-
I want to use the same sequence of mini-batches to compare the performance of different optimizers.
I used "mxnet.random.seed(1)".
However, it only works for the initializer.
For mxnet.gluon.data.D…
-
## Description
HybridBeamSearch tests break after https://github.com/apache/incubator-mxnet/pull/16836.
Prior to the change in MXNet, the tests wouldn't fail because MXNet wouldn't give a chance to …
leezu updated
5 years ago
-
cascade_rcnn_vgg16_pruned_voc
Traceback (most recent call last):
File "scripts/detection/cascade_rcnn/train_cascade_rcnn.py", line 490, in
net = get_model(net_name, pretrained_base=True)
…
-
## Description
I've implemented multi-GPU support (which works fine). But when I add the following:
```
trainer.allreduce_grads()
nlp.utils.clip_grad_global_norm(params, 1)
trainer.update(args.a…
-
Chapter: 8
Notebook: Object Detection (object-detection.ipynb)
Section: Prepare the test data
`image = cv2.imread('img/pikachu.jpg')`
Errors at preprocessing as image doesn't exist. Couldn't f…
-
## 🐛 Bug
## Environment
- DGL Version (e.g., 1.0): 0.6.…
-
当我运行get_features.ipynb中的下面这一行:
features_vgg, labels = get_features(models.vgg16_bn(pretrained=True, ctx=ctx), data)
程序会运行很久之后便会出现错误BadZipFile File is not a zip file。程序运行时显示是从一个网址下载vgg16_bn-7f01cf05.…
-
For the example code provided by https://mxnet.incubator.apache.org/tutorials/nlp/cnn.html
```
# create convolution + (max) pooling layer for each filter operation
filter_list=[3, 4, 5] # the siz…
-
SINGA has multiple example models at http://singa.apache.org/docs/examples/
Some are implemented from scratch and some are converted from ONNX, which has a bigger model zoo https://github.com/onnx/m…
-
## Description
Python 2 : GPU Win
Unrelated PR #16722
Error log (brief)
```
Downloading ./parallel_download\mobilenetv2_0.25-ae8f9392.zip7251db52-2879-49fd-8e29-53861b5f8e3c from https://apache…