deepinsight / deepinsight/insightface
How forwarding on batch in the deploy sample (test.py)?
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
I am able to forward a single image with `f1 = model.get_feature(img)` in test.py in the deploy folder.
Now, I would like to process a batch of images.
I tried with `numpy.stack([img ... img])` obtaining, for example, a [2, 3, 112, 112] input ndarray, but now I have the following error:
`mxnet.base.MXNetError: Error in operator conv0: [19:16:34] C:\Jenkins\workspace\mxnet-tag\mxnet\src\operator\nn\convolution.cc:152: Check failed: dshp.ndim() == 4U (5 vs. 4) : Input data should be 4D in batch-num_filter-y-x`
Thanks in advance!
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.