Testing Model Performance on One Example in testing data set

Beginners
1 
image = Image.open(test_df['Paths'][image_index]).convert("RGB")
image

pixel_values = processor.feature_extractor(image, return_tensors="pt").pixel_values 
print("Pixel Values Shape:", pixel_values.shape)

generated_ids = model.generate(pixel_values)
print("Generated IDs:", generated_ids)

generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print("Generated Text:", generated_text)

I have the above code and it runs smoothly but there is no output when I try to print the generated text.

Screenshot 2023-06-12 at 3.59.25 PM
Screenshot 2023-06-12 at 3.59.25 PM1428×656 81 KB

My model was trained as follows:

model = VisionEncoderDecoderModel.from_encoder_decoder_pretrained(

"google/vit-base-patch16-224-in21k", "bert-base-chinese"

)

model.config.decoder.is_decoder = True

model.config.decoder.add_cross_attention = True

model.config.decoder_start_token_id = processor.tokenizer.cls_token_id

model.config.pad_token_id = processor.tokenizer.pad_token_id

model.config.vocab_size = model.config.decoder.vocab_size

model.config.eos_token_id = processor.tokenizer.sep_token_id

model.config.max_length = 64

model.config.early_stopping = True

model.config.no_repeat_ngram_size = 3

model.config.length_penalty = 2.0

model.config.num_beams = 4

training_args = Seq2SeqTrainingArguments(
    output_dir="./",
    evaluation_strategy="steps",
    learning_rate=1e-4,  # Decreased learning rate
    per_device_train_batch_size=10,  # Decreased batch size
    per_device_eval_batch_size=10,  # Decreased batch size
    weight_decay=0.01,
    save_total_limit=3,
    num_train_epochs=5,  # Decreased number of epochs
    logging_dir="./logs",
    logging_steps=500,  
    save_steps=1000,  
    save_strategy="steps",
    predict_with_generate=True,
    max_steps=100,
    gradient_accumulation_steps=2
)
cer_metric = load_metric("cer")

def compute_metrics(pred):
    labels_ids = pred.label_ids
    pred_ids = pred.predictions

    pred_str = processor.batch_decode(pred_ids, skip_special_tokens=True)
    labels_ids[labels_ids == -100] = processor.tokenizer.pad_token_id
    label_str = processor.batch_decode(labels_ids, skip_special_tokens=True)

    cer = cer_metric.compute(predictions=pred_str, references=label_str)

    return {"cer": cer}
os.environ["TOKENIZERS_PARALLELISM"] = "false"

optimizer = TorchAdamW(model.parameters(), lr=training_args.learning_rate)
scheduler = get_linear_schedule_with_warmup(
    optimizer,
    num_warmup_steps=500,
    num_training_steps=len(train_dataset) * training_args.num_train_epochs
)

# Create the trainer
trainer = Seq2SeqTrainer(
    model=model,
    tokenizer=processor.tokenizer,
    args=training_args,
    compute_metrics=compute_metrics,
    train_dataset=train_dataset,
    eval_dataset=test_dataset,
    data_collator=default_data_collator,
    optimizers=(optimizer, scheduler) 
)

# Train the model
trainer.train()

Please let me know how I can debug this!