-
####### Code ###########
clf = TabNetClassifier(
n_d=64, n_a=64, n_steps=2,
gamma=1.5, n_independent=1, n_shared=1,
cat_idxs=cat_idx,
cat_dims=cat_dims,
#cat_emb_dim=1,
…
-
Thank you very much for sharing your valuable code here. However, I couldn't compile it due to the "sparse_tools" library dependency. Once I try to run "python setup.py develop", it sets the sparse_t…
-
Running Env
```
OS centos7
CUDA 11.0
TensorRT 7.2.2.2
cuDNN8.0
pytorch 1.7.1
```
when run the snipped code, it will print "################" show that **convert_ReLU** was called
```pyt…
-
I'm trying to understand the `SparsityParameters` in tflite schema. But, AFAIK, there is only one example that contains this parameters(`tensorflow/lite/testdata/sparse_tensor.json`).
So, I've got …
-
Hi, I want to use `tf.embedding_lookup_sparse_with_distributed_aggregation` in my training program. The model is built with tf.estimator and tf.feature_column .
But the default is using `safe_emb…
-
I am testing the new slot configurations on main and I fear there's a big bug in the shell.
### via `rasa interactive`
First I figured I'd try running my form in interactive mode.
```
> ras…
-
⚠️⚠️⚠️
I found out that this issue only happens in Keras version > 2.2.2 (so in 2.2.3 and 2.2.4 up to now).
I downgraded to version 2.2.2 (and Tensorflow 1.10.0) and the error doesn't happen any…
-
It's been cited by many users as the reason for switching to Pytorch, but I've yet to find a justification / explanation for sacrificing the most important practical quality, speed, for eager executio…
-
Continuing #336
**Describe the bug**
Getting "CUDA error: an illegal memory access was encountered"
**Reproduction**
1. What command or script did you run?
```
python tools/train.py configs/…
-
A `loss.mark_as_loss()` call inside a module causes the calling of
- `self.name_ctx.make_all_sub_networks_and_optimize()`
- `ctx._make_sub_network_layer(ctx_.layer_ref)`
- `nn.copy(sub_output, n…