con not get .ckpt file after training

[longgang123]

command use this ./experiments/scripts/faster_rcnn_end2end.sh GPU 0 VGG16 pascal_voc while end training it shows like this below: can anybody know the reason? speed: 0.205s / iter Wrote snapshot to: /home/alex/software/Faster-RCNN_TF/output/faster_rcnn_end2end/voc_2007_trainval/VGGnet_fast_rcnn_iter_700.ckpt done solving

real 7m5.121s user 5m46.348s sys 0m46.364s

• set +x
• python ./tools/test_net.py --device GPU --device_id 0 --weights /home/alex/software/Faster-RCNN_TF/output/faster_rcnn_end2end/voc_2007_trainval/VGGnet_fast_rcnn_iter_700.ckpt --imdb voc_2007_test --cfg experiments/cfgs/faster_rcnn_end2end.yml --network VGGnet_test voc_2007_train voc_2007_val voc_2007_trainval voc_2007_test kitti_train kitti_val kitti_trainval kitti_test nthu_71 nthu_370 Called with args: Namespace(cfg_file='experiments/cfgs/faster_rcnn_end2end.yml', comp_mode=False, device='GPU', device_id=0, imdb_name='voc_2007_test', model='/home/alex/software/Faster-RCNN_TF/output/faster_rcnn_end2end/voc_2007_trainval/VGGnet_fast_rcnn_iter_700.ckpt', network_name='VGGnet_test', prototxt=None, wait=True) Using config: {'DATA_DIR': '/home/alex/software/Faster-RCNN_TF/data', 'DEDUP_BOXES': 0.0625, 'EPS': 1e-14, 'EXP_DIR': 'faster_rcnn_end2end', 'GPU_ID': 0, 'IS_MULTISCALE': False, 'MATLAB': 'matlab', 'MODELS_DIR': '/home/alex/software/Faster-RCNN_TF/models/pascal_voc', 'PIXEL_MEANS': array([[[ 102.9801, 115.9465, 122.7717]]]), 'RNG_SEED': 3, 'ROOT_DIR': '/home/alex/software/Faster-RCNN_TF', 'TEST': {'BBOX_REG': True, 'DEBUG_TIMELINE': False, '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': True, 'BBOX_REG': True, 'BBOX_THRESH': 0.5, 'BG_THRESH_HI': 0.5, 'BG_THRESH_LO': 0.0, 'DEBUG_TIMELINE': False, 'DISPLAY': 10, 'FG_FRACTION': 0.25, 'FG_THRESH': 0.5, 'GAMMA': 0.1, 'HAS_RPN': True, 'IMS_PER_BATCH': 1, 'LEARNING_RATE': 0.001, 'MAX_SIZE': 1000, 'MOMENTUM': 0.9, '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': '', 'SNAPSHOT_ITERS': 5000, 'SNAPSHOT_PREFIX': 'VGGnet_fast_rcnn', 'STEPSIZE': 50000, 'USE_FLIPPED': True, 'USE_PREFETCH': False}, 'USE_GPU_NMS': True} Waiting for /home/alex/software/Faster-RCNN_TF/output/faster_rcnn_end2end/voc_2007_trainval/VGGnet_fast_rcnn_iter_700.ckpt to exist... Waiting for /home/alex/software/Faster-RCNN_TF/output/faster_rcnn_end2end/voc_2007_trainval/VGGnet_fast_rcnn_iter_700.ckpt to exist... Waiting for /home/alex/software/Faster-RCNN_TF/output/faster_rcnn_end2end/voc_2007_trainval/VGGnet_fast_rcnn_iter_700.ckpt to exist... I waiting for a long time still there no .ckpt file in the output folder

[zzzzzz0407]

I have the same issue! And i just find the ckpt in appointed dir!

[shaohuifangit]

I have the same issue! How did you solve it?

[zzzzzz0407]

You have to specify write_version=tf.train.SaverDef.V1 in /lib/fast_rcnn/train.py, if you're using tensorflow version lower than 1.0, to get .ckpt file. just like this: saver = tf.train.Saver(max_to_keep=100, write_version=tf.train.SaverDef.V1)

[shaohuifangit]

But my tensorflow version is 1.3.

[IMAUZS]

i'm also meeting the same problem.i used tensorflow-1.1,tensorflow-1.2,tensroflow-1.3.there 's still the same problem.after i run train,there can not get the cpkt file . when i modified the train_net.py to saver = tf.train.Saver(max_to_keep=100, write_version=tf.train.SaverDef.V1),there shows a error that "AttributeError: 'module' object has no attribute 'Save'".i don't know why it happens. there's anyone gives more infos to solve this problem? thank you.

[YCIrving]

#79 can solve this problem though you can just comment the loop in test_net.py like #241