I want to convert pytorch model(hopenet) to caffemodel, However, met the following err

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us

AttributeError: tuple object has no attribute 'grad_fn' about pytorch2caffe HOT 6 CLOSED

dzyjjpy commented on July 17, 2024

AttributeError: tuple object has no attribute 'grad_fn'

from pytorch2caffe.

Comments (6)

dzyjjpy commented on July 17, 2024 1

output has three branch 3*66, so you should edit the code in pytorch2caffe
convert_layer(output_var[0].grad_fn)
convert_layer(output_var[1].grad_fn)
convert_layer(output_var[2].grad_fn)
as tuple object has no attribute 'grad_fn'

from pytorch2caffe.

zhaobaozi commented on July 17, 2024

have you finish?I meet the same problem

from pytorch2caffe.

trohit920 commented on July 17, 2024

@dzyjjpy @zhaobaozi @longcw Any updates on this ?

from pytorch2caffe.

trohit920 commented on July 17, 2024

@dzyjjpy @zhaobaozi I did what you advised but got stuck with this error.

  File "pytorch2caffe.py", line 428, in <module>
    os.path.join(output_dir, 'hopenet-pytorch2caffe.caffemodel'))
  File "pytorch2caffe.py", line 38, in pytorch2caffe
    net_info = pytorch2prototxt(input_var, output_var)
  File "pytorch2caffe.py", line 330, in pytorch2prototxt
    add_layer(output_var[0].grad_fn)
  File "pytorch2caffe.py", line 157, in add_layer
    top_name = add_layer(u[0])
  File "pytorch2caffe.py", line 169, in add_layer
    layer['type'] = layer_dict[parent_type]
KeyError: 'ExpandBackward'

I am a newbie, hope you can understand. Can you share the converted caffe model if possible ?

from pytorch2caffe.

trohit920 commented on July 17, 2024

@dzyjjpy I have solved all the previous errors and stuck with this one:

converting AddmmBackward190
((66L,), (66L, 2048L))
(66,)
(66, 8192)
Traceback (most recent call last):
  File "pytorch2caffe.py", line 441, in <module>
    os.path.join(output_dir, 'hopenet-pytorch2caffe.caffemodel'))
  File "pytorch2caffe.py", line 99, in pytorch2caffe
    convert_layer(output_var[0].grad_fn)
  File "pytorch2caffe.py", line 94, in convert_layer
    save_fc2caffe(weights, biases, params[parent_name])
  File "pytorch2caffe.py", line 118, in save_fc2caffe
    fc_param[0].data[...] = weights.numpy()
ValueError: could not broadcast input array from shape (66,2048) into shape (66,8192)

Please if you know how to convert any advice will be helpful.

from pytorch2caffe.

dzyjjpy commented on July 17, 2024

shape issue, pay attention to your tensor size. there might be issue caused by pooling layer's calculation mode. floor or ceil. pls check the layer with errors carefully

from pytorch2caffe.

Recommend Projects