Open ASH1998 opened 6 years ago
n_images_train: 82783 tl : Build Image Embeddings = InceptionV3 + Dense Layer / uses SlimNetsLayer and DenseLayer instead tensorlayer:Instantiate InputLayer input_image_layer: (64, 299, 299, 3) tensorlayer:Instantiate SlimNetsLayer InceptionV3: inception_v3 tensorlayer:Instantiate DenseLayer image_embedding: 512, identity tl : Build Seq Embedding EmbeddingInputlayer tensorlayer:Instantiate EmbeddingInputlayer seq_embedding: (12000, 512) tl : Build Model = image_embeddings + seq_embeddings + LSTMs + Dropout LSTM tensorlayer:Instantiate ReshapeLayer reshape_layer: (64, 1, 512) Tensor("lstm/reshape_layer:0", shape=(64, 1, 512), dtype=float32) tensorlayer:Instantiate DynamicRNNLayer embed: n_hidden:512, in_dim:3 (64, 1, 512), cell_fn:BasicLSTMCell, dropout:None, n_layer:1 batch_size (concurrent processes): 64 n_params : 2 Traceback (most recent call last): File "train_im2txt2im_coco_64.py", line 871, in <module> tf.app.run() File "/home/gcloud1998/.local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "train_im2txt2im_coco_64.py", line 517, in main softmax, net_img_rnn, net_seq_rnn, state_feed = Build_Model(mode, net_image_embeddings, net_seq_embeddings, target_seqs=None, input_mask=None) File "/home/gcloud1998/Desktop/im2txt2im/model_im2txt.py", line 598, in Build_Model name = 'embed', File "/home/gcloud1998/Desktop/im2txt2im/tensorlayer/layers.py", line 3506, in __init__ self.outputs = tf.reshape(tf.concat(1, outputs), [-1, n_hidden]) File "/home/gcloud1998/.local/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1121, in concat dtype=dtypes.int32).get_shape().assert_is_compatible_with( File "/home/gcloud1998/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1048, in convert_to_tensor as_ref=False) File "/home/gcloud1998/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1144, in internal_convert_to_tensor ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref) File "/home/gcloud1998/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 981, in _TensorTensorConversionFunction (dtype.name, t.dtype.name, str(t))) ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("lstm/embed/rnn/transpose_1:0", shape=(64, 1, 512), dtype=float32)'
Hello,do you solve it?
dany87kuo
commented
3 years ago dany87kuo
commented
3 years ago
n_images_train: 82783 tl : Build Image Embeddings = InceptionV3 + Dense Layer / uses SlimNetsLayer and DenseLayer instead tensorlayer:Instantiate InputLayer input_image_layer: (64, 299, 299, 3) tensorlayer:Instantiate SlimNetsLayer InceptionV3: inception_v3 tensorlayer:Instantiate DenseLayer image_embedding: 512, identity tl : Build Seq Embedding EmbeddingInputlayer tensorlayer:Instantiate EmbeddingInputlayer seq_embedding: (12000, 512) tl : Build Model = image_embeddings + seq_embeddings + LSTMs + Dropout LSTM tensorlayer:Instantiate ReshapeLayer reshape_layer: (64, 1, 512) Tensor("lstm/reshape_layer:0", shape=(64, 1, 512), dtype=float32) tensorlayer:Instantiate DynamicRNNLayer embed: n_hidden:512, in_dim:3 (64, 1, 512), cell_fn:BasicLSTMCell, dropout:None, n_layer:1 batch_size (concurrent processes): 64 n_params : 2 Traceback (most recent call last): File "train_im2txt2im_coco_64.py", line 871, in <module> tf.app.run() File "/home/gcloud1998/.local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "train_im2txt2im_coco_64.py", line 517, in main softmax, net_img_rnn, net_seq_rnn, state_feed = Build_Model(mode, net_image_embeddings, net_seq_embeddings, target_seqs=None, input_mask=None) File "/home/gcloud1998/Desktop/im2txt2im/model_im2txt.py", line 598, in Build_Model name = 'embed', File "/home/gcloud1998/Desktop/im2txt2im/tensorlayer/layers.py", line 3506, in __init__ self.outputs = tf.reshape(tf.concat(1, outputs), [-1, n_hidden]) File "/home/gcloud1998/.local/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1121, in concat dtype=dtypes.int32).get_shape().assert_is_compatible_with( File "/home/gcloud1998/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1048, in convert_to_tensor as_ref=False) File "/home/gcloud1998/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1144, in internal_convert_to_tensor ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref) File "/home/gcloud1998/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 981, in _TensorTensorConversionFunction (dtype.name, t.dtype.name, str(t))) ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("lstm/embed/rnn/transpose_1:0", shape=(64, 1, 512), dtype=float32)'