search

theAIGuysCode / yolov4-custom-functions

A Wide Range of Custom Functions for YOLOv4, YOLOv4-tiny, YOLOv3, and YOLOv3-tiny Implemented in TensorFlow, TFLite, and TensorRT.
MIT License
602 stars 370 forks source link

Unable to create group (name already exists) while converting custom weight to yolov4 #69

Open edwardchang0112-nctu opened 3 years ago

edwardchang0112-nctu commented 3 years ago

Since I am working on Jetson NX, the tensorflow I used is tensorflow-1.15.4+nv20.12

First, download custom.weight then create a custom.names with only car then create checkpoint directory then just followed the command of this repo:

python3 save_model.py --weights ./data/custom.weights --output ./checkpoints/custom-416 --input_size 416 --model yolov4

get the following error

File "save_model.py", line 54, in main
    save_tf()
  File "save_model.py", line 51, in save_tf
    model.save(FLAGS.output)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/network.py", line 1171, in save
    signatures)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/saving/save.py", line 109, in save_model
    model, filepath, overwrite, include_optimizer)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/saving/hdf5_format.py", line 103, in save_model_to_hdf5
    save_weights_to_hdf5_group(model_weights_group, model_layers)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/saving/hdf5_format.py", line 619, in save_weights_to_hdf5_group
    g = f.create_group(layer.name)
  File "/usr/local/lib/python3.6/dist-packages/h5py/_hl/group.py", line 68, in create_group
    gid = h5g.create(self.id, name, lcpl=lcpl, gcpl=gcpl)
  File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
  File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
  File "h5py/h5g.pyx", line 161, in h5py.h5g.create
ValueError: Unable to create group (name already exists)

Any idea on this?

edwardchang0112-nctu commented 3 years ago

I then tried to change the version of tensorflow to tensorflow-2.3.1+nv20.12, but got error:

tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[3,3,512,1024] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc [Op:RandomStandardNormal]

How about this issue?