-
Hi, I am the author of [Dynamic Tensor Rematerialization](https://arxiv.org/abs/2006.09616), a work that save memory for deep learning training, especially for dynamic shape/compute graph. I think thi…
-
When converting a YOLO model to ONNX (or other), we are told the model's output shape(s).
Since I can't use the ultralytics package to rely on the automatically created results object for my use c…
-
wide_and_deep预测用户收入的代码中，出现这个错误，查了google，没有找到合适的答案。请问这个是什么问题导致的呢？
```
KeyError: "The name 'learning_rate:0' refers to a Tensor which does not exist. The operation, 'learning_rate', does not exist i…
-
Arraymancer has become a key piece of Nim ecosystem. Unfortunately I do not have the time to develop it further for several reasons:
- family, birth of family member, death of hobby time.
- competin…
-
The way a recurrent NN in most deep learning toolboxes is trained is via mini-batch training on several trajectories where the input tensor has the shape
(#trajectories, #timesteps, #features).
…
-
Subscribe to this issue and stay notified about new [weekly trending repos in Nim](https://github.com/trending/nim?since=weekly).
-
Hello, I am a white, after I built the deep learning environment, put front3d_rpn_data into the data folder, according to the train.sh configuration parameter, "RuntimeError: split_with_sizes expects …
-
Alexnet implementation in tensorflow has incomplete architecture where 2 convolution neural layers are missing. This issue is in reference to the python notebook mentioned below.
https://github.com…
-
I've noticed that the rnn code in lingvo (in particular for ASR tasks) uses bitmasks for representing the validity of data in a sequence when you do batching.
To be explicit, if you have, `data`, …
-
I am running the code on AWS r5a.xlarge machine with
| Deep Learning AMI (Ubuntu) Version 14.0 - ami-0089d61bf6a518044-- | --
The machine has 32GB RAM and 4 vCPUs.
Running on
tensorflow ins…