leemengtw/cat-recognition-train

Train and deploy a cat vs dog image recognition model using TensorFlow

cat-recognition-train's Issues

hao can train the gray image

Hello, I want to train the datasets which consist of the gray image,but it's occur the error as follows：
self.global_step: epoch})
File "/home/lijh/anaconda3/envs/weiwuhuhu/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 950, in run
run_metadata_ptr)
File "/home/lijh/anaconda3/envs/weiwuhuhu/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1173, in _run
feed_dict_tensor, options, run_metadata)
File "/home/lijh/anaconda3/envs/weiwuhuhu/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1350, in _do_run
run_metadata)
File "/home/lijh/anaconda3/envs/weiwuhuhu/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1370, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Expected image (JPEG, PNG, or GIF), got unknown format starting with 'BM6\264\004\000\000\000\000\0006\004\000\000(\000'
[[{{node DecodeJpeg}}]]
[[IteratorGetNext]]
It looks like that formats error, how can i solve this,thank you your ealy reply!

I just upload a cat image, but the result is 100% dog.

I just upload a cat image, but the result is 100% dog.
Photo 48
But I don't know how to feedback. Sorry about it.