How to test the pretrained model directly？
chuanzhidong opened this issue · 3 comments
I downloaded the "release-no-aug" folder and there were three subfolders: "desc", "kp" and "ori".
I created a new folder under tf-lift folder, named "logs".
Under "logs" folder I created a subfolder named "test".
I copyed the three folders "desc", "kp" and "ori" in to the "tf-lift/logs/test/".
I put the test image named "image1.jpg" in "tf-lift/"
and run the command in tf-lift:
python main.py --task=test --subtask=kp --logdir=logs/test --test_img_file=image1.jpg --test_out_file=image1_kp.txt
It gives me an error:
/home/czdong/anaconda3/lib/python3.6/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as _register_converters
User and hostname: czdong@czdong
2018-11-05 13:50:07.407175: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2018-11-05 13:50:07.529312: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:897] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-11-05 13:50:07.529890: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1405] Found device 0 with properties:
name: GeForce GTX 1080 major: 6 minor: 1 memoryClockRate(GHz): 1.7715
pciBusID: 0000:08:00.0
totalMemory: 7.93GiB freeMemory: 7.30GiB
2018-11-05 13:50:07.529910: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1484] Adding visible gpu devices: 0
2018-11-05 13:50:07.708551: I tensorflow/core/common_runtime/gpu/gpu_device.cc:965] Device interconnect StreamExecutor with strength 1 edge matrix:
2018-11-05 13:50:07.708587: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0
2018-11-05 13:50:07.708592: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] 0: N
2018-11-05 13:50:07.708786: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1097] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 7043 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080, pci bus id: 0000:08:00.0, compute capability: 6.1)
[kp] Loaded input normalizers for testing
WARNING:tensorflow:From /home/czdong/Desktop/tf-lift/layers.py:353: calling reduce_max (from tensorflow.python.ops.math_ops) with keep_dims is deprecated and will be removed in a future version.
Instructions for updating:
keep_dims is deprecated, use keepdims instead
WARNING:tensorflow:From /home/czdong/Desktop/tf-lift/layers.py:368: calling reduce_sum (from tensorflow.python.ops.math_ops) with keep_dims is deprecated and will be removed in a future version.
Instructions for updating:
keep_dims is deprecated, use keepdims instead
Variables: name (type shape) [size]
network/lift/kp/conv-ghh-1/weights:0 (float32_ref 25x25x1x16) [10000, bytes: 40000]
network/lift/kp/conv-ghh-1/biases:0 (float32_ref 16) [16, bytes: 64]
network/lift/desc/conv-act-pool-norm-1/weights:0 (float32_ref 7x7x1x32) [1568, bytes: 6272]
network/lift/desc/conv-act-pool-norm-1/biases:0 (float32_ref 32) [32, bytes: 128]
network/lift/desc/conv-act-pool-norm-2/weights:0 (float32_ref 6x6x32x64) [73728, bytes: 294912]
network/lift/desc/conv-act-pool-norm-2/biases:0 (float32_ref 64) [64, bytes: 256]
network/lift/desc/conv-act-pool-3/weights:0 (float32_ref 5x5x64x128) [204800, bytes: 819200]
network/lift/desc/conv-act-pool-3/biases:0 (float32_ref 128) [128, bytes: 512]
Total size of variables: 290336
Total bytes of variables: 1161344
Traceback (most recent call last):
File "main.py", line 98, in
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/home/czdong/anaconda3/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "main.py", line 67, in main
task = Tester(config, rng)
File "/home/czdong/Desktop/tf-lift/tester.py", line 88, in init
self.saver[_key] = tf.train.Saver(self.network.allparams[_key])
File "/home/czdong/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1281, in init
self.build()
File "/home/czdong/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1293, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/home/czdong/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1330, in _build
build_save=build_save, build_restore=build_restore)
File "/home/czdong/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 756, in _build_internal
saveables = self._ValidateAndSliceInputs(names_to_saveables)
File "/home/czdong/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 656, in _ValidateAndSliceInputs
names_to_saveables = BaseSaverBuilder.OpListToDict(names_to_saveables)
File "/home/czdong/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 563, in OpListToDict
name)
ValueError: At least two variables have the same name: network/lift/kp/conv-ghh-1/biases
my cuda is
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2017 NVIDIA Corporation
Built on Fri_Sep__1_21:08:03_CDT_2017
Cuda compilation tools, release 9.0, V9.0.176
python3.6
opencv3.4.3
Is there anyone know how to solve this problem? Thank you very much.
This seems to be Tensorflow version issue. Please see other closed issues...
Sir，I have met the same bug with you !Have you solve it?If do,can you tell me how to fix it ?Thank you!
Please downgrade to TF 1.4, and please do not necro threads