YAD2K
YAD2K copied to clipboard
YAD2K: Yet Another Darknet 2 Keras
Hi, guys: It's really hard to understand these codes below, I mean , if we can't see .weights, how can I parse hyper-parameters from .weights? by the way, what is...
``` /home/pi/.local/lib/python2.7/site-packages/numpy/core/include/numpy/npy_1_7_deprecated_api.h:15:2: warning: #warning "Using deprecated NumPy API, disable it by " "#defining NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION" [-Wcpp] #warning "Using deprecated NumPy API, disable it by " \ ^~~~~~~ In file included...
Hi I have successfully built a Tiny Yolo v3 model by updating the script. but the model does not run correctly when using the test script. Any ideas?
Hi everyone, I'm new to deep learning and I want to train my own datasets on top of a pre-trained model here in YOLO. If I may ask 3 questions:...
Can you give a mini-tutorial on how to train this model and use it to predict bounding-boxes, on your own data. (given 20,000 images with bounding boxes, of objects not...
``` $ python yad2k.py cfg/yolov2-tiny.cfg yolov2-tiny.weights data\yolov2-tiny.h5 ``` Output ``` 2018-09-10 17:39:44.881414: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX 2018-09-10 17:39:44.883482:...
I'm training model using given retrain script with underwater dataset data downloaded from here. On last epoch I got loss: 20, and it gives wrong bounding boxes.[give prediction about other...
Hi, firstly, thanks for your great suggestion this repo. I'm would like to extract the feature map after the specific layer (example: after the 3 Conv layer of Yolov2-voc). Because...
I've trained yolov3 on mobilenet backend and get a good MAP(about 90M and 2 times faster than keras yolov3).I upload my code for mobilenet-yolov3 on https://github.com/Adamdad/keras-YOLOv3-mobilenet.git use it as you...
Hi @allanzelener , Thank you for your great work. I wonder if the current Loss Function works for non-square images? In file `keras_yolo.py`, I see this: ``` feats = K.reshape(feats,...