fendouai / facerank Goto Github PK

/usr/bin/python3.5 /home/jacli/FaceRank/run_model.py
(?, 128, 128, 24)
(?, 64, 64, 24)
(?, 64, 64, 96)
(?, 32, 32, 96)
WARNING:tensorflow:From /home/jacli/FaceRank/run_model.py:107: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version.
Instructions for updating:

Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.

See tf.nn.softmax_cross_entropy_with_logits_v2.

[]
0
(0,)
Traceback (most recent call last):
File "/home/jacli/FaceRank/run_model.py", line 147, in
pred_result_test=sess.run(pred_result, feed_dict={x: batch_xs,keep_prob: 1.})
File "/home/jacli/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 929, in run
run_metadata_ptr)
File "/home/jacli/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1128, in _run
str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (0,) for Tensor 'Placeholder:0', which has shape '(?, 128, 128, 3)'

Process finished with exit code 1

不知道将这个模型改为回归模型是否可行，评分改成连续的。

E:\ProgramData\Anaconda3\python.exe D:/360c/FaceRank-master/train_model.py
(?, 128, 128, 24)
(?, 64, 64, 24)
(?, 64, 64, 96)
(?, 32, 32, 96)
2017-09-08 10:54:08.382260: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-09-08 10:54:08.382260: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
['2', '3', '4']
3
count: 1
<class 'str'>

--sco---
Traceback (most recent call last):
File "D:/360c/FaceRank-master/train_model.py", line 148, in
batch_y[int(score) - 1] = 1
ValueError: invalid literal for int() with base 10: ''

Process finished with exit code 1

E:\ProgramData\Anaconda3\python.exe D:/360c/FaceRank-master/run_model.py
(?, 128, 128, 24)
(?, 64, 64, 24)
(?, 64, 64, 96)
(?, 32, 32, 96)
2017-09-08 10:56:33.912298: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-09-08 10:56:33.912298: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
Traceback (most recent call last):
File "D:/360c/FaceRank-master/run_model.py", line 144, in
pred_result_test=sess.run(pred_result, feed_dict={x: batch_xs,keep_prob: 1.})
[]
File "E:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 895, in run
0
run_metadata_ptr)
(0,)
File "E:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1100, in _run
% (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (0,) for Tensor 'Placeholder:0', which has shape '(?, 128, 128, 3)'

Process finished with exit code 1

哈喽，大佬好。
请教下数据集的标签是怎么来的，据我所知华工给的数据是很多人的评分，15，也不是110啊，怎么转成1~10的啊？
多谢

OSError: [Errno 12] Cannot allocate memory.

27 def train_data_generator():
28 image_data_list = []
29 label = []
30 progress = 0
31 pos_file_list = os.listdir(pos_image_path)
32 neg_file_list = os.listdir(neg_image_path)
33 while True:
34 for i in range(sample_num):
35 url = os.path.join(pos_image_path +'/' + pos_file_list[i])
36 image = load_img(url, target_size=(128, 128))
37 image_data_list.append(img_to_array(image))
38 label.append(1)
39 image.close()
40 progress = progress + 1
41 url = os.path.join(neg_image_path + '/' + neg_file_list[i])
42 image = load_img(url, target_size=(128, 128))
43 image_data_list.append(img_to_array(image))
44 label.append(0)
45 image.close()
46 progress = progress + 1
47 if progress == fit_gen_batch_size:
48 img_data = np.array(image_data_list)
49 img_data = img_data.astype('float32')
50 img_data /= 255
51 #print("generator image_data=",len(img_data),"label=",len(label))
52 yield img_data, label
53 label.clear()
54 img_data[:]=0
55 image_data_list.clear()
56 progress = 0
57 gc.collect()

因为之前定义了batch_size大小为10，所以在128行for batch_id in range(0, 12），改成图片的数量/10就行了，并不是直接写图片数量

2018-03-13 15:20:04.122000: I C:\tf_jenkins\workspace\rel-win\M\windows-gpu\PY\3
6\tensorflow\core\common_runtime\bfc_allocator.cc:680] Stats:
Limit: 1631711232
InUse: 1229069056
MaxInUse: 1631711232
NumAllocs: 51
MaxAllocSize: 422898176

2018-03-13 15:20:04.122000: W C:\tf_jenkins\workspace\rel-win\M\windows-gpu\PY\3
6\tensorflow\core\common_runtime\bfc_allocator.cc:279] _______________________
**************************************************************************x
2018-03-13 15:20:04.123000: W C:\tf_jenkins\workspace\rel-win\M\windows-gpu\PY\3
6\tensorflow\core\framework\op_kernel.cc:1202] OP_REQUIRES failed at assign_op.h
:111 : Resource exhausted: OOM when allocating tensor with shape[98304,1024] and
type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_b
fc
Traceback (most recent call last):
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\clie
nt\session.py", line 1361, in _do_call
return fn(*args)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\clie
nt\session.py", line 1340, in _run_fn
target_list, status, run_metadata)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\fram
ework\errors_impl.py", line 516, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocat
ing tensor with shape[98304,1024] and type float on /job:localhost/replica:0/tas
k:0/device:GPU:0 by allocator GPU_0_bfc
[[Node: save/Assign_7 = Assign[T=DT_FLOAT, _class=["loc:@Variable_2"],
use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/
device:GPU:0"](Variable_2/Adam, save/RestoreV2/_23)]]
Hint: If you want to see a list of allocated tensors when OOM happens, add repor
t_tensor_allocations_upon_oom to RunOptions for current allocation info.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "run_model.py", line 117, in
saver.restore(sess, "./model/model.ckpt")
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\trai
ning\saver.py", line 1755, in restore
{self.saver_def.filename_tensor_name: save_path})
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\clie
nt\session.py", line 905, in run
run_metadata_ptr)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\clie
nt\session.py", line 1137, in _run
feed_dict_tensor, options, run_metadata)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\clie
nt\session.py", line 1355, in _do_run
options, run_metadata)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\clie
nt\session.py", line 1374, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocat
ing tensor with shape[98304,1024] and type float on /job:localhost/replica:0/tas
k:0/device:GPU:0 by allocator GPU_0_bfc
[[Node: save/Assign_7 = Assign[T=DT_FLOAT, _class=["loc:@Variable_2"],
use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/
device:GPU:0"](Variable_2/Adam, save/RestoreV2/_23)]]
Hint: If you want to see a list of allocated tensors when OOM happens, add repor
t_tensor_allocations_upon_oom to RunOptions for current allocation info.

Caused by op 'save/Assign_7', defined at:
File "run_model.py", line 113, in
saver=tf.train.Saver()
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\trai
ning\saver.py", line 1293, in init
self.build()
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\trai
ning\saver.py", line 1302, in build
self._build(self._filename, build_save=True, build_restore=True)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\trai
ning\saver.py", line 1339, in _build
build_save=build_save, build_restore=build_restore)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\trai
ning\saver.py", line 796, in _build_internal
restore_sequentially, reshape)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\trai
ning\saver.py", line 471, in _AddRestoreOps
assign_ops.append(saveable.restore(saveable_tensors, shapes))
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\trai
ning\saver.py", line 161, in restore
self.op.get_shape().is_fully_defined())
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\ops
state_ops.py", line 280, in assign
validate_shape=validate_shape)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\ops
gen_state_ops.py", line 61, in assign
use_locking=use_locking, name=name)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\fram
ework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\fram
ework\ops.py", line 3271, in create_op
op_def=op_def)
File "D:\Program Files (x86)\anaconda\lib\site-packages\tensorflow\python\fram
ework\ops.py", line 1650, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-
access

ResourceExhaustedError (see above for traceback): OOM when allocating tensor wit
h shape[98304,1024] and type float on /job:localhost/replica:0/task:0/device:GPU
:0 by allocator GPU_0_bfc
[[Node: save/Assign_7 = Assign[T=DT_FLOAT, _class=["loc:@Variable_2"],
use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/
device:GPU:0"](Variable_2/Adam, save/RestoreV2/_23)]]
Hint: If you want to see a list of allocated tensors when OOM happens, add repor
t_tensor_allocations_upon_oom to RunOptions for current allocation info.

我用的是华工实验室的数据，另外自己加入了100张平分为4、5的图像，可是无论什么照片进去，出来的结果评分都是2分（满分5分），所以是不是模型欠拟合的问题？