-
您好,我想请问下,不使用“import tensorflow.compat.v1 as tf”的情况下,使用tf 2.x进行训练,会报错:
TypeError: You are passing KerasTensor(type_spec=TensorSpec(shape=(), dtype=tf.float32, name=None), name='Placeholder:0', descr…
panhu updated
2 months ago
-
**Is your feature request related to a problem? Please describe.**
The histograms of weights in the WandbCallback() are only taken when there are 1 or 2 weights in the keras Layer.
https://github.…
-
I sent the following issue [16495](https://github.com/keras-team/tf-keras/issues/631).
Following the advice, I encounter an incompatibility between keras.wrappers.scikit_learn and scikeras.
With k…
-
I have created a CustomModel using the subclass API
```python
class CustomModel(keras.Model):
def __init__(self, num_classes=10):
super().__init__()
self.num_classes = num_c…
-
#### Issue Description
Various keras pre processing layers are currently missing from import. These include the computer vision layer such as Rescale and Resize as well as other methods of pre proces…
-
### 🚀 The feature, motivation and pitch
To support strings as a dtype on torch tensors, similarily to how [TensorFlow](https://www.tensorflow.org/api_docs/python/tf/strings) does it. This will enri…
-
### 🚀 The feature, motivation and pitch
LayerNorm starts to be applied to image data on per-channel basis (e.g. in ConvNeXt model).
`torch.nn.LayerNorm` support normalization only on the last se…
-
When I run test.py. The error occur below.
File "test.py", line 4, in
from keras import backend as K
File "Keras-2.0.8/keras/__init__.py", line 4, in
from . import activations
Fil…
-
This is likely due to Keras version changes. Currently using Keras 3.2.1 with Tensorflow 2.16.1.
So far, I've changed the following in `layers.py`:
`from keras.src.layers.rnn.dropout_rnn_cell_mi…
-
hi
我在转换 https://huggingface.co/BAAI/bge-small-en-v1.5/tree/main/onnx
这个模型,遇到下面的错:
```
2024-07-05 16:21:59.085678: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is op…