Git Product home page Git Product logo

yolov3_tensorflow2's People

Contributors

calmilovesai avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar

yolov3_tensorflow2's Issues

您好,我在解码时遇到了一些问题

您好,在运行时出现了这样的错误UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd5 in position 95: invalid continuation byte

这里出现了问题 train_from_scratch.py, line 74, in
train_step(image_batch=process_image_filenames(images), label_batch=labels)

how to decide the anchor box width and height

wo can get the best number of classify through the kmeans, but how to decide the anchor box shape is still question, I saw you use the fixed number for anchor box width and height ,I want to know how you consider about it

用tf.metrics.Mean()记录损失,进入新的epoch时损失出现跳跃性下降。

我正在用tf.metrics.Mean()记录训练的损失,如果按照每一轮训练结束后重置loss metrics,那么在新的一轮训练中输出的loss值会骤降。现实训练中,第一轮训练训练loss会从几千降低到几百,然后进入下一轮时,损失直接突变为几十,请问此时的loss值是否是准确的呢?

a small bug on test_on_single_image.py

In the 36th line of test_on_single_image.py, '''img_tensor = img_tensor / 255.0''', but in the 34th line '''resize_image_with_pad''' had done it (in the 10th line of utils.preprocess.py), that means max(img_tensor)=0.0039 not 1.

confused with ignore_mask and true_object_mask

ignore_mask = best_ious < ignore_threshold
confidence_loss = true_object_mask * self.__binary_crossentropy_keep_dim(true_object_mask, pred_features[..., 4:5], from_logits=True) + \
                              (1 - true_object_mask) * self.__binary_crossentropy_keep_dim(true_object_mask, pred_features[..., 4:5], from_logits=True) * ignore_mask

when compute the confidence_loss, here you use the ignore_mask, and only in here, other place all use the true_object_mask, I m really confused with this part...

any reply is appreciate, thanks in advance
@calmisential

Using a `tf.Tensor` as a Python `bool` is not allowed.

File "/home/zhangyt/TensorFlow2.0-Examples/4-Object_Detection/YOLOV3/core/backbone.py", line 20, in darknet53
input_data = common.convolutional(input_data, (3, 3, 3, 32))
File "/home/zhangyt/TensorFlow2.0-Examples/4-Object_Detection/YOLOV3/core/common.py", line 43, in convolutional
if bn: conv = BatchNormalization()(conv)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 625, in call
exception_str + '\n"""')
TypeError: You are attempting to use Python control flow in a layer that was not declared to be dynamic. Pass dynamic=True to the class constructor.
Encountered error:
"""
Using a tf.Tensor as a Python bool is not allowed. Use if t is not None: instead of if t: to test if a tensor is defined, and use TensorFlow ops such as tf.cond to execute subgraphs conditioned on the value of a tensor.

按照提示改了,但是还是出现这个问题,感觉也没什么错啊

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.