To get started using this repo quickly using a Google Cloud Platform (GCP) Deep Learning Virtual Machine (VM) follow the instructions below. New GCP users are eligible for a $300 free credit offer. Other quickstart options for this repo include our [Google Colab Notebook](https://colab.research.google.com/github/ultralytics/yolov3/blob

Per my understanding, the functions bunched together in the sub-directory tf_extended are meant to supplement the SSD implementation using standard TensorFlow functions, but it is not the same as TFX - Tensorflow Extended. Is this correct?

If that's the case, perhaps a modification to the readme will help newcomers avoid conflating the two. I'm willing to

Thanks for your tutorial from scratch. It helps me a lot.
In article part 3, there are some codes you wrote. I copy that codes but some error for me.

model = Darknet("cfg/yolov3.cfg")
inp = get_test_input()
pred = model(inp)
print (pred)

TypeError: forward() missing 1 required positional argument: 'CUDA'

and I want to ask you that training module is the only left work

hi, @Cartucho thanks for you contribution, it do help me a lot with understanding the criteria metric of PASCOL VOC 2012!

I have a similar question to #93 but not exact same. As you provided curve in the readme file:

Considering the first prediction entry is false positive, thus:

Guys can you please, please update your documentation. Its really painful to figure out nuances.
It would really help if you gave some canonical examples for configuring cells with dynamic height. labels, html, etc. The documentation is is mixed between the legacy implementation and the current implementation.

Using TensorFlow backend.
C:\Users\Home\Anaconda3\envs\Tensorflow\lib\site-packages\tensorflow\python\framework\dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\Home\Anaconda3\envs\Tensorflow\lib\site-packages\te

The 2x down-sampling is one of the important operations in reference models. But, a convolution or a pooling with stride=2, padding='SAME' may result in different outputs over different deep learning libraries (e.g., TensorFlow, CNTK, Theano, Caffe, Torch, ...) due to their different padding behaviors.

For example (TensorNets syntax; but can be regarded as pseudo codes for other libraries),

I stumbled upon this repo https://github.com/dataplayer12/homesecurity/ which uses the jetson for CCTV system.
Idea: use a raspberry pi zero with a pi-camera-module could be a simple solution for uses cases like: Hardware inside and camera module outside.

• more secure since the pi only costs a fraction of the jetson
• no cable connection between board and camera
• option to connect more than

I would like to pass the array values, inside the filtered_boxes dictionary, to the tf.image.crop_to_bounding_box() function, and crop the detected images.
But the format of the values in the array is unclear. That is, i am unsure which of the values are top left, top right, width and height. Could you please help with the format. Thanks.

I see you have added gaussian_yolov3_layer and yolo detection gaussian_box.(from this paper https://arxiv.org/abs/1904.04620)

can you provide a wiki or same example prototxts to explain how to use gaussian yolo correctly

thank you very much

I find run.py is updated.

-# FLAGS.model = "darkflow/cfg/yolo.cfg" # tensorflow model
-# FLAGS.load = "darkflow/bin/yolo.weights" # tensorflow weights
-FLAGS.pbLoad = "tiny-yolo-voc-traffic.pb" # tensorflow model
-FLAGS.metaLoad = "tiny-yolo-voc-traffic.meta" # tensorflow weights

could you share the file of tiny-yolo-voc-traffic.pb and tiny-yolo-voc-traffic.meta ?
thank you very much!