-
I'm trying to run several example on my old workstation, specs:
* CPU
```
Model: Intel(R) Xeon(R) CPU E5-1620 0 @ 3.60GHz
RAM: 16 GB
```
* GPU
```bash
+----------------------------------…
-
I'm trying to compile darknet with OpenCV on my macOS 10.14.3 (Mojave). Here is basically what I did:
I installed OpenCV via `brew install opencv` and it gave me version 4.1.0 (confirmed via `openc…
-
Hi,
first, thanks for the awesome library. I've been testing DALI for a current project and found that DALI does not support different methods to shuffle video data similar to for example decord (h…
-
### [R and C++] About times
All times, including _forecast times_, _forecast lead times_, and _observation times_, in the program use **seconds** as the unit. The origin is assumed to be `1970-01-0…
-
## 🐛 Bug
I can train Transformers but not Fully convolutional or LSTMs models (e.g.: `fconv,fconv_iwslt_de_en, fconv_wmt_en_de, lstm, lstm_luong_wmt_en_de,`...) because gradients are inconsistent b…
-
### Issue summary
Networks using the **Reshape** layer fail to back-propagate when certain conditions are met.
Instead the bottom layer's diff blob will include only zeros, regardless of the conte…
-
Hi, I want to ask a simple problem about the mnist classification example. Images in mnist are treated as sequences by expanding them to 1D, then each image gets a probability distribution. But imag…
-
I'm trying to train my custom datasets using darknet but everytime I initialize training I encounter this kind of error
try to allocate additional workspace_size = 13.31 MB
CUDA allocate done!
…
-
I try to train the yolo-small with my own data, totally 5092 images and objects in 4 classes.
The pre-trained model I used is **darknet19_448.conv.23**.
My configuration in Makefile:
```
GPU=1
CU…
-
Currentrly, Keras TCN does not support [`tf.RaggedTensor`](https://www.tensorflow.org/api_docs/python/tf/RaggedTensor) input. It would be very useful for speeding up training for variying length time …