Я попытался tf.reset_default_graph (), но все равно ошибка приходит. Я столкнулся с десятками ошибок из релизной версии. Почему в тензорном потоке много ошибок? Если проблема с версией, я надеюсь предоставить информацию о версии тоже. Есть много открытых источников на inte rnet, но они бесполезны из-за ошибок. Я собрал около десяти проектов в inte rnet только до тех пор, пока не обнаружил, что программа работает нормально, но все ошибки в результате. Наконец, при попытке исправить ошибки.
Версии зависимостей:
absl-py 0.9.0 pypi_0 pypi
alabaster 0.7.12 pypi_0 pypi
astor 0.8.1 pypi_0 pypi
astroid 2.3.3 pypi_0 pypi
atomicwrites 1.3.0 pypi_0 pypi
attrs 19.3.0 pypi_0 pypi
autopep8 1.5.1 pypi_0 pypi
babel 2.8.0 pypi_0 pypi
backcall 0.1.0 pypi_0 pypi
bcrypt 3.1.7 pypi_0 pypi
blas 1.0 mkl
bleach 1.5.0 pypi_0 pypi
cachetools 4.1.0 pypi_0 pypi
certifi 2020.4.5.1 py36h9f0ad1d_0 conda-forge
cffi 1.14.0 py36h7a1dbc1_0
chardet 3.0.4 pypi_0 pypi
cloudpickle 1.3.0 pypi_0 pypi
colorama 0.4.3 pypi_0 pypi
cryptography 2.9 pypi_0 pypi
cudatoolkit 10.0.130 0
cycler 0.10.0 pypi_0 pypi
decorator 4.4.2 pypi_0 pypi
defusedxml 0.6.0 pypi_0 pypi
diff-match-patch 20181111 pypi_0 pypi
dill 0.3.1.1 pypi_0 pypi
docutils 0.16 pypi_0 pypi
entrypoints 0.3 pypi_0 pypi
enum34 1.1.10 pypi_0 pypi
ffmpeg 1.4 pypi_0 pypi
flake8 3.7.9 pypi_0 pypi
freetype 2.9.1 ha9979f8_1
gast 0.2.2 pypi_0 pypi
google-auth 1.14.0 pypi_0 pypi
google-auth-oauthlib 0.4.1 pypi_0 pypi
google-pasta 0.2.0 pypi_0 pypi
grpcio 1.28.1 pypi_0 pypi
h5py 2.10.0 pypi_0 pypi
helpdev 0.6.10 pypi_0 pypi
hickle 3.4.6 pypi_0 pypi
html5lib 0.9999999 pypi_0 pypi
icc_rt 2019.0.0 h0cc432a_1
idna 2.9 pypi_0 pypi
imageio 2.8.0 pypi_0 pypi
imagesize 1.2.0 pypi_0 pypi
importlib-metadata 1.6.0 pypi_0 pypi
intel-openmp 2020.0 166
intervaltree 3.0.2 pypi_0 pypi
ipykernel 5.2.1 pypi_0 pypi
ipython 7.13.0 pypi_0 pypi
ipython-genutils 0.2.0 pypi_0 pypi
isort 4.3.21 pypi_0 pypi
jedi 0.15.2 pypi_0 pypi
jinja2 2.11.2 pypi_0 pypi
joblib 0.14.1 pypi_0 pypi
jpeg 9b hb83a4c4_2
jsonschema 3.2.0 pypi_0 pypi
jupyter-client 6.1.3 pypi_0 pypi
jupyter-core 4.6.3 pypi_0 pypi
keras 2.3.1 pypi_0 pypi
keras-applications 1.0.8 pypi_0 pypi
keras-preprocessing 1.1.0 pypi_0 pypi
keyring 21.2.0 pypi_0 pypi
kiwisolver 1.2.0 pypi_0 pypi
lazy-object-proxy 1.4.3 pypi_0 pypi
libgpuarray 0.7.6 hfa6e2cd_0
libpng 1.6.37 h2a8f88b_0
libpython 2.1 py36_0
libtiff 4.1.0 h56a325e_0
m2w64-binutils 2.25.1 5
m2w64-bzip2 1.0.6 6
m2w64-crt-git 5.0.0.4636.2595836 2
m2w64-gcc 5.3.0 6
m2w64-gcc-ada 5.3.0 6
m2w64-gcc-fortran 5.3.0 6
m2w64-gcc-libgfortran 5.3.0 6
m2w64-gcc-libs 5.3.0 7
m2w64-gcc-libs-core 5.3.0 7
m2w64-gcc-objc 5.3.0 6
m2w64-gmp 6.1.0 2
m2w64-headers-git 5.0.0.4636.c0ad18a 2
m2w64-isl 0.16.1 2
m2w64-libiconv 1.14 6
m2w64-libmangle-git 5.0.0.4509.2e5a9a2 2
m2w64-libwinpthread-git 5.0.0.4634.697f757 2
m2w64-make 4.1.2351.a80a8b8 2
m2w64-mpc 1.0.3 3
m2w64-mpfr 3.1.4 4
m2w64-pkg-config 0.29.1 2
m2w64-toolchain 5.3.0 7
m2w64-tools-git 5.0.0.4592.90b8472 2
m2w64-windows-default-manifest 6.4 3
m2w64-winpthreads-git 5.0.0.4634.697f757 2
m2w64-zlib 1.2.8 10
mako 1.1.2 py_0
markdown 3.2.1 pypi_0 pypi
markupsafe 1.1.1 py36he774522_0
matplotlib 3.2.1 pypi_0 pypi
mccabe 0.6.1 pypi_0 pypi
mistune 0.8.4 pypi_0 pypi
mkl 2020.0 166
mkl-service 2.3.0 py36hb782905_0
mkl_fft 1.0.15 py36h14836fe_0
mkl_random 1.1.0 py36h675688f_0
msys2-conda-epoch 20160418 1
nbconvert 5.6.1 pypi_0 pypi
nbformat 5.0.5 pypi_0 pypi
networkx 2.4 pypi_0 pypi
ninja 1.9.0 py36h74a9793_0
notebook 6.0.3 pypi_0 pypi
numpy 1.18.2 pypi_0 pypi
numpy-base 1.18.1 py36hc3f5095_1
numpydoc 0.9.2 pypi_0 pypi
oauthlib 3.1.0 pypi_0 pypi
olefile 0.46 py36_0
opencv-python 4.2.0.34 pypi_0 pypi
opt-einsum 3.2.1 pypi_0 pypi
packaging 20.3 pypi_0 pypi
pandas 1.0.3 pypi_0 pypi
pandocfilters 1.4.2 pypi_0 pypi
paramiko 2.7.1 pypi_0 pypi
parso 0.5.2 pypi_0 pypi
pathtools 0.1.2 pypi_0 pypi
pexpect 4.8.0 pypi_0 pypi
pickle5 0.0.9 py36hfa6e2cd_0 conda-forge
pickleshare 0.7.5 pypi_0 pypi
pillow 7.0.0 pypi_0 pypi
pip 20.0.2 py36_1
pluggy 0.13.1 pypi_0 pypi
prometheus-client 0.7.1 pypi_0 pypi
prompt-toolkit 3.0.5 pypi_0 pypi
protobuf 3.11.3 pypi_0 pypi
psutil 5.7.0 pypi_0 pypi
ptyprocess 0.6.0 pypi_0 pypi
pyarrow 0.16.0 pypi_0 pypi
pyasn1 0.4.8 pypi_0 pypi
pyasn1-modules 0.2.8 pypi_0 pypi
pycodestyle 2.5.0 pypi_0 pypi
pycparser 2.20 py_0
pydocstyle 5.0.2 pypi_0 pypi
pyflakes 2.2.0 pypi_0 pypi
pygments 2.6.1 pypi_0 pypi
pygpu 0.7.6 py36h452e1ab_0
pylint 2.4.4 pypi_0 pypi
pynacl 1.3.0 pypi_0 pypi
pyparsing 2.4.7 pypi_0 pypi
pyqt5 5.12.3 pypi_0 pypi
pyqt5-sip 12.7.2 pypi_0 pypi
pyqtwebengine 5.12.1 pypi_0 pypi
pyrsistent 0.16.0 pypi_0 pypi
python 3.6.10 h9f7ef89_1
python-dateutil 2.8.1 pypi_0 pypi
python-jsonrpc-server 0.3.4 pypi_0 pypi
python-language-server 0.31.9 pypi_0 pypi
python_abi 3.6 1_cp36m conda-forge
pytorch 1.2.0 py3.6_cuda100_cudnn7_1 pytorch
pytz 2019.3 pypi_0 pypi
pywavelets 1.1.1 pypi_0 pypi
pywin32 227 pypi_0 pypi
pywin32-ctypes 0.2.0 pypi_0 pypi
pywinpty 0.5.7 pypi_0 pypi
pyyaml 5.3.1 pypi_0 pypi
pyzmq 19.0.0 pypi_0 pypi
qdarkstyle 2.8.1 pypi_0 pypi
qtawesome 0.7.1 pypi_0 pypi
qtconsole 4.7.3 pypi_0 pypi
qtpy 1.9.0 pypi_0 pypi
requests 2.23.0 pypi_0 pypi
requests-oauthlib 1.3.0 pypi_0 pypi
rope 0.16.0 pypi_0 pypi
rsa 4.0 pypi_0 pypi
scikit-image 0.16.2 pypi_0 pypi
scikit-learn 0.22.2.post1 pypi_0 pypi
scipy 1.1.0 pypi_0 pypi
send2trash 1.5.0 pypi_0 pypi
setuptools 46.1.3 py36_0
six 1.14.0 py36_0
snowballstemmer 2.0.0 pypi_0 pypi
sortedcontainers 2.1.0 pypi_0 pypi
sphinx 3.0.1 pypi_0 pypi
sphinxcontrib-applehelp 1.0.2 pypi_0 pypi
sphinxcontrib-devhelp 1.0.2 pypi_0 pypi
sphinxcontrib-htmlhelp 1.0.3 pypi_0 pypi
sphinxcontrib-jsmath 1.0.1 pypi_0 pypi
sphinxcontrib-qthelp 1.0.3 pypi_0 pypi
sphinxcontrib-serializinghtml 1.1.4 pypi_0 pypi
spyder 4.1.2 pypi_0 pypi
spyder-kernels 1.9.0 pypi_0 pypi
sqlite 3.31.1 he774522_0
tensorboard 1.15.0 pypi_0 pypi
tensorflow-estimator 1.15.1 pypi_0 pypi
tensorflow-gpu 2.0.0 pypi_0 pypi
tensorflow-gpu-estimator 2.1.0 pypi_0 pypi
tensorflow-tensorboard 0.4.0 pypi_0 pypi
termcolor 1.1.0 pypi_0 pypi
terminado 0.8.3 pypi_0 pypi
testpath 0.4.4 pypi_0 pypi
theano 1.0.4 py36_0
tk 8.6.8 hfa6e2cd_0
torchvision 0.4.0 py36_cu100 pytorch
tornado 6.0.4 pypi_0 pypi
tqdm 4.45.0 pypi_0 pypi
traitlets 4.3.3 pypi_0 pypi
typed-ast 1.4.1 pypi_0 pypi
urllib3 1.25.8 pypi_0 pypi
vc 14.1 h0510ff6_4
vs2015_runtime 14.16.27012 hf0eaf9b_1
watchdog 0.10.2 pypi_0 pypi
wcwidth 0.1.9 pypi_0 pypi
webencodings 0.5.1 pypi_0 pypi
werkzeug 1.0.1 pypi_0 pypi
wheel 0.34.2 py36_0
wincertstore 0.2 py36h7fe50ca_0
wrapt 1.11.2 pypi_0 pypi
xz 5.2.5 h62dcd97_0
yapf 0.29.0 pypi_0 pypi
zipp 3.1.0 pypi_0 pypi
zlib 1.2.11 h62dcd97_3
zstd 1.3.7 h508b16e_0
Код из solver.py, где возникает ошибка:
class CaptioningSolver(object):
def __init__(self, model, data, **kwargs):
self.model = model
self.train_data = data['train_data']
self.n_epochs = kwargs.pop('n_epochs')
self.batch_size = kwargs.pop('batch_size')
self.update_rule = kwargs.pop('update_rule')
self.learning_rate = kwargs.pop('learning_rate')
self.print_every = kwargs.pop('print_every')
self.save_every = kwargs.pop('save_every')
self.data_path = kwargs.pop('data_path')
self.log_path = kwargs.pop('log_path')
self.model_path = kwargs.pop('model_path')
self.test_result_save_path = kwargs.pop('test_result_save_path')
self.models_val_disp = kwargs.pop('models_val_disp')
self.pretrained_model = kwargs.pop('pretrained_model')
self.test_model = kwargs.pop('test_model')
# set an optimizer by update rule
if self.update_rule == 'adam':
self.optimizer = tf.train.AdamOptimizer
elif self.update_rule == 'momentum':
self.optimizer = tf.train.MomentumOptimizer
elif self.update_rule == 'rmsprop':
self.optimizer = tf.train.RMSPropOptimizer
# create necessary folders
if not os.path.exists(self.model_path):
os.makedirs(self.model_path)
if not os.path.exists(self.log_path):
os.makedirs(self.log_path)
if not os.path.exists(self.test_result_save_path):
os.makedirs(self.test_result_save_path)
def train(self):
# train dataset
features = np.array(self.train_data['features'])
labels = np.array(self.train_data['labels'])
video_ids = np.array(self.train_data['video_ids'])
n_iters_per_epoch = int(labels.size / self.batch_size)
# # mix up the training data
# rand_idxs = np.random.permutation(len(labels))
# labels = labels1[rand_idxs]
# video_ids = video_ids1[rand_idxs]
# features = features[rand_idxs]
# build graphs for training model and sampling captions
loss = self.model.build_model()
#tf.reset_default_graph()
tf.get_variable_scope().reuse_variables() # set the 'reuse' of each variable as True
#tf.variable_scope(tf.get_variable_scope(), reuse=True)
#tf.variable_scope(tf.get_variable_scope()):
_, _, sam_labels = self.model.build_sampler()
# train op
with tf.name_scope('optimizer'):
optimizer = self.optimizer(learning_rate=self.learning_rate)
grads = tf.gradients(loss, tf.trainable_variables())
grads_and_vars = list(zip(grads, tf.trainable_variables()))
train_op = optimizer.apply_gradients(grads_and_vars=grads_and_vars)
tf.scalar_summary('batch_loss', loss) # add those to the observing process
# add the variables into observation
for var in tf.trainable_variables():
tf.histogram_summary(var.op.name, var)
for grad, var in grads_and_vars:
tf.histogram_summary(var.op.name + '/gradient', grad)
# train_summary = tf.merge_all_summaries()
print("The number of epoch: %d" % self.n_epochs)
print("Data size: %d" % (len(labels)))
print("Batch size: %d" % self.batch_size)
print("Iterations per epoch: %d" % (n_iters_per_epoch))
config = tf.ConfigProto(allow_soft_placement=True)
# config.gpu_options.per_process_gpu_memory_fraction=0.9
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
print('Session created')
tf.initialize_all_variables().run()
# train_summary_writer = tf.train.SummaryWriter(self.log_path, graph=tf.get_default_graph())
saver = tf.train.Saver(max_to_keep=50)
if self.pretrained_model is not None:
print("Start training with pretrained Model..")
saver.restore(sess, self.pretrained_model)
prev_loss = -1
curr_loss = 0
start_t = time.time()
# training process -- n_epochs iterations + n_iter_per_epoch
for e in range(self.n_epochs):
for i in range(n_iters_per_epoch):
S = i * self.batch_size
E = (i + 1) * self.batch_size
labels_batch = labels[S:E]
video_ids_batch = video_ids[S:E]
features_batch = features[S:E]
label_batch_idxs = np.array([[self.model.label_to_idx[per] for per in PER] for PER in labels_batch])
feed_dict = {self.model.features: features_batch, self.model.label_idxs: label_batch_idxs}
_, l = sess.run([train_op, loss], feed_dict)
curr_loss += l
# # write summary for tensorboard visualization
# if i % 10 == 0:
# summary = sess.run(train_summary, feed_dict)
# train_summary_writer.add_summary(summary, e * n_iters_per_epoch + i)
# show the current training condition
if (i + 1) % self.print_every == 0:
print("\nTrain loss at epoch %d & iteration %d (mini-batch): %.5f" % (e + 1, i + 1, l))
sam_labels_list = sess.run(sam_labels, feed_dict)
# decode the training result
gen_label_idxs, gen_labels = decode(sam_labels_list, self.model.idx_to_label)
org_label_idxs = label_batch_idxs[:, 0]
# visualize the current comparison
for j in range(len(org_label_idxs)):
print(video_ids_batch[j])
Ground_truth = 'org: ' + str(org_label_idxs[j])
Generated_one = 'gen: ' + str(gen_label_idxs[j])
print(Ground_truth + '--V.S.--' + Generated_one)
print('the current accurancy rate: ' +
str(accurate_percentage(gen_label_idxs, org_label_idxs)))
print("Previous epoch loss: ", prev_loss)
print("Current epoch loss: ", curr_loss)
print("Elapsed time: ", time.time() - start_t)
prev_loss = curr_loss
curr_loss = 0
# save model's parameters
if (e + 1) % self.save_every == 0:
saver.save(sess, self.model_path + 'model', global_step=e + 1)
print("model-%s saved." % (e + 1))
Полный стек след:
File "C:\Users\NewServer\Desktop\Action_Recognition_using_Visual_Attention-master\train.py", line 47, in <module>
solver.train()
File "C:\Users\NewServer\Desktop\Action_Recognition_using_Visual_Attention-master\core\solver.py", line 84, in train
train_op = optimizer.apply_gradients(grads_and_vars=grads_and_vars)
File "C:\Users\NewServer\anaconda3\envs\myconda\lib\site-packages\tensorflow_core\python\training\optimizer.py", line 597, in apply_gradients
self._create_slots(var_list)
File "C:\Users\NewServer\anaconda3\envs\myconda\lib\site-packages\tensorflow_core\python\training\adam.py", line 131, in _create_slots
self._zeros_slot(v, "m", self._name)
File "C:\Users\NewServer\anaconda3\envs\myconda\lib\site-packages\tensorflow_core\python\training\optimizer.py", line 1156, in _zeros_slot
new_slot_variable = slot_creator.create_zeros_slot(var, op_name)
File "C:\Users\NewServer\anaconda3\envs\myconda\lib\site-packages\tensorflow_core\python\training\slot_creator.py", line 190, in create_zeros_slot
colocate_with_primary=colocate_with_primary)
File "C:\Users\NewServer\anaconda3\envs\myconda\lib\site-packages\tensorflow_core\python\training\slot_creator.py", line 164, in create_slot_with_initializer
dtype)
File "C:\Users\NewServer\anaconda3\envs\myconda\lib\site-packages\tensorflow_core\python\training\slot_creator.py", line 74, in _create_slot_var
validate_shape=validate_shape)
File "C:\Users\NewServer\anaconda3\envs\myconda\lib\site-packages\tensorflow_core\python\ops\variable_scope.py", line 1500, in get_variable
aggregation=aggregation)
File "C:\Users\NewServer\anaconda3\envs\myconda\lib\site-packages\tensorflow_core\python\ops\variable_scope.py", line 1243, in get_variable
aggregation=aggregation)
File "C:\Users\NewServer\anaconda3\envs\myconda\lib\site-packages\tensorflow_core\python\ops\variable_scope.py", line 567, in get_variable
aggregation=aggregation)
File "C:\Users\NewServer\anaconda3\envs\myconda\lib\site-packages\tensorflow_core\python\ops\variable_scope.py", line 519, in _true_getter
aggregation=aggregation)
File "C:\Users\NewServer\anaconda3\envs\myconda\lib\site-packages\tensorflow_core\python\ops\variable_scope.py", line 886, in _get_single_variable
"reuse=tf.AUTO_REUSE in VarScope?" % name)
ValueError: Variable Conv_featuresbatch_norm/beta/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=tf.AUTO_REUSE in VarScope?