-
Click to expand!
### Issue Type
Documentation Bug
### Have you reproduced the bug with TF nightly?
Yes
### Source
source
### Tensorflow Version
tf 2.12.0
### Custom Code
Yes
### OS Platf…
-
We're working on a private cloud solution for personal photo management, see https://github.com/photoprism/photoprism
In order to enable uploading in our [demo](https://demo.photoprism.org/) again,…
-
The performance gap to TensorFlow is quite significant on models heavily using `DepthwiseConv2D` or `SeparableConv2D` layers.
Those models are:
- `mobilenet`
- `mobilenetv2`
- `nasnetlarge`
- `…
-
I'm implementing a CNN model, when I just have few layers, it works well. When I tried a deeper network, I can achieve a high performance (a small loss given during the training process) on training d…
-
## networks
- [x] CNN-GRU
- [ ] Inception v4
- [x] PHOCNet
- [ ] ResNet
- [ ] InceptionResNet
- [x] DenseNet
- [ ] LSTM and TimeDistributed
## Custom and hybrid networks
- [x] DenseNet Conv…
-
Hi, bro, have u test all the model? When I change the model to nasmobile, error occurs:
Traceback (most recent call last):
File "", line 1, in
File "D:\Program Files (x86)\JetBrains\PyCharm …
ghost updated
3 years ago
-
**System information**
- Have I written custom code (as opposed to using a stock example script provided in TensorFlow):
- OS Platform and Distribution (Linux Ubuntu 16.04):
- TensorFlow version (2…
-
Below is the demo
`
base_model = NASNetMobile(weights='imagenet', include_top=False, input_shape=(width, height, 3))
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Den…
-
**System information**
- Have I written custom code (as opposed to using example directory): yes
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): U16.04
- TensorFlow backend (yes / no…
-
現状、`weights/mobilenetv2/mobilenetv2_hasc_weights_256.hdf5`などであるが、
`weights/mobilenetv2/mobilenetv2_hasc_weights_768_1.hdf5`などにするにする。