tensorflow-yolov4-tflite
tensorflow-yolov4-tflite copied to clipboard
hunglc007
YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
I am facing the following error: ```python ValueError: cannot reshape array of size 5370 into shape (30,256,1,1) ``` What I did -Changed config.py as follows. ```python # YOLO options __C.YOLO...
can't run program on android os oreo(8.1) but program can run on android os marshmallow(6.0). error is given in the log as follows. 2022-03-10 19:47:08.264 29063-30043/org.tensorflow.lite.examples.detection E/AndroidRuntime: FATAL EXCEPTION: Thread-2...
2022-03-10 15:57:04.654803: W tensorflow/python/util/util.cc:348] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them. 2022-03-10 15:58:08.954586: W tensorflow/core/framework/op_kernel.cc:1767] OP_REQUIRES failed at save_restore_v2_ops.cc:109...
First I use darknet to train the yolov4-tiny model, it has two detection classes, and the input image size is 224. The trained weight is first converted to tensorflow, and...
Made the required changes to make the repo work for `yolov4-tiny-3l`.
This issue has been mentioned quite sometime ago on: https://github.com/hunglc007/tensorflow-yolov4-tflite/issues/356 and https://github.com/hunglc007/tensorflow-yolov4-tflite/issues/282 But there still isn't a proper solution to this. I am wondering if anyone managed to solve this....
I want to convert my darknet weights to tensorflow. when I use the command : python save_model.py --weights ./data/yolov4-tier_last.weights --output ./checkpoints/yolov4-320 --input_size 320 --model yolov4 And I get the error...
Hey @hunglc007 I have a new darknet model with different architecture, which is obtained by removing some connections in the yolov4 tiny model. Is it possible to convert that model...
Hello, I have had to update all libraries using an RTX 3070. I have got this working for images on custom data sets, but when I run the video detection...
Hi, I want to make the generated yolov4 (tensorflow) to be a static model not a dynamic model ? how could i do that ?? Note: I need it to...
