jian3xiao
commented
4 years ago you can use: inputs = np.expand_dims(inputs, 0) outputs = network.predict(inputs)
to make the shape of inputs is [1, h, w, 3]
Open skdingding opened 5 years ago
jian3xiao
commented
4 years ago you can use: inputs = np.expand_dims(inputs, 0) outputs = network.predict(inputs)
to make the shape of inputs is [1, h, w, 3]
weizhiliang0520
commented
3 years ago feed_dict={self.input:x}) |
|---|
after--->feed_dict={self.input:[x]})
when i test only one image using your trained model,something wrong at Predicting... Traceback (most recent call last): File "test.py", line 29, in
outputs = network.predict(x)
File "/home/dingyuyang/EDSR-Tensorflow-master/model.py", line 172, in predict
return self.sess.run(self.out,feed_dict={self.input:x})
File "/home/dingyuyang/.conda/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 929, in run
run_metadata_ptr)
File "/home/dingyuyang/.conda/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1128, in _run
str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (50, 50, 3) for Tensor 'Placeholder:0', which has shape '(?, 50, 50, 3)'
can you help me?