-
def init_loss(hg, jp_batch, device):
with tf.variable_scope("logits", reuse=device > 0), tf.device("/gpu:%d" % device):
logits = slim.fully_connected(hg, jp_vocab_size) ## ?
log…
azzhu updated
6 years ago
-
Notice codes [HERE](https://github.com/tensorflow/benchmarks/blob/master/scripts/tf_cnn_benchmarks/tf_cnn_benchmarks.py#L333)
```
biased = tf.reshape(
tf.nn.bias_add(
…
-
I compress the model by ChannelPrunedLearner, when executed to `self.sess_train.run(self.train_op)` in `__train_pruned_model(self, finetune=False)` fun, the program don't continue execution。 I don't k…
-
Traceback (most recent call last):
File "train.py", line 8, in
from model import DeepLab
File "C:\Users\DGRE\DeepLab-V3\model.py", line 6, in
from feature_extractor import MobileNet,…
ghost updated
3 years ago
-
修改inception_v3_train_val.py 增加
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
试着在tf2.0下运行，提示错误
import slim.nets.inception_v3 as inception_v3
from nets import inception_utils
Attribut…
cj741 updated
4 years ago
-
when I was training ,an error comes up:
Traceback (most recent call last):
File "/home/zz/code/tf-Faster-RCNN/Models/faster_rcnn_resnet50ish.py", line 300, in
main()
File "/home/zz/code…
ZZ727 updated
6 years ago
-
Based on this [TF-slim models page](https://github.com/tensorflow/models/tree/master/slim#pre-trained-models), good candidate could be `Inception V2`, good accuracy and small weight of pre-trained mod…
-
# evaluating tensors
TensorFlow can't directly evaluate tf.Tensors defined inside functions or inside control flow constructs. If a tf.Tensor depends on a value from a queue, evaluating the tf.Tensor…
-
## The problem
I tried to run ResNet by using the slim version in **/models/research/slim/nets/resnetv2.py**, but the moving_mean and the moving_variance didn't be saved, even if I did as the offic…
-
I am using windows. When I try to run a flow command, it prompts: ModuleNotFoundError: No module named 'tensorflow.contrib'.
I looked it up and find tensorflow.contrib is removed after tensorflow 1.1…