tensorflow-yolov4-tflite

tensorflow-yolov4-tflite copied to clipboard

infer() failed to predict any bbox after the first call

24

The 'serving_default' signature infer always returns pred_bbox with shape (1, 0, 84) except in the first call which returns pred_bbox with shape (1, 8, 84). It happens in detectvideo.py and...

wangyi1177

How can I generate the .pbtxt file from .pb saved?

1

Hello, I used the script "save_model.py" to generate .pb file, which is generated successfully and runs fine. My problem is, I need to generate the .pbtxt file from the .pb...

ELERKSOSY

Hi, I have trained yolov4-tiny with depthwise convolutional layer and got a weight file. My darknet depthwise cfg is like  , and I use Netron to look my cfg...

KuoEuran

Not able to run benchmark.py with pretrained model

5

I'm trying to run benchmark with pretrained model YOLOv4-Mish-416 from this page: https://github.com/AlexeyAB/darknet/wiki/YOLOv4-model-zoo After run: python benchmarks.py --size 416 --model yolov4 --weights ./data/yolov4-mish-416.weights I got error: ``` Traceback (most recent...

dh0d

refactoring code with var unpack which is more pythonic, concise, readable and efficient; how do think this change which has practical value？

idiomaticrefactoring

There is a bug in train logic?

1

The training logic cannot work cause this exception: ``` File "...\tensorflow-yolov4-tflite-master\core\dataset.py", line 124, in __next__ self.train_output_sizes[2], IndexError: index 2 is out of bounds for axis 0 with size 2 ```...

shinyke

Easier for people to create a docker environment and run their experiments.

siddhi47

Slow Detection

1

W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message...

ogzhn1k

i run the android example in my device and got this error java.lang.IllegalArgumentException: Cannot copy between a TensorFlowLite tensor with shape [1, 2535, 4] and a Java object with shape [1, 10647, 4]

2

hello , i download the code and run it in android device and got the following error when i try to do detection any idea how to solve this issue...

Abdullamhd

Hi, I have trained a Yolo model based on yolov4-tiny include separable convolutional layer, but the conversion is not successful, I think the problem is the conv_layer.set_weights in utils.py. Does...

KuoEuran