xyolo icon indicating copy to clipboard operation
xyolo copied to clipboard

一个高度封装的yolov3类库。

Results 8 xyolo issues
Sort by recently updated
recently updated
newest added

我之前用的keras-yolov3项目生成的h5使用的save_weights,结果我咋转都转不到pb,用于手机上使用opencv加载,这个是使用save函数吗?

xyolo使用时,其tensorflow版本是2.2.0,只能在cuda11.1以下运行。如果想在cuda11.3以上版本使用xyolo,应该如何配置呢?

为什么我在腾讯云gpu训练的时候loss总是nan,colab和本地cpu(epyc)都正常

大佬的这个项目用起来确实简单,但是在训练的部分还有值得优化的地方,能让训练效率提高3-5倍不止

``` Create Tiny YOLOv3 model with 6 anchors and 80 classes. Load weights /DATA/xyolo/xyolo/xyolo_data/keras_weights.h5. Freeze the first 42 layers of total 44 layers. 2021-01-31 18:03:41.533 | INFO | xyolo.xyolo.yolo3.yolo:fit:195 -...

因为compute_output中输入的参数类型, 为python的list, 而tf.function对于python基础类型, 只支持相同值下的加速 `@tf.function def compute_output(self, image_data, image_shape):` tf.function对于TensorFlow 张量或 NumPy 数组, 支持相同类型下的加速, 故, 应修改为: ` def detect_image(self, img: typing.Union[Image.Image, str]) -> typing.List[ typing.Tuple[str, int, float, int, int, int,...

Collecting xyolo Using cached xyolo-0.1.6-py3-none-any.whl (118 kB) Collecting tensorflow>=2.2 (from xyolo) Obtaining dependency information for tensorflow>=2.2 from https://files.pythonhosted.org/packages/93/21/9b035a4f823d6aee2917c75415be9a95861ff3d73a0a65e48edbf210cec1/tensorflow-2.15.0-cp311-cp311-win_amd64.whl.metadata Using cached tensorflow-2.15.0-cp311-cp311-win_amd64.whl.metadata (3.6 kB) Collecting numpy=1.18.1 (from xyolo) Using cached numpy-1.18.5.zip...