ksanjeevan/dourflow

Keras implementation of YOLO v2

dourflow's Issues

Slow webcam

The webcam operates very slowly at 1 digit fps. Have you encountered the issue?
System: Windows 10

What is the pretrained model ?

Hi all,
I want to ask which model is the pretrained model, that we must use to train on our own dataset. Because in the link that is given, there is many folders : coco_model.h5, coco_weights.h5... which one is the pretrained model ? from all this

THanks in advance for your response.
Sincerely

Unknown opcode

Hi,

I tried running your code and this is what I encountered:

λ py dourflow.py bird.jpeg
Using TensorFlow backend.
2018-10-10 18:31:03.236078: I T:\src\github\tensorflow\tensorflow\core\platform\cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2018-10-10 18:31:03.902197: I T:\src\github\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:1356] Found device 0 with properties:
name: GeForce 940MX major: 5 minor: 0 memoryClockRate(GHz): 1.189
pciBusID: 0000:01:00.0
totalMemory: 2.00GiB freeMemory: 1.66GiB
2018-10-10 18:31:03.919254: I T:\src\github\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:1435] Adding visible gpu devices: 0
2018-10-10 18:31:04.612760: I T:\src\github\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:923] Device interconnect StreamExecutor with strength 1 edge matrix:
2018-10-10 18:31:04.624627: I T:\src\github\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:929]      0
2018-10-10 18:31:04.631026: I T:\src\github\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:942] 0:   N
2018-10-10 18:31:04.638714: I T:\src\github\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:1053] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1430 MB memory) -> physical GPU (device: 0, name: GeForce 940MX, pci bus id: 0000:01:00.0, compute capability: 5.0)
XXX lineno: 91, opcode: 0
Traceback (most recent call last):
  File "dourflow.py", line 22, in <module>
    YoloV2().run()
  File "C:\Users\Psyf\Desktop\git\dourflow\yolov2.py", line 39, in run
    self.model = self.yolo_arch.get_model()
  File "C:\Users\Psyf\Desktop\git\dourflow\net\netarch.py", line 74, in get_model
    yolo_model = self._load_yolo_model()
  File "C:\Users\Psyf\Desktop\git\dourflow\net\netarch.py", line 97, in _load_yolo_model
    model = load_model(self.in_model_name, compile=False)
  File "C:\Users\Psyf\Anaconda3\lib\site-packages\keras\models.py", line 270, in load_model
    model = model_from_config(model_config, custom_objects=custom_objects)
  File "C:\Users\Psyf\Anaconda3\lib\site-packages\keras\models.py", line 347, in model_from_config
    return layer_module.deserialize(config, custom_objects=custom_objects)
  File "C:\Users\Psyf\Anaconda3\lib\site-packages\keras\layers\__init__.py", line 55, in deserialize
    printable_module_name='layer')
  File "C:\Users\Psyf\Anaconda3\lib\site-packages\keras\utils\generic_utils.py", line 144, in deserialize_keras_object
    list(custom_objects.items())))
  File "C:\Users\Psyf\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2535, in from_config
    process_node(layer, node_data)
  File "C:\Users\Psyf\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2492, in process_node
    layer(input_tensors[0], **kwargs)
  File "C:\Users\Psyf\Anaconda3\lib\site-packages\keras\engine\topology.py", line 619, in __call__
    output = self.call(inputs, **kwargs)
  File "C:\Users\Psyf\Anaconda3\lib\site-packages\keras\layers\core.py", line 685, in call
    return self.function(inputs, **arguments)
  File "netarch.py", line 91, in space_to_depth_x2
SystemError: unknown opcode

I'll be going through the code trying to fix it. In the meanwhile, if you know what might be causing it, please let me know.

Batch inference

Hi, could you please tell me how did you perform batch inference. I would like to do batch inference for yolov3 and your suggestions might help me

Error when using new tensorflow version

I am using tensorflow version 1.14, and the code seems to be not compatible with it. It's raising errors saying 'deprecated' while training and validating. The code works fine for image and video object detection.
How do I run the code with my tensorflow version?