tensorflow-yolov4-tflite

tensorflow-yolov4-tflite copied to clipboard

Error converting gray-scale (1 channel) yolo4 model

2

I have trained a 1 channel yolo4 model and verified that it is working. However, when I run `python save_model.py --weights ./data/yolov4_1Chanell.weights --output ./checkpoints/yolov4-416 --input_size 416 --model yolov4` I get...

PatrikPatrik2

Aborted Error while running detect.py with yolov4-tiny-trt model in Jetson Nano

12

Hi @hunglc007 , I have converted the yolov4-tiny weights into tensorflow weights and then converted it into tensorrt model using your repo. Now when trying to run detect.py file with...

srikar242

when convert yolov4 tiny model to tf file happen error

2

I training my yolov4 for custom data based on alexeyab rep. I try convert weight to tf file by use save_model.py , but it give a error :  I...

ericosmic

error when i convert tensorflow weight to tflite

2

Hi Guys i got error when i run this command #Convert to tflite in yolov4 model in colab google drive thanks for help !python convert_tflite.py --weights ./checkpoints/yolov4-416 --output ./checkpoints/yolov4-416.tflite I1111...

falahgs

loss nan problem

1

this may be mish bugs, even I clip the gradient value and descend the lr to even 1e-6. I also load the darknet weights and can only get about [email protected]...

manutdzou

Tflite Conversion Issue with Scale

1

Hello, I have successfully converted darknet pretrained model into tflite model using tensorflow 2.3.0 or rc version and opencv 4.1.1.26. Then, I ran detect.py but the scales of bounding boxes...

khg2478

Yolov4 Evaluation returns an mAP of 0

4

I am having an issue with Yolov4. I downloaded the weights, and convert to pb. I create the dataset and do the preprocessing of the dataset. Then I run the...

milanpatel25

Inference on saved Tensorflow model

2

I converted the weights using save_model.py and got the final model. My question is how to load it via Keras/Tensorflow to do inference? ``` model = tf.saved_model.load(str(model_dir), tags=['serve']) model =...

AlphaNumeric99

Fixed int8 quantization and added experimental mixed int8/int16 quantization

11

Thanks for providing these examples of working with Yolo v4/v3! I managed to fix the int8 quantization by adding a `model.compile()` statement to fix the "optimize global tensors" exception. I...

mikljohansson

According to the answer from "lazarjovanovicnissatech", did some modification on core/utils.py and annotated original code

lsmh886