-
The benchmark show the nx could get >800fps when use ssd-mobilenet-v1 models,
but when I use this model for process real video, it only get 60fps, and I use mutiple threat method to accelerat…
-
> ValueError: Cannot feed value of shape (1, 224, 224, 3) for Tensor 'import/fifo_queue_Dequeue:0', which has shape '(32, 224, 224, 3)'
```
import tensorflow as tf
from scipy.misc import imread, …
-
Hello,
Would it be possible for you to add a test for squeezenet? I mean like the ones for mobilenet and resnet50 on the `imagenet` folder.
Maybe the parameter file of squeeznet is not so big and …
-
**Expected Result**:
I expected that all zoo ONNX models are working properly but only 2 of them are OK: Alex and mobilenet. Is it Ok?
**Actual Result**:
All other models are crashing or results mi…
avt77 updated
5 years ago
-
@ricky40403
Hey, thanks for your great work. When i read the paper and your code, i have three question:
1. Can i set quan_bit to 2 or 4?
2. I notice ` tested in 4 bit with res18 on imagenet`, can…
-
您好，我在使用您的代码对整个mobilenet进行分组时，发现有部分层会被分到不同组里，请问这是为什么
-
Currently `tf` is bundled into this package. However it should be loaded separately.
Other packages do this using the `browserify-shim` as a global transformation, see https://github.com/tensorflow…
-
Can I get pre-trained model for mobilenet v3 that is modified in this Retinaface_Ghost?
If so, I think that I can train my data efficiently.
-
API를 더 일관되게 통일 하려고 합니다 (WIP)
* Rename `batch_preproc_params` of ssd mobilenet, resnet34 to `context`
* NativePostProcessor is designed to take only one context, but python version of postprocessor c…
-
NotFoundError: object_detection_real_time-master/detection/tf_models/ssd_mobilenet_v1_coco_2017_11_17/frozen_inference_graph.pb
could you supply the corresponding file?
Thanks!