search

ardianumam / Tensorflow-TensorRT

This repository is for my YT video series about optimizing a Tensorflow deep learning model using TensorRT. We demonstrate optimizing LeNet-like model and YOLOv3 model, and get 3.7x and 1.5x faster for the former and the latter, respectively, compared to the original models.
303 stars 110 forks source link

difficulty generating correct frozen .pb #7

Closed LukeAI closed 5 years ago

LukeAI commented 5 years ago

I understand that you generated the provided yolov3_gpu_nms.pb using the pretrained coco weights from https://pjreddie.com/media/files/yolov3.weights placed in the checkpoint dir in this repo https://github.com/ardianumam/tensorflow-yolov3

My question is, what exactly did you run in order to generate the .pb? I generated my .pb with python convert_weight.py --convert --freeze but it doesn't give the correct output tensors as illustrated below.

  input_tensor, output_tensors = \
  utils.read_pb_return_tensors(tf.get_default_graph(),
                               GIVEN_ORIGINAL_YOLOv3_MODEL,
                               ["Placeholder:0", "concat_9:0", "mul_9:0"])
  print("\n\ninput_tensor\n", input_tensor)
  print("\n\noutput_tensors\n", output_tensors)

** Output for provided .pb (this works) **
input_tensor
 Tensor("import/Placeholder:0", shape=(1, 416, 416, 3), dtype=float32)

output_tensors
 [<tf.Tensor 'import/concat_9:0' shape=(1, 10647, 4) dtype=float32>, <tf.Tensor 'import/mul_9:0' shape=(1, 10647, 80) dtype=float32>]

** Output for my .pb (this doesn't work - see the output tensors shape)**
input_tensor
 Tensor("import/Placeholder:0", shape=(1, 416, 416, 3), dtype=float32)

output_tensors
 [<tf.Tensor 'import/concat_9:0' shape=(1, 10647, 4) dtype=float32>, <tf.Tensor 'import/mul_9:0' shape=(?,) dtype=int32>]

[ I've tried this conversion using TF 1.11, 1.12, 1.13rc2 - all give the same results]

LukeAI commented 5 years ago

OK, I have resolved this by specifying: "["Placeholder:0", "concat_9:0", "mul_6:0"]" as the return_elements arg for utils.read_pb_return_tensors() I guess that ["Placeholder:0", "concat_9:0", "mul_9:0"] was an older definition for the outputs here https://github.com/ardianumam/tensorflow-yolov3 which was used to generate your provided .pb and has now changed?

ardianumam commented 5 years ago

Hi,

Sorry for late response, was quite crowded recently. But glad that you already solve the issue. Yes, you might be right, those new tensor names may be already changed.