47:21.767122 3142 net.cpp:198] rpn_cls_score_reshape needs backward computation.I0707 10:47:21.767144 3142 net.cpp:198] rpn_bbox_pred needs backward computation.I0707 10:47:21.767163 3142 net.cpp:198] rpn_cls_score_rpn_cls_score_0_split needs backward computation.I0707 10:47:21.767176 3142 net.cpp:198] rpn_cls_score needs backward computation.I0707 10:47:21.767191 3142 net.cpp:198] rpn_conv1_rpn_relu1_0_split needs backward computation.I0707 10:47:21.767199 3142 net.cpp:198] rpn_relu1 needs backward computation.I0707 10:47:21.767211 3142 net.cpp:198] rpn_conv1 needs backward computation.I0707 10:47:21.767216 3142 net.cpp:198] relu5 needs backward computation.I0707 10:47:21.767220 3142 net.cpp:198] conv5 needs backward computation.I0707 10:47:21.767225 3142 net.cpp:198] relu4 needs backward computation.I0707 10:47:21.767232 3142 net.cpp:198] conv4 needs backward computation.I0707 10:47:21.767237 3142 net.cpp:198] relu3 needs backward computation.I0707 10:47:21.767241 3142 net.cpp:198] conv3 needs backward computation.I0707 10:47:21.767244 3142 net.cpp:198] pool2 needs backward computation.I0707 10:47:21.767251 3142 net.cpp:198] norm2 needs backward computation.I0707 10:47:21.767254 3142 net.cpp:198] relu2 needs backward computation.I0707 10:47:21.767257 3142 net.cpp:198] conv2 needs backward computation.I0707 10:47:21.767261 3142 net.cpp:198] pool1 needs backward computation.I0707 10:47:21.767264 3142 net.cpp:198] norm1 needs backward computation.I0707 10:47:21.767268 3142 net.cpp:198] relu1 needs backward computation.I0707 10:47:21.767283 3142 net.cpp:198] conv1 needs backward computation.I0707 10:47:21.767297 3142 net.cpp:200] data_input-data_0_split does not need backward computation.I0707 10:47:21.767303 3142 net.cpp:200] input-data does not need backward computation.I0707 10:47:21.767307 3142 net.cpp:242] This network produces output rpn_cls_lossI0707 10:47:21.767313 3142 net.cpp:242] This network produces output rpn_loss_bboxI0707 10:47:21.767336 3142 net.cpp:255] Network initialization done.I0707 10:47:21.767424 3142 solver.cpp:56] Solver scaffolding done.Loading pretrained model weights from data/imagenet_models/ZF.v2.caffemodelI0707 10:47:25.234427 3142 upgrade_proto.cpp:67] Attempting to upgrade input file specified using deprecated input fields: data/imagenet_models/ZF.v2.caffemodelI0707 10:47:25.234450 3142 upgrade_proto.cpp:70] Successfully upgraded file specified using deprecated input fields.W0707 10:47:25.234455 3142 upgrade_proto.cpp:72] Note that future Caffe releases will only support input layers and not input fields.I0707 10:47:25.239126 3142 net.cpp:744] Ignoring source layer pool5_spm6I0707 10:47:25.239156 3142 net.cpp:744] Ignoring source layer pool5_spm6_flattenI0707 10:47:25.284266 3142 net.cpp:744] Ignoring source layer drop6I0707 10:47:25.302134 3142 net.cpp:744] Ignoring source layer relu7I0707 10:47:25.302163 3142 net.cpp:744] Ignoring source layer drop7I0707 10:47:25.302166 3142 net.cpp:744] Ignoring source layer fc8I0707 10:47:25.302170 3142 net.cpp:744] Ignoring source layer probProcess Process-1:Traceback (most recent call last): File "/usr/lib/python2.7/multiprocessing/process.py", line 258, in _bootstrap self.run() File "/usr/lib/python2.7/multiprocessing/process.py", line 114, in run self._target(*self._args, **self._kwargs) File "./tools/train_faster_rcnn_alt_opt.py", line 129, in train_rpn max_iters=max_iters) File "/home/pikachu/dev/py-faster-rcnn/tools/../lib/fast_rcnn/train.py", line 157, in train_net pretrained_model=pretrained_model) File "/home/pikachu/dev/py-faster-rcnn/tools/../lib/fast_rcnn/train.py", line 51, in __init__ pb2.text_format.Merge(f.read(), self.solver_param)AttributeError: 'module' object has no attribute 'text_format'
阅读全文
0 0
- AttributeError: 'module' object has no attribute 'text_format'
- AttributeError: 'module' object has no attribute 'text_format'
- AttributeError: 'module' object has no attribute 'text_format'
- AttributeError: 'module' object has no attribute 'text_format'
- AttributeError: 'module' object has no attribute 'text_format'
- AttributeError: 'module' object has no attribute 'getpass'
- AttributeError: 'module' object has no attribute 'Serial'
- AttributeError: 'module' object has no attribute(转)
- AttributeError: 'module' object has no attribute 'randint'
- AttributeError: 'module' object has no attribute 'HAVE_DECL_MPZ_POWM_SEC'
- AttributeError: 'module' object has no attribute 'Serial'
- AttributeError: 'module' object has no attribute 'LabelMap'
- AttributeError: 'module' object has no attribute 'XXX'
- AttributeError: 'module' object has no attribute 'urlopen'
- AttributeError:'module' object has no attribute 'classify'
- AttributeError: ‘module’ object has no attribute’xxx’
- AttributeError: ‘module’ object has no attribute’ 问题
- AttributeError: 'module' object has no attribute 'VideoWriter_fourcc'
- 401. Binary Watch的C++解法
- 利用pandas进行数据分析之二:DataFrame与Series数据结构对比
- @property和@synthesize
- ZMQ(java)-编译的心酸历程
- 事物注解方式: @Transactional
- AttributeError: 'module' object has no attribute 'text_format'
- 面经
- jQuery源码分析-----pushStack
- LeetCode-string-Longest Substring Without Repeating Characters
- linux centos FTP服务器搭建vsftpd配置
- Android实现透明状态栏方法以及改变状态栏文字颜色
- 关于使用Maven管理引入Oracle驱动报错
- 关于android 消息提醒,在网上找到这个项目在eslipse中使用ValueAnimator报错
- 文章标题