TensorFlow2.0-Examples

TensorFlow2.0-Examples copied to clipboard

YOLOv3 model doesn't converge

7

Hello. First of all, thank you for your amazing code. While trying to train the YOLOv3 model from scratch on yymnist dataset, I noticed that the loss is fluctuating between...

JVD9kh96

Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 2.0.0 to 2.7.2. Release notes Sourced from tensorflow's releases. TensorFlow 2.7.2 Release 2.7.2 This releases introduces several vulnerability fixes: Fixes a code injection in saved_model_cli (CVE-2022-29216) Fixes...

dependabot[bot]

运行video_demo.py时，只有第一帧预测正确后面都是nan，也就是后面没有预测框

1

有没有朋友遇到同样问题？我在运行video_demo.py时，只有第一帧预测正确后面都是nan。我怀疑是**utils.load_weights(model, "./yolov3.weights")**这一句的问题，于是把这一句放到了while true里，如代码所示，结果预测正确，但视频速度非常慢了，因为每次都要加载一次权重，我不知道该怎么修改**def load_weights(model, weights_file)**。求助！ `model = tf.keras.Model(input_layer, bbox_tensors)` `utils.load_weights(model, "./yolov3.weights")` `#model.summary()` `vid = cv2.VideoCapture(video_path)` `while True:` ` #utils.load_weights(model, "./yolov3.weights")` ` return_value, frame = vid.read()` ` if return_value:` ` frame...

mastergao57

Has any one encountered this issue when training with your own dataset? Traceback (most recent call last): File "train.py", line 93, in train_step(image_data, target) File "train.py", line 52, in train_step...

Guanzhao-hub

请问这个代码yolov3在pascal voc 2012上的map可以调到多少

Phoenix0qi

YOLOv3中训练自己的数据集时可以调用官方的yolov3.weights,在它的基础上进行训练吗？

8

非常感谢有这样一份2.0版本的示例，有一个问题是我在训练自己的数据集时初始loss很大，最终也没得到一个理想的效果，所以想请教如何在yolov3.weights的基础上进行训练？

monoloxo

运行test.py只有第一张图片有测试结果，剩下的图片都没有检测框出现

3

把test.py里的 `model.load_weights("checkpoint/yolov3_debris")` 移动到 `for num, line in enumerate(annotation_file):` 循环内可以测试所有图片。 但这明显不是根本原因，不知道哪位大神知道原因？

taojianggit

Bumps [pillow](https://github.com/python-pillow/Pillow) from 6.2.0 to 9.0.1. Release notes Sourced from pillow's releases. 9.0.1 https://pillow.readthedocs.io/en/stable/releasenotes/9.0.1.html Changes In show_file, use os.remove to remove temporary images. CVE-2022-24303 #6010 [@​radarhere, @​hugovk] Restrict builtins within...

dependabot[bot]

Meet a problem when applying model by compile-build-fit route. In 'resent.py' ,row 112: out = tf.reshape(out, (out.shape[0], -1)) By using out.shape, it will return a tuple rather than a tensor,...

A-cunminF

我用tf2的版本训练从头训练SeaShip数据集，最后效果不太好，想用coco数据集的权重进行初始化，但找了很久，都没有很详细的教程说明应该怎么做，因为自己数据类别数不一样，不知道怎么能加载coco前面层的部分权重，进行迁移学习，求大佬指点！

jsago