-
Hi,
I've used the following code to convert:
```
# Convert SavedModel using TF-TRT
def convert_model_to_trt():
params = trt.DEFAULT_TRT_CONVERSION_PARAMS._replace(
precision_mode=trt…
-
我基于作者的代码实现了yolov3-tiny，基本上就是把pred_sbbox去掉，然后训练voc数据集。
1、把107-109移到79行，得到模型是**34.9M**，然后evaluate时报错，Keyconv0/batch_normalization/beta/ExponentialMovingAverage not found in checkpoint...然后把self.saver =…
-
devices not set
Traceback (most recent call last):
File "hcaptcha.py", line 305, in
resolver = hCaptcha( '51829642-2cda-4b09-896c-594f89d700cc', 'democaptcha.com' )
File "hcaptcha.py", li…
-
I am trying to use ImageAI library for detecting objects in video. It is working properly if CPU is used for processing but performance is far from real time. I have 2080TI 11Gb GPU available but whe…
-
In your previous discussion, I learned that it is better to train the pre-model through IMAGENET and then train on VOC, but I want to use the VOC dataset to roughly test the effect of this model. But…
Zmjcc updated
4 years ago
-
I am trying to train YOLO V3 on a custom dataset to detect a single object.
After 7 hours of training on a NVIDIA 1080 GTX (8GB RAM), this is what I get
```
Region 94 Avg IOU: -nan, Class: -nan, …
-
-
@AlexeyAB and @WongKinYiu, I have noticed that not many people been able to replicate the results of this loss function from scratch outside of the darknet repo using the exact same loss function.
…
-
This code (https://sites.google.com/view/tensorflow-example-java-api) is running successfully on YOLOv2 model, but not runs on my tensorflow model which I have trained by using python tutorial:
(h…
-
Whatever photos I put , the net_ouput will be the same.And the final image showed last have the same frame.I am upset about this phenomenon.
Hope someone could tell me any advice.
Thank you.
> de…