# C3W3\_Assignment 3 - Error thrown just prior to end of first epoch **URL:** \ **Category:** Natural Language Processing in TensorFlow\ **Created:** [December 30, 2023, 11:25pm UTC](https://community.deeplearning.ai/t/c3w3-assignment-3-error-thrown-just-prior-to-end-of-first-epoch/531245 "2023-12-30T23:25:07Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![Raymond\_Hawthorne](https://avatars.discourse-cdn.com/v4/letter/r/439d5e/32.png) [@Raymond\_Hawthorne](https://community.deeplearning.ai/u/Raymond_Hawthorne)\ **Post date:** [December 30, 2023, 11:25pm UTC](https://community.deeplearning.ai/t/c3w3-assignment-3-error-thrown-just-prior-to-end-of-first-epoch/531245/1 "2023-12-30T23:25:07Z")
When trying to train the model (under a number of different architectures), I’m getting the following error just prior to the first epoch completing: UnimplementedError: Cast string to float is not supported [[node binary\_crossentropy/Cast (defined at /opt/conda/lib/python3.8/site-packages/keras/losses.py:1797) ]] [Op:\_\_inference\_test\_function\_64273] Errors may have originated from an input operation. Input Source operations connected to node binary\_crossentropy/Cast: In[0] ExpandDims (defined at /opt/conda/lib/python3.8/site-packages/keras/engine/compile\_utils.py:677) The cells at the start of the assignment are showing the expected outputs. Anyone else run into this issue and have suggestions on things I may be able to try to resolve? ---
**Author:** ![Deepti\_Prasad](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/deepti_prasad/32/165831_2.png) [@Deepti\_Prasad](https://community.deeplearning.ai/u/Deepti_Prasad)\ **Post date:** [December 31, 2023, 3:36pm UTC](https://community.deeplearning.ai/t/c3w3-assignment-3-error-thrown-just-prior-to-end-of-first-epoch/531245/2 "2023-12-31T15:36:59Z")
Hello Raymond, Can you share a screenshot of the image of your error without sharing any codes. Kindly look at your model compile statement where your function call from strong to float is creating this error. ---
**Author:** ![balaji.ambresh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/balaji.ambresh/32/128697_2.png) [@balaji.ambresh](https://community.deeplearning.ai/u/balaji.ambresh)\ **Post date:** [December 31, 2023, 4:50pm UTC](https://community.deeplearning.ai/t/c3w3-assignment-3-error-thrown-just-prior-to-end-of-first-epoch/531245/3 "2023-12-31T16:50:20Z")
Labels should be numeric. ---
**Author:** ![Raymond\_Hawthorne](https://avatars.discourse-cdn.com/v4/letter/r/439d5e/32.png) [@Raymond\_Hawthorne](https://community.deeplearning.ai/u/Raymond_Hawthorne)\ **Post date:** [January 1, 2024, 12:48am UTC](https://community.deeplearning.ai/t/c3w3-assignment-3-error-thrown-just-prior-to-end-of-first-epoch/531245/4 "2024-01-01T00:48:33Z")
## Hello Deepti, The stack trace is pretty long. But here it is: Epoch 1/20 4493/4500 [============================\>.] - ETA: 0s - loss: 0.5779 - accuracy: 0.6899 UnimplementedError Traceback (most recent call last) in 5 6 # Train the model and save the training history ----\> 7 history = model.fit(train\_pad\_trunc\_seq, train\_labels, epochs=20, validation\_data=(val\_pad\_trunc\_seq, val\_labels)) /opt/conda/lib/python3.8/site-packages/keras/utils/traceback\_utils.py in error\_handler(\*args, \*\*kwargs) 65 except Exception as e: # pylint: disable=broad-except 66 filtered\_tb = \_process\_traceback\_frames(e. **traceback** ) —\> 67 raise e.with\_traceback(filtered\_tb) from None 68 finally: 69 del filtered\_tb /opt/conda/lib/python3.8/site-packages/tensorflow/python/eager/execute.py in quick\_execute(op\_name, num\_outputs, inputs, attrs, ctx, name) 56 try: 57 ctx.ensure\_initialized() —\> 58 tensors = pywrap\_tfe.TFE\_Py\_Execute(ctx.\_handle, device\_name, op\_name, 59 inputs, attrs, num\_outputs) 60 except core.\_NotOkStatusException as e: UnimplementedError: Cast string to float is not supported [[node binary\_crossentropy/Cast (defined at /opt/conda/lib/python3.8/site-packages/keras/losses.py:1797) ]] [Op:\_\_inference\_test\_function\_19035] Errors may have originated from an input operation. Input Source operations connected to node binary\_crossentropy/Cast: In[0] ExpandDims (defined at /opt/conda/lib/python3.8/site-packages/keras/engine/compile\_utils.py:677) Operation defined at: (most recent call last) > > > File “/opt/conda/lib/python3.8/runpy.py”, line 194, in \_run\_module\_as\_main > > > return \_run\_code(code, main\_globals, None, > > > > > > File “/opt/conda/lib/python3.8/runpy.py”, line 87, in \_run\_code > > > exec(code, run\_globals) > > > > > > File “/opt/conda/lib/python3.8/site-packages/ipykernel\_launcher.py”, line 16, in > > > app.launch\_new\_instance() > > > > > > File “/opt/conda/lib/python3.8/site-packages/traitlets/config/application.py”, line 845, in launch\_instance > > > app.start() > > > > > > File “/opt/conda/lib/python3.8/site-packages/ipykernel/kernelapp.py”, line 612, in start > > > self.io\_loop.start() > > > > > > File “/opt/conda/lib/python3.8/site-packages/tornado/platform/asyncio.py”, line 199, in start > > > self.asyncio\_loop.run\_forever() > > > > > > File “/opt/conda/lib/python3.8/asyncio/base\_events.py”, line 570, in run\_forever > > > self.\_run\_once() > > > > > > File “/opt/conda/lib/python3.8/asyncio/base\_events.py”, line 1859, in \_run\_once > > > handle.\_run() > > > > > > File “/opt/conda/lib/python3.8/asyncio/events.py”, line 81, in \_run > > > self.\_context.run(self.\_callback, \*self.\_args) > > > > > > File “/opt/conda/lib/python3.8/site-packages/tornado/ioloop.py”, line 688, in > > > lambda f: self.\_run\_callback(functools.partial(callback, future)) > > > > > > File “/opt/conda/lib/python3.8/site-packages/tornado/ioloop.py”, line 741, in \_run\_callback > > > ret = callback() > > > > > > File “/opt/conda/lib/python3.8/site-packages/tornado/gen.py”, line 814, in inner > > > self.ctx\_run(self.run) > > > > > > File “/opt/conda/lib/python3.8/site-packages/tornado/gen.py”, line 775, in run > > > yielded = self.gen.send(value) > > > > > > File “/opt/conda/lib/python3.8/site-packages/ipykernel/kernelbase.py”, line 374, in dispatch\_queue > > > yield self.process\_one() > > > > > > File “/opt/conda/lib/python3.8/site-packages/tornado/gen.py”, line 250, in wrapper > > > runner = Runner(ctx\_run, result, future, yielded) > > > > > > File “/opt/conda/lib/python3.8/site-packages/tornado/gen.py”, line 741, in **init** > > > self.ctx\_run(self.run) > > > > > > File “/opt/conda/lib/python3.8/site-packages/tornado/gen.py”, line 775, in run > > > yielded = self.gen.send(value) > > > > > > File “/opt/conda/lib/python3.8/site-packages/ipykernel/kernelbase.py”, line 358, in process\_one > > > yield gen.maybe\_future(dispatch(\*args)) > > > > > > File “/opt/conda/lib/python3.8/site-packages/tornado/gen.py”, line 234, in wrapper > > > yielded = ctx\_run(next, result) > > > > > > File “/opt/conda/lib/python3.8/site-packages/ipykernel/kernelbase.py”, line 261, in dispatch\_shell > > > yield gen.maybe\_future(handler(stream, idents, msg)) > > > > > > File “/opt/conda/lib/python3.8/site-packages/tornado/gen.py”, line 234, in wrapper > > > yielded = ctx\_run(next, result) > > > > > > File “/opt/conda/lib/python3.8/site-packages/ipykernel/kernelbase.py”, line 536, in execute\_request > > > self.do\_execute( > > > > > > File “/opt/conda/lib/python3.8/site-packages/tornado/gen.py”, line 234, in wrapper > > > yielded = ctx\_run(next, result) > > > > > > File “/opt/conda/lib/python3.8/site-packages/ipykernel/ipkernel.py”, line 302, in do\_execute > > > res = shell.run\_cell(code, store\_history=store\_history, silent=silent) > > > > > > File “/opt/conda/lib/python3.8/site-packages/ipykernel/zmqshell.py”, line 539, in run\_cell > > > return super(ZMQInteractiveShell, self).run\_cell(\*args, \*\*kwargs) > > > > > > File “/opt/conda/lib/python3.8/site-packages/IPython/core/interactiveshell.py”, line 2894, in run\_cell > > > result = self.\_run\_cell( > > > > > > File “/opt/conda/lib/python3.8/site-packages/IPython/core/interactiveshell.py”, line 2940, in \_run\_cell > > > return runner(coro) > > > > > > File “/opt/conda/lib/python3.8/site-packages/IPython/core/async\_helpers.py”, line 68, in \_pseudo\_sync\_runner > > > coro.send(None) > > > > > > File “/opt/conda/lib/python3.8/site-packages/IPython/core/interactiveshell.py”, line 3165, in run\_cell\_async > > > has\_raised = await self.run\_ast\_nodes(code\_ast.body, cell\_name, > > > > > > File “/opt/conda/lib/python3.8/site-packages/IPython/core/interactiveshell.py”, line 3357, in run\_ast\_nodes > > > if (await self.run\_code(code, result, async\_=asy)): > > > > > > File “/opt/conda/lib/python3.8/site-packages/IPython/core/interactiveshell.py”, line 3437, in run\_code > > > exec(code\_obj, self.user\_global\_ns, self.user\_ns) > > > > > > File “”, line 7, in > > > history = model.fit(train\_pad\_trunc\_seq, train\_labels, epochs=20, validation\_data=(val\_pad\_trunc\_seq, val\_labels)) > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/utils/traceback\_utils.py”, line 64, in error\_handler > > > return fn(\*args, \*\*kwargs) > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/engine/training.py”, line 1252, in fit > > > val\_logs = self.evaluate( > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/utils/traceback\_utils.py”, line 64, in error\_handler > > > return fn(\*args, \*\*kwargs) > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/engine/training.py”, line 1537, in evaluate > > > tmp\_logs = self.test\_function(iterator) > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/engine/training.py”, line 1366, in test\_function > > > return step\_function(self, iterator) > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/engine/training.py”, line 1356, in step\_function > > > outputs = model.distribute\_strategy.run(run\_step, args=(data,)) > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/engine/training.py”, line 1349, in run\_step > > > outputs = model.test\_step(data) > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/engine/training.py”, line 1305, in test\_step > > > self.compiled\_loss( > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/engine/compile\_utils.py”, line 201, in **call** > > > loss\_value = loss\_obj(y\_t, y\_p, sample\_weight=sw) > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/losses.py”, line 141, in **call** > > > losses = call\_fn(y\_true, y\_pred) > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/losses.py”, line 245, in call > > > return ag\_fn(y\_true, y\_pred, \*\*self.\_fn\_kwargs) > > > > > > File “/opt/conda/lib/python3.8/site-packages/keras/losses.py”, line 1797, in binary\_crossentropy > > > y\_true = tf.cast(y\_true, y\_pred.dtype) ---
**Author:** ![Raymond\_Hawthorne](https://avatars.discourse-cdn.com/v4/letter/r/439d5e/32.png) [@Raymond\_Hawthorne](https://community.deeplearning.ai/u/Raymond_Hawthorne)\ **Post date:** [January 1, 2024, 12:54am UTC](https://community.deeplearning.ai/t/c3w3-assignment-3-error-thrown-just-prior-to-end-of-first-epoch/531245/5 "2024-01-01T00:54:27Z")
The labels are of type int. ---
**Author:** ![balaji.ambresh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/balaji.ambresh/32/128697_2.png) [@balaji.ambresh](https://community.deeplearning.ai/u/balaji.ambresh)\ **Post date:** [January 1, 2024, 3:29am UTC](https://community.deeplearning.ai/t/c3w3-assignment-3-error-thrown-just-prior-to-end-of-first-epoch/531245/6 "2024-01-01T03:29:15Z")
Apparently not. See here: ```auto UnimplementedError: Cast string to float is not supported [[node binary_crossentropy/Cast (defined at /opt/conda/lib/python3.8/site-packages/keras/losses.py:1797) ]] [Op:__inference_test_function_19035] ``` and here: ```auto File “/opt/conda/lib/python3.8/site-packages/keras/losses.py”, line 1797, in binary_crossentropy y_true = tf.cast(y_true, y_pred.dtype) ``` If this doesn’t help, please click my name and message your notebook as an attachment. ---
**Author:** ![Raymond\_Hawthorne](https://avatars.discourse-cdn.com/v4/letter/r/439d5e/32.png) [@Raymond\_Hawthorne](https://community.deeplearning.ai/u/Raymond_Hawthorne)\ **Post date:** [January 1, 2024, 1:49pm UTC](https://community.deeplearning.ai/t/c3w3-assignment-3-error-thrown-just-prior-to-end-of-first-epoch/531245/7 "2024-01-01T13:49:18Z")
@balaji.ambresh Yep. You are correct. I accidentally set validation\_labels to be sentences split on the training size instead of the _labels_ with the appropriate split. Oof. Thank you and Happy New Year! ---
**Author:** ![sako](https://avatars.discourse-cdn.com/v4/letter/s/e9bcb4/32.png) [@sako](https://community.deeplearning.ai/u/sako)\ **Post date:** [February 16, 2024, 2:40pm UTC](https://community.deeplearning.ai/t/c3w3-assignment-3-error-thrown-just-prior-to-end-of-first-epoch/531245/8 "2024-02-16T14:40:01Z")
got exactly the same error, thanks for the answer mate.